diff --git a/assets/Bando_Dottorato_di_Ricerca_XLI_ciclo_Comunicazione_1750159552604_0.pdf b/assets/Bando_Dottorato_di_Ricerca_XLI_ciclo_Comunicazione_1750159552604_0.pdf new file mode 100644 index 00000000..578c5ca9 Binary files /dev/null and b/assets/Bando_Dottorato_di_Ricerca_XLI_ciclo_Comunicazione_1750159552604_0.pdf differ diff --git a/assets/Orario_definitivo_prima_settimana_1750056154238_0.edn b/assets/Orario_definitivo_prima_settimana_1750056154238_0.edn new file mode 100644 index 00000000..963aa3a7 --- /dev/null +++ b/assets/Orario_definitivo_prima_settimana_1750056154238_0.edn @@ -0,0 +1,66 @@ +{:highlights [{:id #uuid "684fbd0a-e948-4f25-9fd4-4ca045edad83", + :page 1, + :position {:bounding {:x1 486.5487976074219, + :y1 498.4389343261719, + :x2 601.209716796875, + :y2 634.2398681640625, + :width 777.9999999999999, + :height 1100.4935483870966}, + :rects ({:x1 486.5487976074219, + :y1 498.4389343261719, + :x2 601.209716796875, + :y2 511.5842590332031, + :width 777.9999999999999, + :height 1100.4935483870966} + {:x1 486.5487976074219, + :y1 512.5199584960938, + :x2 600.4761962890625, + :y2 525.665283203125, + :width 777.9999999999999, + :height 1100.4935483870966} + {:x1 486.5487976074219, + :y1 526.931884765625, + :x2 504.9493713378906, + :y2 540.0772705078125, + :width 777.9999999999999, + :height 1100.4935483870966} + {:x1 486.5487976074219, + :y1 543.8770751953125, + :x2 600.4428100585938, + :y2 557.0223999023438, + :width 777.9999999999999, + :height 1100.4935483870966} + {:x1 486.5487976074219, + :y1 558.277587890625, + :x2 533.0376586914062, + :y2 571.4229736328125, + :width 777.9999999999999, + :height 1100.4935483870966} + {:x1 486.5487976074219, + :y1 572.8036499023438, + :x2 574.1879272460938, + :y2 585.9490356445312, + :width 777.9999999999999, + :height 1100.4935483870966} + {:x1 486.5487976074219, + :y1 587.2156372070312, + :x2 528.8746948242188, + :y2 600.3609619140625, + :width 777.9999999999999, + :height 1100.4935483870966} + {:x1 486.5487976074219, + :y1 604.1493530273438, + :x2 574.6978759765625, + :y2 617.2947387695312, + :width 777.9999999999999, + :height 1100.4935483870966} + {:x1 486.5487976074219, + :y1 621.0945434570312, + :x2 569.527099609375, + :y2 634.2398681640625, + :width 777.9999999999999, + :height 1100.4935483870966}), + :page 1}, + :content {:text "Introduzione al dominio applicativo “Generative AI”: Large Language Models e loro uso nell'ingegneria del software(area Informatica)(Davide Di Ruscio"}, + :properties {:color "green"}}], + :extra {:page 1}} diff --git a/assets/Orario_definitivo_prima_settimana_1750056154238_0.pdf b/assets/Orario_definitivo_prima_settimana_1750056154238_0.pdf new file mode 100644 index 00000000..f77f81fa Binary files /dev/null and b/assets/Orario_definitivo_prima_settimana_1750056154238_0.pdf differ diff --git a/assets/SERVICES_DOTTORATO.edn b/assets/SERVICES_DOTTORATO.edn index 285f9a8b..c3eb3071 100644 --- a/assets/SERVICES_DOTTORATO.edn +++ b/assets/SERVICES_DOTTORATO.edn @@ -1 +1 @@ -{:highlights [], :extra {:page 10}} +{:highlights [], :extra {:page 7}} diff --git a/assets/image_1750085408113_0.png b/assets/image_1750085408113_0.png new file mode 100644 index 00000000..622cb37f Binary files /dev/null and b/assets/image_1750085408113_0.png differ diff --git a/assets/image_1750241099606_0.png b/assets/image_1750241099606_0.png new file mode 100644 index 00000000..49fa272c Binary files /dev/null and b/assets/image_1750241099606_0.png differ diff --git a/assets/image_1750241493088_0.png b/assets/image_1750241493088_0.png new file mode 100644 index 00000000..63a672b9 Binary files /dev/null and b/assets/image_1750241493088_0.png differ diff --git a/assets/image_1750241756355_0.png b/assets/image_1750241756355_0.png new file mode 100644 index 00000000..68d4178e Binary files /dev/null and b/assets/image_1750241756355_0.png differ diff --git a/assets/image_1750241967042_0.png b/assets/image_1750241967042_0.png new file mode 100644 index 00000000..7cebac24 Binary files /dev/null and b/assets/image_1750241967042_0.png differ diff --git a/assets/image_1750338527527_0.png b/assets/image_1750338527527_0.png new file mode 100644 index 00000000..629eca48 Binary files /dev/null and b/assets/image_1750338527527_0.png differ diff --git a/assets/image_1750338537901_0.png b/assets/image_1750338537901_0.png new file mode 100644 index 00000000..ae7e2376 Binary files /dev/null and b/assets/image_1750338537901_0.png differ diff --git a/assets/image_1750338557774_0.png b/assets/image_1750338557774_0.png new file mode 100644 index 00000000..b3040692 Binary files /dev/null and b/assets/image_1750338557774_0.png differ diff --git a/assets/image_1750338587417_0.png b/assets/image_1750338587417_0.png new file mode 100644 index 00000000..86dd2b92 Binary files /dev/null and b/assets/image_1750338587417_0.png differ diff --git a/assets/image_1750338631965_0.png b/assets/image_1750338631965_0.png new file mode 100644 index 00000000..c90c088f Binary files /dev/null and b/assets/image_1750338631965_0.png differ diff --git a/assets/image_1750338755324_0.png b/assets/image_1750338755324_0.png new file mode 100644 index 00000000..26083ebf Binary files /dev/null and b/assets/image_1750338755324_0.png differ diff --git a/assets/image_1750338804683_0.png b/assets/image_1750338804683_0.png new file mode 100644 index 00000000..28104ef6 Binary files /dev/null and b/assets/image_1750338804683_0.png differ diff --git a/assets/image_1750339418053_0.png b/assets/image_1750339418053_0.png new file mode 100644 index 00000000..f16aeb21 Binary files /dev/null and b/assets/image_1750339418053_0.png differ diff --git a/assets/image_1750339701109_0.png b/assets/image_1750339701109_0.png new file mode 100644 index 00000000..e69de29b diff --git a/assets/storages/logseq-citation-manager/Biblioteca-zotero.bib b/assets/storages/logseq-citation-manager/Biblioteca-zotero.bib index da8f8086..59175e23 100644 --- a/assets/storages/logseq-citation-manager/Biblioteca-zotero.bib +++ b/assets/storages/logseq-citation-manager/Biblioteca-zotero.bib @@ -2978,7 +2978,9 @@ This paper investigates the conceptual and technical feasibility of a new softwa \par 8E5M8QKA\{"readingTime":\{"page":12,"data":\{"0":530,"1":1430,"2":1400,"3":1140,"4":450,"5":240,"6":330,"7":210,"8":250,"9":50\}\}\} \par -9G4B4RYG\{"readingTime":\{"page":477,"data":\{"0":10,"2":10,"3":20,"4":10,"7":20,"14":10,"17":140,"18":40,"19":10,"20":40,"21":30,"22":10,"25":220,"26":180,"27":140,"28":110,"29":40,"30":40,"31":340,"32":250,"33":80,"399":10,"400":20\}\}\} +9F5F2G9D\{"readingTime":\{"page":8,"data":\{"0":50\}\}\} +\par +9G4B4RYG\{"readingTime":\{"page":477,"data":\{"0":20,"2":10,"3":20,"4":10,"7":20,"14":10,"17":140,"18":40,"19":10,"20":40,"21":30,"22":10,"25":220,"26":180,"27":140,"28":110,"29":40,"30":40,"31":340,"32":250,"33":90,"34":300,"35":340,"36":490,"37":220,"38":400,"39":230,"40":80,"399":10,"400":20\}\}\} \par 9QF9CWEH\{"readingTime":\{"page":44,"data":\{"0":30\}\}\} \par @@ -2986,6 +2988,8 @@ This paper investigates the conceptual and technical feasibility of a new softwa \par 9VTMURYV\{"readingTime":\{"page":9,"data":\{"3":10\}\}\} \par +66AQQ5ZI\{"readingTime":\{"page":4,"data":\{"0":430,"1":680,"2":780,"3":490\}\}\} +\par 78JSCZMI\{"readingTime":\{"page":12,"data":\{"0":810,"1":1060,"2":440,"3":610,"4":430,"5":520,"6":760,"7":220,"8":430,"9":500,"10":200\}\}\} \par 836S4XI5\{"readingTime":\{"page":79,"data":\{"0":20,"3":10,"9":10,"12":10,"13":10\}\}\} @@ -3052,7 +3056,7 @@ PSRA6HK6\{"readingTime":\{"page":76,"data":\{"0":10\}\}\} \par RUKHUVV6\{"readingTime":\{"page":58,"data":\{"1":160,"11":10,"25":10,"39":10,"44":10,"45":20,"46":20,"51":30,"52":10\}\}\} \par -SJH2XINQ\{"readingTime":\{"page":80,"data":\{"0":100,"1":150,"2":120,"3":30,"4":40,"5":10,"6":10,"8":10,"11":10,"15":10,"18":10,"21":10,"22":50,"23":50,"24":20,"25":50,"26":210,"27":20,"31":10,"32":10,"33":10,"34":10,"37":10,"39":10\}\}\} +SJH2XINQ\{"readingTime":\{"page":80,"data":\{"0":120,"1":180,"2":130,"3":50,"4":40,"5":20,"6":10,"7":20,"8":30,"11":20,"12":10,"15":10,"17":10,"18":10,"19":20,"21":20,"22":90,"23":50,"24":20,"25":50,"26":210,"27":20,"28":10,"29":80,"31":10,"32":10,"33":30,"34":80,"37":20,"38":20,"39":120,"40":30,"41":80,"45":10,"49":10,"52":10,"57":10\}\}\} \par TK8XNYNL\{"readingTime":\{"page":15,"data":\{"0":10,"1":10\}\}\} \par @@ -3425,6 +3429,15 @@ TL;DR Analysis reveals that PLBART learns program syntax, style, logical flow, and style that are crucial to program semantics and thus excels even with limited annotations, and outperforms or rivals state-of-the-art models.} } +@online{AIAgentCapabilities, + title = {{{AI Agent Capabilities Periodic Table}}}, + url = {https://www.digitaltwinconsortium.org/initiatives/ai-agent-capabilities-periodic-table/}, + urldate = {2025-06-19}, + abstract = {The AI Agent Capability Table enables scalable, ethical, and intelligent AI-twin integration across platforms and industries.}, + langid = {american}, + organization = {Digital Twin Consortium} +} + @online{AiAgenticAgents, title = {\#ai \#agentic \#agents \#opensource \#rag \#mcp | {{Eduardo Ordax}} | 60 Commenti}, url = {https://www.linkedin.com/posts/eordax_ai-agentic-agents-activity-7328742367086227456-6T2P}, @@ -5186,7 +5199,8 @@ The definitions, architecture, fundamental technologies, and applications of IoT publisher = {Packt Publishing}, location = {Birmingham}, abstract = {Go beyond foundational LangChain documentation with detailed coverage of LangGraph interfaces, design patterns for building AI agents, and scalable architectures used in production--ideal for Python developers building GenAI applications Key Features Bridge the gap between prototype and production with robust LangGraph agent architectures Apply enterprise-grade practices for testing, observability, and monitoring Build specialized agents for software development and data analysis Purchase of the print or Kindle book includes a free PDF eBook Book Description This second edition tackles the biggest challenge facing companies in AI today: moving from prototypes to production. Fully updated to reflect the latest developments in the LangChain ecosystem, it captures how modern AI systems are developed, deployed, and scaled in enterprise environments. This edition places a strong focus on multi-agent architectures, robust LangGraph workflows, and advanced retrieval-augmented generation (RAG) pipelines. You'll explore design patterns for building agentic systems, with practical implementations of multi-agent setups for complex tasks. The book guides you through reasoning techniques such as Tree-of -Thoughts, structured generation, and agent handoffs--complete with error handling examples. Expanded chapters on testing, evaluation, and deployment address the demands of modern LLM applications, showing you how to design secure, compliant AI systems with built-in safeguards and responsible development principles. This edition also expands RAG coverage with guidance on hybrid search, re-ranking, and fact-checking pipelines to enhance output accuracy. Whether you're extending existing workflows or architecting multi-agent systems from scratch, this book provides the technical depth and practical instruction needed to design LLM applications ready for success in production environments. What you will learn Design and implement multi-agent systems using LangGraph Implement testing strategies that identify issues before deployment Deploy observability and monitoring solutions for production environments Build agentic RAG systems with re-ranking capabilities Architect scalable, production-ready AI agents using LangGraph and MCP Work with the latest LLMs and providers like Google Gemini, Anthropic, Mistral, DeepSeek, and OpenAI's o3-mini Design secure, compliant AI systems aligned with modern ethical practices Who this book is for This book is for developers, researchers, and anyone looking to learn more about LangChain and LangGraph. With a strong emphasis on enterprise deployment patterns, it's especially valuable for teams implementing LLM solutions at scale. While the first edition focused on individual developers, this updated edition expands its reach to support engineering teams and decision-makers working on enterprise-scale LLM strategies. A basic understanding of Python is required, and familiarity with machine learning will help you get the most out of this book}, - langid = {english} + langid = {english}, + keywords = {LOGSEQ} } @article{augusteijnNeuralNetworkClassification2002, @@ -29145,6 +29159,8 @@ An effective optimization approach, which integrated the probabilistic surrogate shorttitle = {Management of {{Self-Admitted Technical Debt}} Using {{Machine Learning}}}, author = {Li, Yikun}, date = {2024-04-23}, + eprint = {11370/0212b8bb-b0af-481d-9f17-a943d0356a90}, + eprinttype = {hdl}, institution = {University of Groningen}, doi = {10.33612/diss.972242960}, langid = {english} @@ -29342,7 +29358,7 @@ Comment: 7 pages, 3 figures, IEEE conference format} title = {Proposed Title: {{IoT-native}} Software Engineering}, author = {Li, Zheng and O’Brien, Liam and Yang, Ye and Gorton, Ian}, langid = {english}, - note = {{$<$}!-- ~== For your convenience, this form can be processed by EasyChair ~== automatically. You can fill out this form offline and then upload it ~== to EasyChair. Several review forms can be uploaded simultaneously. ~== You can modify your reviews as many times as you want. ~== ~== When filling out the review form please mind the following rules: ~== ~== (1) Blocks such as this are comments. EasyChair will ignore them. ~== ~ ~ Do not write any text into these blocks as it will be ignored. ~== ~ ~ You can add comments to the review form or remove them. ~== (2) Write only into the tags where instructed. Do not modify any ~== ~ ~ tags and attributes, or the review will become unusable and will ~== ~ ~ be rejected by EasyChair. ~--{$><$}review id=":7075322::3424433" ~ ~ ~ ~submission="35" ~ ~ ~ ~title="IoT-native Software Engineering" ~ ~ ~ ~authors="Zheng Li, ~ ~ ~ ~ ~ ~ ~ ~ Liam O'Brien, ~ ~ ~ ~ ~ ~ ~ ~ Ye Yang, ~ ~ ~ ~ ~ ~ ~ ~ Ian Gorton" ~ ~ ~ ~pc\_member="Davide Di Ruscio"{$><$}field id="611399" name="SCORE: Overall evaluation of the submitted document"{$>$} ~{$<$}!-- ~ ~== This field defines the "proposal overall quality". ~ ~--{$>$} ~{$<$}score{$>$} ~{$<$}!-- ~ ~== Select your choice from the options below and write its number below, ~ ~== before the {$<$}/score{$>$} tag. ~ ~== ~ ~== 3 Accept ~ ~== 2 Borderline ~ ~== 1 Reject ~ ~--{$>$} ~ ~ ~{$<$}/score{$><$}/field{$><$}!-- ~ ~ Additional Scores ~ ~ --{$><$}field id="611401" name="TOPIC Rating (1-100)"{$>$} ~{$<$}!-- ~ ~== This field represents the importance of the TOPIC presented ~ ~== (independently from the proposal quality) ~ ~--{$>$} ~{$<$}score{$>$} ~{$<$}!-- ~ ~== Select your choice from the options below and write its number below, ~ ~== before the {$<$}/score{$>$} tag. ~ ~== ~ ~== 5 (81-100) Strong TOPIC that definitively should be published. ~ ~== 4 (61-80) Interesting TOPIC that most likely will generate interest; ~ ~== 3 (41-60) Potentially a good TOPIC; ~ ~== 2 (21-40) Weak TOPIC; ~ ~== 1 (1-20) Very weak TOPIC that should not be published; ~ ~--{$>$} ~ ~ ~{$<$}/score{$><$}/field{$><$}field id="611402" name="Is the Topic relevant and timely?"{$>$} ~{$<$}!-- ~ ~== Please describe if the topic is of importance for the IEEE SW ~ ~--{$>$} ~{$<$}score{$>$} ~{$<$}!-- ~ ~== Select your choice from the options below and write its number below, ~ ~== before the {$<$}/score{$>$} tag. ~ ~== ~ ~== 2 Yes ~ ~== 1 Not ~ ~--{$>$} ~ ~ ~{$<$}/score{$><$}/field{$><$}field id="611403" name="Do you expect this theme issue to attract an adequate number of submissions?"{$>$} ~{$<$}!-- ~ ~== Please describe if the guest editors are supposed to be able to ~ ~== attract an adequate ({$>>$}10) number of submissions. ~ ~--{$>$} ~{$<$}score{$>$} ~{$<$}!-- ~ ~== Select your choice from the options below and write its number below, ~ ~== before the {$<$}/score{$>$} tag. ~ ~== ~ ~== 3 I expect a high number of submissions. ~ ~== 2 I expect a proper number of submissions; ~ ~== 1 I expect a limited number of submissions; ~ ~--{$>$} ~ ~ ~{$<$}/score{$><$}/field{$><$}!-- ~ ~ Review ~ ~ --{$><$}field id="611405" name="Review"{$>$} ~{$<$}!-- ~ ~== Please provide a detailed review, including justification for your ~ ~== scores. This field is required. ~ ~--{$>$} ~{$<$}text required="required"{$>$} ~{$<$}!-- ~ ~== Enter the text for the field ~ ~== ~ Review ~ ~== below. This field is required. ~ ~--{$>$}The proposal is too broad. It aims at covering "any aspect of IoT-native Software Engineering", which is risky. For instance, proponents should decide if they want to elicit empirical studies or experience reports. In any case, I don't think pure empirical studies can be appropriate for this venue especially considering the length of typical IEEE Software papers. Overall, it is not clear the need that the proponents aim to fill. ~{$<$}/text{$><$}/field{$><$}field id="611406" name="Confidential remarks for the board members"{$>$} ~{$<$}!-- ~ ~== If you wish to add any remarks intended only for board members ~ ~== please write them below. These remarks will only be seen by the ~ ~== board members having access to reviews for this submission. They ~ ~== will not be sent to the authors. This field is optional. ~ ~--{$>$} ~{$<$}text optional="optional"{$>$} ~{$<$}!-- ~ ~== Enter the text for the field ~ ~== ~ Confidential remarks for the board members ~ ~== below. This field is optional. ~ ~--{$>$} ~{$<$}/text{$><$}/field{$><$}reviewer{$>$} ~{$<$}!-- ~ ~== If the review was written by (or with the help from) a subreviewer ~ ~== different from the PC member in charge, add information about ~ ~== the subreviewer below. Write subreviewer's first name, last name ~ ~== and email between the tags below. ~ ~--{$>$} ~{$<$}first\_name{$>$} ~{$<$}/first\_name{$>$} ~{$<$}last\_name{$>$} ~ {$<$}/last\_name{$>$} ~{$<$}email{$>$} ~{$<$}/email{$><$}/reviewer{$><$}/review{$>$}} + note = {\texttt{{$<$}!-- ~== For your convenience, this form can be processed by EasyChair ~== automatically. You can fill out this form offline and then upload it ~== to EasyChair. Several review forms can be uploaded simultaneously. ~== You can modify your reviews as many times as you want. ~== ~== When filling out the review form please mind the following rules: ~== ~== (1) Blocks such as this are comments. EasyChair will ignore them. ~== ~ ~ Do not write any text into these blocks as it will be ignored. ~== ~ ~ You can add comments to the review form or remove them. ~== (2) Write only into the tags where instructed. Do not modify any ~== ~ ~ tags and attributes, or the review will become unusable and will ~== ~ ~ be rejected by EasyChair. ~--{$><$}review id=":7075322::3424433" ~ ~ ~ ~submission="35" ~ ~ ~ ~title="IoT-native Software Engineering" ~ ~ ~ ~authors="Zheng Li, ~ ~ ~ ~ ~ ~ ~ ~ Liam O'Brien, ~ ~ ~ ~ ~ ~ ~ ~ Ye Yang, ~ ~ ~ ~ ~ ~ ~ ~ Ian Gorton" ~ ~ ~ ~pc\_member="Davide Di Ruscio"{$><$}field id="611399" name="SCORE: Overall evaluation of the submitted document"{$>$} ~{$<$}!-- ~ ~== This field defines the "proposal overall quality". ~ ~--{$>$} ~{$<$}score{$>$} ~{$<$}!-- ~ ~== Select your choice from the options below and write its number below, ~ ~== before the {$<$}/score{$>$} tag. ~ ~== ~ ~== 3 Accept ~ ~== 2 Borderline ~ ~== 1 Reject ~ ~--{$>$} ~ ~ ~{$<$}/score{$><$}/field{$><$}!-- ~ ~ Additional Scores ~ ~ --{$><$}field id="611401" name="TOPIC Rating (1-100)"{$>$} ~{$<$}!-- ~ ~== This field represents the importance of the TOPIC presented ~ ~== (independently from the proposal quality) ~ ~--{$>$} ~{$<$}score{$>$} ~{$<$}!-- ~ ~== Select your choice from the options below and write its number below, ~ ~== before the {$<$}/score{$>$} tag. ~ ~== ~ ~== 5 (81-100) Strong TOPIC that definitively should be published. ~ ~== 4 (61-80) Interesting TOPIC that most likely will generate interest; ~ ~== 3 (41-60) Potentially a good TOPIC; ~ ~== 2 (21-40) Weak TOPIC; ~ ~== 1 (1-20) Very weak TOPIC that should not be published; ~ ~--{$>$} ~ ~ ~{$<$}/score{$><$}/field{$><$}field id="611402" name="Is the Topic relevant and timely?"{$>$} ~{$<$}!-- ~ ~== Please describe if the topic is of importance for the IEEE SW ~ ~--{$>$} ~{$<$}score{$>$} ~{$<$}!-- ~ ~== Select your choice from the options below and write its number below, ~ ~== before the {$<$}/score{$>$} tag. ~ ~== ~ ~== 2 Yes ~ ~== 1 Not ~ ~--{$>$} ~ ~ ~{$<$}/score{$><$}/field{$><$}field id="611403" name="Do you expect this theme issue to attract an adequate number of submissions?"{$>$} ~{$<$}!-- ~ ~== Please describe if the guest editors are supposed to be able to ~ ~== attract an adequate ({$>>$}10) number of submissions. ~ ~--{$>$} ~{$<$}score{$>$} ~{$<$}!-- ~ ~== Select your choice from the options below and write its number below, ~ ~== before the {$<$}/score{$>$} tag. ~ ~== ~ ~== 3 I expect a high number of submissions. ~ ~== 2 I expect a proper number of submissions; ~ ~== 1 I expect a limited number of submissions; ~ ~--{$>$} ~ ~ ~{$<$}/score{$><$}/field{$><$}!-- ~ ~ Review ~ ~ --{$><$}field id="611405" name="Review"{$>$} ~{$<$}!-- ~ ~== Please provide a detailed review, including justification for your ~ ~== scores. This field is required. ~ ~--{$>$} ~{$<$}text required="required"{$>$} ~{$<$}!-- ~ ~== Enter the text for the field ~ ~== ~ Review ~ ~== below. This field is required. ~ ~--{$>$}The proposal is too broad. It aims at covering "any aspect of IoT-native Software Engineering", which is risky. For instance, proponents should decide if they want to elicit empirical studies or experience reports. In any case, I don't think pure empirical studies can be appropriate for this venue especially considering the length of typical IEEE Software papers. Overall, it is not clear the need that the proponents aim to fill. ~{$<$}/text{$><$}/field{$><$}field id="611406" name="Confidential remarks for the board members"{$>$} ~{$<$}!-- ~ ~== If you wish to add any remarks intended only for board members ~ ~== please write them below. These remarks will only be seen by the ~ ~== board members having access to reviews for this submission. They ~ ~== will not be sent to the authors. This field is optional. ~ ~--{$>$} ~{$<$}text optional="optional"{$>$} ~{$<$}!-- ~ ~== Enter the text for the field ~ ~== ~ Confidential remarks for the board members ~ ~== below. This field is optional. ~ ~--{$>$} ~{$<$}/text{$><$}/field{$><$}reviewer{$>$} ~{$<$}!-- ~ ~== If the review was written by (or with the help from) a subreviewer ~ ~== different from the PC member in charge, add information about ~ ~== the subreviewer below. Write subreviewer's first name, last name ~ ~== and email between the tags below. ~ ~--{$>$} ~{$<$}first\_name{$>$} ~{$<$}/first\_name{$>$} ~{$<$}last\_name{$>$} ~ {$<$}/last\_name{$>$} ~{$<$}email{$>$} ~{$<$}/email{$><$}/reviewer{$><$}/review{$>$}}} } @article{liSystematicMappingStudy2015, @@ -34276,6 +34292,154 @@ And then add a Detailed Comments section to report the notets that contain issue langid = {english} } +@article{muctadirModelConsistencyManagement, + title = {Model {{Consistency Management}} of a {{Brewery Digital Twin}}}, + author = {Muctadir, Hossain Muhammad and Liao, Yanyifan and Cleophas, Loek}, + abstract = {Digital Twins (DTs) are often defined as a pairing of a physical entity (PE) and one or more virtual entities (VEs) where the latter mimics certain behaviors of the former to provide specific services. VEs are typically model-based software systems that incorporate a variety of multi-domain, multi-tool models that are essential throughout the DT’s lifecycle. Any inconsistency among these models directly affects the performance, reliability, and effectiveness of a DT. In this paper, we present a case study on consistency management of VE models contained within a DT of a microbrewery, which encapsulates the fermentation process to optimize beer production.}, + langid = {english}, + note = {\section{Annotazioni\\ +(16/6/2025, 23:22:43)} + +\par +- “Digital Twins (DTs) are often defined as a pairing of a physical entity (PE) and one or more virtual entities (VEs) where the latter mimics certain behaviors of the former to provide specific services.” (Muctadir et al., p. 1) \#5fb236\\ +\mkbibemph{ } +\par +- “Any inconsistency among these models directly affects the performance, reliability, and effectiveness of a DT.” (Muctadir et al., p. 1) \#5fb236\\ +\mkbibemph{ } +\par +- “consistency management of VE models contained within a DT of a microbrewery, which encapsulates the fermentation process to optimize beer production” (Muctadir et al., p. 1) \#a28ae5\\ +\mkbibemph{ } +\par +- “model inconsistencies during the DT lifecycle are frequent and have a major impact on DT functionality” (Muctadir et al., p. 1) \#e56eee\\ +\mkbibemph{ } +\par +- “effective consistency management method for DT models.” (Muctadir et al., p. 1) \#a28ae5\\ +\mkbibemph{ } +\par +- “conceptual framework to address the challenges of consistency management for DT models.” (Muctadir et al., p. 1) \#5fb236\\ +\mkbibemph{ } +\par +- “In this paper, we further evaluate the framework with a DT from the bio-chemical domain.” (Muctadir et al., p. 1) \#a28ae5\\ +\mkbibemph{ } +\par +- “We manage the consistency of the VE comprising four models, which are essential for delivering two services associated with predicting and controlling alcohol production.” (Muctadir et al., p. 1) \#e56eee\\ +\mkbibemph{ } +\par +- “Section II reviews research on model consistency management” (Muctadir et al., p. 1) \#5fb236\\ +\mkbibemph{ } +\par +- “microbrewery” (Muctadir et al., p. 1) \#5fb236\\ +\mkbibemph{ } +\par +- “consistency management approaches into three categories” (Muctadir et al., p. 1) \#5fb236\\ +\mkbibemph{ } +\par +- “proof-theorybased” (Muctadir et al., p. 1) \#2ea8e5\\ +\mkbibemph{ } +\par +- “synchronization-based” (Muctadir et al., p. 1) \#2ea8e5\\ +\mkbibemph{ } +\par +- “rule-based” (Muctadir et al., p. 1) \#2ea8e5\\ +\mkbibemph{ } +\par +- “derivation of consistency from axioms and theorems.” (Muctadir et al., p. 1) \#5fb236\\ +\mkbibemph{ } +\par +- “extensive manual definition of transformation rules and become increasingly difficult to manage in heterogeneous or large-scale system” (Muctadir et al., p. 1) \#5fb236\\ +\mkbibemph{ } +\par +- “entities and their relationships required to facilitate the development of systems that can effectively maintain model consistency by addressing specific requirements.” (Muctadir et al., p. 2) \#5fb236\\ +\mkbibemph{ } +\par +- “5D DT architecture proposed by Tao et al. [24].” (Muctadir et al., p. 2) \#5fb236\\ +\mkbibemph{ } +\par +- “(1) Physical Entity (PE)” (Muctadir et al., p. 2) \#2ea8e5\\ +\mkbibemph{ } +\par +- “(2) Virtual Entity (VE)” (Muctadir et al., p. 2) \#2ea8e5\\ +\mkbibemph{ } +\par +- “chemical kinetics model” (Muctadir et al., p. 2) \#2ea8e5\\ +\mkbibemph{ } +\par +- “thermal dynamics model” (Muctadir et al., p. 2) \#2ea8e5\\ +\mkbibemph{ } +\par +- “heat transfer model” (Muctadir et al., p. 2) \#2ea8e5\\ +\mkbibemph{ } +\par +- “control model” (Muctadir et al., p. 2) \#2ea8e5\\ +\mkbibemph{ } +\par +- “Services” (Muctadir et al., p. 2) \#2ea8e5\\ +\mkbibemph{ } +\par +- “Production prediction” (Muctadir et al., p. 2) \#2ea8e5\\ +\mkbibemph{ } +\par +- “production control” (Muctadir et al., p. 2) \#2ea8e5\\ +\mkbibemph{ } +\par +- “PE sends monitoring data and receives control signals, beer flavor and physical attributes dictate VE model parameters, and the remaining VE data are model states” (Muctadir et al., p. 2) \#5fb236\\ +\mkbibemph{ } +\par +- “a) Read and extract model data:” (Muctadir et al., p. 2) \#2ea8e5\\ +\mkbibemph{ } +\par +- “b) Store the extracted data:” (Muctadir et al., p. 2) \#2ea8e5\\ +\mkbibemph{ } +\par +- “ConsistencyRules” (Muctadir et al., p. 2) \#5fb236\\ +\mkbibemph{ } +\par +- “c) Evaluate consistency rules:” (Muctadir et al., p. 3) \#2ea8e5\\ +\mkbibemph{ } +\par +- “d) Manage consistency rule relevancy” (Muctadir et al., p. 3) \#2ea8e5\\ +\mkbibemph{ } +\par +- “VE of the brewery DT” (Muctadir et al., p. 3) \#5fb236\\ +\mkbibemph{ } +\par +- “CommonModelStructure” (Muctadir et al., p. 3) \#5fb236\\ +\mkbibemph{ } +\par +- “the second ensures correct connectivity with the thermal dynamics model.” (Muctadir et al., p. 3) \#ffd400\\ +\mkbibemph{What does it mean "ensures". How connectivity is ensured? } +\par +- “If a rule’s condition is violated, the associated error message is shown.” (Muctadir et al., p. 3) \#ffd400\\ +\mkbibemph{ANd then? WHo is the main intended user of the approach. What are the conditions to use the consistency management? What's the supported development of runtime environments that are required to enable the usage of the consistency management system? } +\par +- “The checker mentioned previously enables us to preserve this structure” (Muctadir et al., p. 3) \#5fb236\\ +\mkbibemph{ } +\par +- “Discussion on results” (Muctadir et al., p. 4) \#ffd400\\ +\mkbibemph{What results? I undertand it's a short paper, however the paper is not effective in stressing the novelties of the proposed approach. What's the novelty? Is it the consistency language? is it the engine? Authors should distill what are the main ingredientes of the proposed approach. The paper presents an overview of the consistency mangenent systems consisting of different classes and interfaces. The presentation of the consistency managemtn rule is not effective in stressing what are the cases that existing approaches cannot support and that instead the proposed approach can do. } +\par +- “In the case study presented in Section IV-B, we demonstrate the practical implementation and advantages of the consistency management framework (cf. Section IV-A) for the microbrewery DT.” (Muctadir et al., p. 4) \#ffd400\\ +\mkbibemph{ } +\par +- “Furthermore, it supports the structured management of consistency rules, with integrated checkers to ensure that these rules remain well organized and continuously aligned with the evolving DT models.” (Muctadir et al., p. 4) \#ffd400\\ +\mkbibemph{The paper presents some ideas, by sketching essentially a class diagram of the consistency management system. What's the novel aspects of the proposed system? } +\par +- “b) Future work: Similar to the case studies presented in [3] implementing the consistency management framework,” (Muctadir et al., p. 4) \#ffd400\\ +\mkbibemph{WHat's the difference of the consistency management presented in this paper and that of [3]? } +\par +- “[3]” (Muctadir et al., p. 4) \#ffd400\\ +\mkbibemph{ } +\par +- “the framework’s relevance, practicality, and usability for a more complex system continue to be an area for further research.” (Muctadir et al., p. 4) \#ffd400\\ +\mkbibemph{ } +\par +- “For this purpose, we implement a consistency management framework designed specifically to manage the consistency of DT models.” (Muctadir et al., p. 4) \#ffd400\\ +\mkbibemph{The strenghts and the limitations of the framework are not clearly stated. } +\par +- “This provides a strong indication of the usefulness and applicability of the framework for DTs developed within the biochemical domain.” (Muctadir et al., p. 4) \#5fb236\\ +\mkbibemph{ }} +} + @incollection{mullerAutonomicComputingNow2009, title = {Autonomic {{Computing Now You See It}}, {{Now You Don}}’t}, booktitle = {Software {{Engineering}}}, @@ -37897,6 +38061,13 @@ Google's monolithic repository provides a common source of truth for tens of tho langid = {english} } +@article{pretelAgentDesignPattern, + title = {An Agent Design Pattern Catalogue for the Entanglement of {{Digital Twins}}}, + author = {Pretel, Elena and Navarro, Elena and López-Jaquero, Víctor and González, Pascual and Dustdar, Schahram}, + abstract = {The entanglement property is an essential property of Digital Twins (DTs), enabling seamless interaction between the physical twin and its DT. Despite the increasing adoption of MultiAgent Systems (MAS) in DT development, there is a lack of structured guidance on how agent design can support different levels of entanglement. This paper addresses this gap by proposing a catalogue of agent design patterns tailored to support weak, simple, and strong entanglement in DTs. Each pattern is aligned with established design patterns in MAS literature. A decision model is also introduced to guide practitioners in selecting appropriate patterns based on the essential aspects of entanglement: connectivity, promptness, and association. The proposed patterns and model were applied in a real-world case study involving the design of a DT to manage study sessions for children with ADHD, demonstrating their effectiveness and practical value. The results support the feasibility and utility of our catalogue of design patterns for the entanglement of the DT.}, + langid = {english} +} + @inproceedings{Pretschner05, title = {One Evaluation of Model-Based Testing and Its Automation}, booktitle = {Proc. 27th {{Int}}. {{Conf}}. {{Softw}}. {{Eng}}.}, @@ -49774,6 +49945,12 @@ A taxonomy of tool-related considerations is presented, based on industry data, keywords = {source\_mobile} } +@online{WhyMachineLearning, + title = {Why Do {{Machine Learning Notebooks Crash}}? {{An Empirical Study}} on {{Public Python Jupyter Notebooks}}}, + url = {https://www.computer.org/csdl/journal/ts/5555/01/11022755/27fzlMGbues}, + urldate = {2025-06-15} +} + @incollection{Wilcoxon1992, title = {Individual Comparisons by Ranking Methods}, booktitle = {Breakthroughs in Statistics: {{Methodology}} and Distribution}, @@ -50284,12 +50461,12 @@ This paper proposes TagCombine, an automatic tag recommendation method which ana @online{xiaoFoundationsLargeLanguage2025, title = {Foundations of {{Large Language Models}}}, author = {Xiao, Tong and Zhu, Jingbo}, - date = {2025-01-16}, + date = {2025-06-15}, eprint = {2501.09223}, eprinttype = {arXiv}, eprintclass = {cs}, doi = {10.48550/arXiv.2501.09223}, - abstract = {This is a book about large language models. As indicated by the title, it primarily focuses on foundational concepts rather than comprehensive coverage of all cutting-edge technologies. The book is structured into four main chapters, each exploring a key area: pre-training, generative models, prompting techniques, and alignment methods. It is intended for college students, professionals, and practitioners in natural language processing and related fields, and can serve as a reference for anyone interested in large language models.}, + abstract = {This is a book about large language models. As indicated by the title, it primarily focuses on foundational concepts rather than comprehensive coverage of all cutting-edge technologies. The book is structured into five main chapters, each exploring a key area: pre-training, generative models, prompting, alignment, and inference. It is intended for college students, professionals, and practitioners in natural language processing and related fields, and can serve as a reference for anyone interested in large language models.}, langid = {english}, pubstate = {prepublished}, keywords = {/unread,Computer Science - Artificial Intelligence,Computer Science - Computation and Language,Computer Science - Machine Learning} diff --git a/journals/2025_06_15.md b/journals/2025_06_15.md new file mode 100644 index 00000000..3d72aebf --- /dev/null +++ b/journals/2025_06_15.md @@ -0,0 +1,17 @@ +progress:: {{renderer :todomaster}} +icon:: 📅 +boox-notes:: ![BOOX Notes](../assets/../../onyx/TabUltraCPro/Notepad/JOURNALING.pdf) + + - ## Tasks + - ## Notes +- +- +- [[ReadingNotes]] + - #[[Clip]] [[16-06-2025]] 08:08 [Proteggere Hormuz | Corriere.it](https://www.corriere.it/native/25_giugno_16/economia-u350018900686040ah.shtml?bsft_eid=cff042c2-45d6-4440-8bb5-181c6f95da51&bsft_clkid=86c998cb-e582-45c2-a2bb-4ad8a4d139d4&bsft_uid=75f119ca-55cd-4a60-9aa0-5d53f831d1ea&bsft_mid=ded00d25-7fb4-4ba0-bd60-26ce2129b719&bsft_txnid=a93d0a8c-1935-4988-be95-10bbcb97b0de&bsft_utid=75f119ca-55cd-4a60-9aa0-5d53f831d1ea-Newsletter_COR_PRIMAORA&bsft_mime_type=html&bsft_ek=2025-06-16T04%3A00%3A02Z&bsft_lx=9&bsft_tv=467&bsft_aaid=72bb9dec-3452-4075-a63c-0f8d60246a1e) + L o Stretto di Hormuz misura 33chilometri nel suo punto più stretto tra la penisola araba a Sud e l’Iran a Nord. Le corsie per le navi in entrata e uscita nelle due direzioni sono larghe tre chilometri ciascuna: i tremila metri più vitali e più fragili dell’economia mondiale, nel Golfo Persico. + - #[[Clip]] [[16-06-2025]] 08:10 [Proteggere Hormuz | Corriere.it](https://www.corriere.it/native/25_giugno_16/economia-u350018900686040ah.shtml?bsft_eid=cff042c2-45d6-4440-8bb5-181c6f95da51&bsft_clkid=86c998cb-e582-45c2-a2bb-4ad8a4d139d4&bsft_uid=75f119ca-55cd-4a60-9aa0-5d53f831d1ea&bsft_mid=ded00d25-7fb4-4ba0-bd60-26ce2129b719&bsft_txnid=a93d0a8c-1935-4988-be95-10bbcb97b0de&bsft_utid=75f119ca-55cd-4a60-9aa0-5d53f831d1ea-Newsletter_COR_PRIMAORA&bsft_mime_type=html&bsft_ek=2025-06-16T04%3A00%3A02Z&bsft_lx=9&bsft_tv=467&bsft_aaid=72bb9dec-3452-4075-a63c-0f8d60246a1e) + Bassora alla confluenza di Tigri ed Eufrate in Iraq — vicino alla foce nel Golfo — e la costa dell’Oman dall’altra parte dello stretto. + - #[[Clip]] [[16-06-2025]] 08:10 [Proteggere Hormuz | Corriere.it](https://www.corriere.it/native/25_giugno_16/economia-u350018900686040ah.shtml?bsft_eid=cff042c2-45d6-4440-8bb5-181c6f95da51&bsft_clkid=86c998cb-e582-45c2-a2bb-4ad8a4d139d4&bsft_uid=75f119ca-55cd-4a60-9aa0-5d53f831d1ea&bsft_mid=ded00d25-7fb4-4ba0-bd60-26ce2129b719&bsft_txnid=a93d0a8c-1935-4988-be95-10bbcb97b0de&bsft_utid=75f119ca-55cd-4a60-9aa0-5d53f831d1ea-Newsletter_COR_PRIMAORA&bsft_mime_type=html&bsft_ek=2025-06-16T04%3A00%3A02Z&bsft_lx=9&bsft_tv=467&bsft_aaid=72bb9dec-3452-4075-a63c-0f8d60246a1e) + L’Europa, già sotto la minaccia dei dazi americani e della guerra della Russia, si risveglierebbe in una morsa fra inflazione e stagnazione. Oscillazioni + - #[[Clip]] [[16-06-2025]] 08:12 [Proteggere Hormuz | Corriere.it](https://www.corriere.it/native/25_giugno_16/economia-u350018900686040ah.shtml?bsft_eid=cff042c2-45d6-4440-8bb5-181c6f95da51&bsft_clkid=86c998cb-e582-45c2-a2bb-4ad8a4d139d4&bsft_uid=75f119ca-55cd-4a60-9aa0-5d53f831d1ea&bsft_mid=ded00d25-7fb4-4ba0-bd60-26ce2129b719&bsft_txnid=a93d0a8c-1935-4988-be95-10bbcb97b0de&bsft_utid=75f119ca-55cd-4a60-9aa0-5d53f831d1ea-Newsletter_COR_PRIMAORA&bsft_mime_type=html&bsft_ek=2025-06-16T04%3A00%3A02Z&bsft_lx=9&bsft_tv=467&bsft_aaid=72bb9dec-3452-4075-a63c-0f8d60246a1e&refresh_ce) + In primo luogo gli Houthi dello Yemen, sostenuti da Teheran, hanno dimostrato di poter mantenere semichiuso lo stretto di Bab el-Mandeb dall’Oceano Indiano verso Suez malgrado più di un anno di pressione occidentale. \ No newline at end of file diff --git a/journals/2025_06_16.md b/journals/2025_06_16.md new file mode 100644 index 00000000..1583fdd6 --- /dev/null +++ b/journals/2025_06_16.md @@ -0,0 +1,15 @@ +progress:: {{renderer :todomaster}} +icon:: 📅 +boox-notes:: ![BOOX Notes](../assets/../../onyx/TabUltraCPro/Notepad/JOURNALING.pdf) + + - ## Tasks + - ## Notes + - [[SERVICES/PINKAMP]] + - Apertura evento: + - P.Inverardi: "Le società progrediscono molto lentamente ma regrediscono molto velocemente!" + - [[Preparazione Intervento PINKAMP]] #todoist-task #SERVICES/PINKAMP + - [[Missione STAF 2025]] #todoist-task #STAF #ADMIN/MISSIONI #[[Attended Event]] + - [[SERVICES/PHDICT]] + - Commissione ammissione XLI ciclo + - Parlare con Costanzo e Pepe + - [[Linee guida afferenza Collegio dottorato ICT]] #todoist-task #SERVICES/PHDICT \ No newline at end of file diff --git a/journals/2025_06_17.md b/journals/2025_06_17.md new file mode 100644 index 00000000..8440afa9 --- /dev/null +++ b/journals/2025_06_17.md @@ -0,0 +1 @@ +- Processo consultazione \ No newline at end of file diff --git a/journals/2025_06_18.md b/journals/2025_06_18.md new file mode 100644 index 00000000..d93b5334 --- /dev/null +++ b/journals/2025_06_18.md @@ -0,0 +1,53 @@ +progress:: {{renderer :todomaster}} +icon:: 📅 +boox-notes:: ![BOOX Notes](../assets/../../onyx/TabUltraCPro/Notepad/JOURNALING.pdf) + + - ## Tasks + - DONE Chiamare Franco + - DONE Finalizzare [[Preparazione Intervento PINKAMP]] #todoist-task #SERVICES/PINKAMP +id:: 685266e9-3b29-401d-a2de-b8aad90054b7 + :LOGBOOK: + CLOCK: [2025-06-18 Wed 13:14:51]--[2025-06-18 Wed 13:14:52] => 00:00:01 + :END: + - DONE Call MOSAICO + :LOGBOOK: + CLOCK: [2025-06-18 Wed 10:16:22]--[2025-06-18 Wed 10:16:23] => 00:00:01 + :END: + - ### DONE **[[SWEN]] [[meeting]]** + collapsed:: true + :LOGBOOK: + CLOCK: [2025-06-18 Wed 15:06:39]--[2025-06-18 Wed 15:06:40] => 00:00:01 + :END: + - #### **Metadata** + - **Talk Title**: From Data to Decisions: Engineering Persona-Driven Tools for Smart Territories + - **Speaker**: Gennaro Zanfardino, PhD Student + - **Abstract**: This talk presents a software engineering approach for supporting urban resilience and planning through data-driven, user-centered design. It introduces an open-source software ecosystem for territorial monitoring that integrates diverse data sources such as satellite imagery and ground-based sensors. This ecosystem is used to produce KPI-based insights on quality of life metrics including air quality, temperature, and walkability. Built on this platform, the second contribution is a customizable application for validating urban evacuation plans using multi-agent simulations. Featuring a persona-based interface, the app adapts to various user roles such as civil protection agencies and safety planners. It simulates complex scenarios and supports iterative development through continuous stakeholder feedback. Together, the ecosystem and the application combine Geographic Information Systems, agent-based models, and scalable architectures to deliver actionable intelligence and improve public decision-making in dynamic environments. + - #### **Questions** + - {{query (and [[question]] [[18-06-2025]] )[[question]]}} + query-table:: true + - #### **Notes** + - Software ecosystems vs digital twins (to validate evacuation plans) + - SOftware engineering for digital twins + - The goal was to produce multi-dimensional model to represet territories at various level of abstraction + - Persona approach + - In software engineering, the *persona approach* is a method used to create fictional characters that represent different user types or target audiences for a product or system. These personas are based on research and data, and are used to guide design decisions and ensure that the product meets the needs and expectations of its intended users. + - The **DestinE Platform**, developed by the European Space Agency (ESA), is a groundbreaking initiative aimed at promoting collaboration and innovation in the field of space exploration. This platform brings together scientists, engineers, and researchers from across Europe to work collectively on projects related to space technology, exploration, and research. By fostering an environment of cooperation and knowledge-sharing, the DestinE Platform is shaping the future of space exploration and advancing our understanding of the universe. Through this initiative, ESA is leading the way in pushing the boundaries of space science and technology, paving the path for future discoveries and advancements in the field. + - **Multidimensional Integrated Dashboards** + - Inlcuding data from + - Cetemps + - Usra + - ESA + - ArtaAbruzzo + - Open Filestores + - How have you defined dashboards with respet to Personas #question + - Have you considerd some guidelines? Have yuo done some interviews with the actual stakeholders? Essentially I'm referring to the process in slide 15. + - Simulator and planner for what? + - What's the most difficult part you had to deal with? #question + - Is there any recurrent patterns that can be reused depending on the goal / users / etc, of the wanetd dashboard? #question + - How general can you be? Essentially the software ecosystems seem the typical one related to collecting data, filtering, and visualization. + - DOING [[Presentazione dei documenti di monitoraggio]] + :LOGBOOK: + CLOCK: [2025-06-18 Wed 17:01:15] + :END: + - Alessandro + - ## Notes \ No newline at end of file diff --git a/journals/2025_06_19.md b/journals/2025_06_19.md new file mode 100644 index 00000000..d902d44c --- /dev/null +++ b/journals/2025_06_19.md @@ -0,0 +1,22 @@ +icon:: 📅 +boox-notes:: ![BOOX Notes](../assets/../../onyx/TabUltraCPro/Notepad/JOURNALING.pdf) +progress:: {{renderer :todomaster}} + + - ## Tasks + - ## Notes + - DONE Corsa +id:: 6852f4e6-5a49-40a5-9807-72cafcb3fbc5 + - DONE Intervento [[Preparazione Intervento PINKAMP]] + - DONE Call [[PAPERS/2025-LLM-GENERATION]] +id:: 68540a72-f93d-4413-9b74-79d3e5716758 + - DONE Call [[MODELS: 10 years most infuential paper selection committee]] +id:: 6853f169-1d30-4e3e-8bd6-d795d2f01914 + - DONE Capelli +id:: d4b795f4-21e9-408f-a6c2-3aadc10c3468 + - TODO Capire cosa fare con [[🗓 TIASSISTO24 - MEETING BANDO REGIONE ABRUZZO 1.1.1.2]] + - DOING [[Presentazione dei documenti di monitoraggio]] + :LOGBOOK: + CLOCK: [2025-06-18 Wed 17:01:15] + :END: + - TODO Capire cosa fare [[PRIN 2020 - scadenza rendicontazione finale]] + - \ No newline at end of file diff --git a/logseq/.recycle/pages_chatgpt__2025-06-18 14%3A40%3A41.md b/logseq/.recycle/pages_chatgpt__2025-06-18 14%3A40%3A41.md new file mode 100644 index 00000000..1111f2df --- /dev/null +++ b/logseq/.recycle/pages_chatgpt__2025-06-18 14%3A40%3A41.md @@ -0,0 +1,11 @@ +type:: ChatGPT +chatgpt-flow:: alternating +chatgpt-prompt:: Custom: what is it? can you provide a short definition in the context of software engineering? +chatgpt-prompt-source:: ((6852b3a1-45f7-4ad4-bdd6-ce676aff0b32)) + +- speaker:: [[user]] + what is it? can you provide a short definition in the context of software engineering?: + {{embed ((6852b3a1-45f7-4ad4-bdd6-ce676aff0b32))}} +- id:: 6852b3ca-e62b-49bc-953f-78d970124b8c + speaker:: [[assistant]] + In software engineering, the persona approach is a method used to create fictional characters that represent different user types or target audiences for a product or system. These personas are based on research and data, and are used to guide design decisions and ensure that the product meets the needs and expectations of its intended users. \ No newline at end of file diff --git a/logseq/.recycle/pages_chatgpt__2025-06-18 14%3A43%3A19.md b/logseq/.recycle/pages_chatgpt__2025-06-18 14%3A43%3A19.md new file mode 100644 index 00000000..efbc6397 --- /dev/null +++ b/logseq/.recycle/pages_chatgpt__2025-06-18 14%3A43%3A19.md @@ -0,0 +1,11 @@ +type:: ChatGPT +chatgpt-flow:: alternating +chatgpt-prompt:: Custom: Can you provide an introductory paragraph about this European effort? +chatgpt-prompt-source:: ((6852b3e3-0cea-4d7a-af22-5313acb2d2c9)) + +- speaker:: [[user]] + Can you provide an introductory paragraph about this European effort?: + {{embed ((6852b3e3-0cea-4d7a-af22-5313acb2d2c9))}} +- id:: 6852b468-25fc-4806-bf16-54f090dd9c21 + speaker:: [[assistant]] + The DestinE Platform, developed by the European Space Agency (ESA), is a groundbreaking initiative aimed at promoting collaboration and innovation in the field of space exploration. This platform brings together scientists, engineers, and researchers from across Europe to work collectively on projects related to space technology, exploration, and research. By fostering an environment of cooperation and knowledge-sharing, the DestinE Platform is shaping the future of space exploration and advancing our understanding of the universe. Through this initiative, ESA is leading the way in pushing the boundaries of space science and technology, paving the path for future discoveries and advancements in the field. \ No newline at end of file diff --git a/pages/Agentic AI.md b/pages/Agentic AI.md index 83b37bf5..4484cc0b 100644 --- a/pages/Agentic AI.md +++ b/pages/Agentic AI.md @@ -16,4 +16,12 @@ icon:: 🧠 - *Limited tool orchestration:* to execute complex workflows a proper infrastructure is needed to discover tools and manage tool interactions across multiple turns. - *Task coordination challenges*: structured control mechanisms are require to manage with LLMs multi-step workflows - **LangChain** - - \ No newline at end of file + - Open-source framework and venture-backed company based in San Francisco + - Main features: + - *Composable workflows*: the LCEL - LangChain Expression Language permits to break down complex tasks into modulare components that can be assembled. This enable the orchestration of multiple processing steps. + - *Integration ecosystem:* it provides interfaces for all generative components i.e., LLMs, embeddings, vector databases, document loaders, search engines. This will permit to switch between providers without rewriting core logic. + - *Unified model access:* interfaces to different language and embedding models + - Application development concepts: + - *Memory and state management* + - *Agent architecture* +- \ No newline at end of file diff --git a/pages/DIARIO.md b/pages/DIARIO.md index 288f23da..13324821 100644 --- a/pages/DIARIO.md +++ b/pages/DIARIO.md @@ -4,6 +4,7 @@ icon:: 📒 - Per cosa sono grato? - Perche' non c'e' motivo di sentirsi inferiore ad altri? - [[12-06-2025]] + collapsed:: true - Per qualche motivo c'e' qualcosa che non mi torna e che mi lascia triste da un punto di vista lavorativo. Non so perchè. è piuttosto stupido considerando la posizione che rivesto. Spesso sento la classica sensazione "dell'impostore". Perchè tutto ciò? - Al momento ci sono degli aspetti che mi arregano preoccupazione: - **Gestione del dottorato**: per questo, spesso mi viene da pensare di non essere in grado. Non mi riferisco all'aspetto gestionale, ma piuttosto ad aspetti politici e di indirizzo. Forse dovrei prendere più iniziativa, ma per questo sento di non essere ancora abbastanza sicuro. Cosa è giusto fare? Perchè ho dovuto mandare il documento a Guido? Come e' stato visto da parte sua questo mio passaggio? diff --git a/pages/DONE.md b/pages/DONE.md index 015935c0..8970e88f 100644 --- a/pages/DONE.md +++ b/pages/DONE.md @@ -109,4 +109,10 @@ icon:: ✅ - ✔️ [[10-06-2025]] *14:40* ((6843518f-f8a7-4629-b184-1ef230d8c645)) - ✔️ [[10-06-2025]] *14:42* ((6843518f-b30c-484e-aba0-97ae9328b3f3)) - ✔️ [[10-06-2025]] *14:43* ((6843518c-4984-4ec8-ac40-c6fba1517d03)) - - ✔️ [[11-06-2025]] *14:24* ((684350a8-08ce-44ba-ac20-7512a49e598d)) \ No newline at end of file + - ✔️ [[11-06-2025]] *14:24* ((684350a8-08ce-44ba-ac20-7512a49e598d)) + - ✔️ [[18-06-2025]] *13:14* ((685266e9-3b29-401d-a2de-b8aad90054b7)) + - ✔️ [[18-06-2025]] *15:06* ((6852b2bb-9757-4ab4-8661-fdda350c9647)) + - ✔️ [[19-06-2025]] *13:06* ((6852f4e6-5a49-40a5-9807-72cafcb3fbc5)) + - ✔️ [[19-06-2025]] *15:51* ((68540a72-f93d-4413-9b74-79d3e5716758)) + - ✔️ [[19-06-2025]] *16:46* ((6853f169-1d30-4e3e-8bd6-d795d2f01914)) + - ✔️ [[19-06-2025]] *18:57* ((d4b795f4-21e9-408f-a6c2-3aadc10c3468)) \ No newline at end of file diff --git a/pages/MODELS%3A 10 years most infuential paper selection committee.md b/pages/MODELS%3A 10 years most infuential paper selection committee.md new file mode 100644 index 00000000..cb85f6ab --- /dev/null +++ b/pages/MODELS%3A 10 years most infuential paper selection committee.md @@ -0,0 +1,5 @@ +tags:: #todoist-task, [[EditoringChairing]] +date:: [[19-06-2025]] - 13:16 +progress:: {{renderer :todomaster}} + +- [Models'15 best paper - Google Sheets](https://docs.google.com/spreadsheets/d/1mzYF9c08bSwEPRPP0sWjc-SCk3d6A0WIg9nNEpXmkvg/edit?gid=508154343#gid=508154343) \ No newline at end of file diff --git a/pages/Missione STAF 2025.md b/pages/Missione STAF 2025.md index f0954269..f2a04f18 100644 --- a/pages/Missione STAF 2025.md +++ b/pages/Missione STAF 2025.md @@ -16,9 +16,7 @@ progress:: {{renderer :todomaster}} - ![image.png](../assets/image_1748872921830_0.png){:height 361, :width 252} - ## Notes - ## My first day at [[staf]] - collapsed:: true - #### **Modeling and LLMs in Continuous Software Engineering** - collapsed:: true - [Anne Koziolek, Karlsruhe Institute of Technology Germany](https://conf.researchr.org/profile/STAF-2025/annekoziolek) - Abstract: - The notion of continuous software engineering extends practices like continuous integration to view the entire software development lifecycle as a continuous, interconnected flow of activities. At the same time, recent advances in large language models (LLMs) have revolutionized the way machines process natural language—language that plays a central role throughout software engineering, from requirements elicitation and design discussions to documentation. @@ -73,7 +71,6 @@ progress:: {{renderer :todomaster}} - ![Immagine WhatsApp 2025-06-11 ore 10.16.57_48fec7ed.jpg](../assets/Immagine_WhatsApp_2025-06-11_ore_10.16.57_48fec7ed_1749629843969_0.jpg) - ### Keynote at [[STAF]] 2025 - ### A metascience study of the low-code scientific field - Jordi Cabot at [[STAF]] 2025 - ECMFA - collapsed:: true - Can the low-code popularity to help the community grow? - Looking for win-win - [lens.org](https://www.lens.org/) has been used to collect articles @@ -86,7 +83,6 @@ progress:: {{renderer :todomaster}} - Becuase of the so different keywords like MDE/MDA/MBD/.,,, we look so fragmented - Majority of low-code papers are applications - ### An internal DSL for Graphical Modeling Tools Based on GLSP - Georg Hinkel - ECMFA - collapsed:: true - Requirements of the language - GLSP- specific - Recurring concepts like layout information @@ -98,7 +94,6 @@ progress:: {{renderer :todomaster}} - Integrated Protocols Support - Used the same technology as **NMF Syncronizations** - ### User-modeling in MDE - an SLR - ECMFA - collapsed:: true - To facilitate the development of personalized applications - - ### Who will create the languages of the Future? - Jordi Cabot at OOPSLE @@ -126,10 +121,8 @@ progress:: {{renderer :todomaster}} - [Augment Code - AI coding platform for real software.](https://www.augmentcode.com/?utm_campaign=gg_emea_dg_search_competitor_cursor&utm_source=google&utm_medium=cpc&utm_content=cursor_ai&utm_term=cursor%20ai&gad_source=1&gad_campaignid=22644987260&gclid=Cj0KCQjw0qTCBhCmARIsAAj8C4Z9b90Sn1dgn5oHyCdgVLn8bGMBKTLMJAXocET5cYs4nHFEgU64q3oaAtuzEALw_wcB) - Cursor AI - - ### Let's make abstraction engineering fun again! - A. Cicchetti - OOPSLE - collapsed:: true - Ha fatto una presentazione su JJODEL di fatto, ma non mi ha fatto impazzire. - ### Wrap-up - collapsed:: true - List of open problems - Are they solved? - Are you satisfied by existing solutions? @@ -140,7 +133,6 @@ progress:: {{renderer :todomaster}} - - ## Second day at [[STAF]] / [[SLE]] - ### Keynote at [[sle]] da Thorsten Berger (A new DSL textbook in town!) - collapsed:: true - Abstract: collapsed:: true - DSLs are the ultimate abstraction in software engineering. While programming languages have – since the advent of computers – continuously increased their level of abstraction, they are still limited to the domain of computing, with their instances containing many technicalities. Unlike programming languages, DSLs reflect a given application domain, ideally abstracting away anything beyond it. Recognizing their strengths, the programming-language and the software-engineering community introduced many technologies for engineering DSLs. While well-polished widely-used DSLs have existed for a long time (e.g., SQL, regular expressions, HTML), language engineering technologies have made great progress over the last two decades, allowing developers who are not language or compiler experts to create their own DSL – in order to increase the level of automation for their projects. @@ -159,7 +151,6 @@ progress:: {{renderer :todomaster}} - external vs internal DSL - - ### LLM4SE Workshop - collapsed:: true - **[LLMs for Software Engineering: What does that mean for model-driven software development?](https://conf.researchr.org/home/staf-2025/llm4se-2025#)** - **Gabriele Taentzer** invited talk - ### **[Optimizing Retrieval Augmented Generation for Object Constraint Language](https://conf.researchr.org/program/staf-2025/program-staf-2025/?date=Thu%2012%20Jun%202025&past=Show%20upcoming%20events%20only#)** - ![Immagine WhatsApp 2025-06-12 ore 14.04.42_4fffb92f.jpg](../assets/Immagine_WhatsApp_2025-06-12_ore_14.04.42_4fffb92f_1749730047339_0.jpg){:height 370, :width 677} diff --git a/pages/PAPERS___2025-LLM-GENERATION.md b/pages/PAPERS___2025-LLM-GENERATION.md new file mode 100644 index 00000000..13027670 --- /dev/null +++ b/pages/PAPERS___2025-LLM-GENERATION.md @@ -0,0 +1,22 @@ +tags:: #todoist-task, [[PAPERS]] +date:: [[19-06-2025]] - 15:03 +progress:: {{renderer :todomaster}} + + - ## [[MEETINGS]] + - [[19-06-2025]] + - ### Slides + collapsed:: true + - ![image.png](../assets/image_1750338527527_0.png) + - ![image.png](../assets/image_1750338537901_0.png) + - ![image.png](../assets/image_1750338557774_0.png) + - ![image.png](../assets/image_1750338587417_0.png) + - ![image.png](../assets/image_1750338631965_0.png) + - Can you explan the definition of low complexity? [[question]] + - ![image.png](../assets/image_1750338755324_0.png) + - WE need to clearly define this complexity definition [[question]] + - ![image.png](../assets/image_1750338804683_0.png) + - ![image.png](../assets/image_1750339418053_0.png){:height 444, :width 920} + - ### Comments + - Sembra che l'uso di forma passiva o l'uso di forme come maybe, can etc. porta in confusione il modello riducendo la qualità del domain model description (case di EventManagementSystem) + - Quindi ora e' provare a rifrasare la descrizione del dominio EvenetManagement System e vedere se miglioriamo la situazione. L'idea e' definire delle guidelines. Per provarne lavalidità l'idea e' applicarle anche agli altri documenti e vedere se l'applicazione di queste guideline migliora o meno la generazione dei domain model corrispondenti. + - \ No newline at end of file diff --git a/pages/Preparazione Intervento PINKAMP.md b/pages/Preparazione Intervento PINKAMP.md index 1ab26be3..391d2640 100644 --- a/pages/Preparazione Intervento PINKAMP.md +++ b/pages/Preparazione Intervento PINKAMP.md @@ -2,45 +2,262 @@ tags:: #todoist-task, [[SERVICES/PINKAMP]] date:: [[04-06-2025]] - 12:24 progress:: {{renderer :todomaster}} -- Si puo pensare di far realizzare alle studentesse un GPT specifico per il task di interesse. Realizzare un chatbot? -- L'anno scorso le ragazze avevano fatto un GPT per gestire l'ansia - - ![image.png](../assets/image_1749464049205_0.png) -- I tutor sono: - - Isabella - - Gennaro - - Alina -- Oggi [[10-06-2025]] abbiamo avuto una call con i tutor. Si e' deciso di investigare la strada di progettare una sessione di approfindimento che coinvolta tutte le fase principali relative all'uso di strumenti LLM etc. -- [[References]] per preparare l'intervento - - [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - - - #[[Clip]] [[15-06-2025]] 16:10 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - Quando parliamo di AI generative ci riferiamo a modelli linguistici di grandi dimensioni (o LLM), un tipo di tecnologia in cui reti neurali profonde vengono addestrate con enormi quantità di documenti per elaborare e generare testi. - - - #[[Clip]] [[15-06-2025]] 16:10 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - In molti casi, questi modelli non sono in grado di capire quando una domanda è al di là delle loro capacità, e provano comunque a rispondere. - - - #[[Clip]] [[15-06-2025]] 16:10 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - i LLM hanno ancora un problema con le cosiddette [allucinazioni](https://www.ilpost.it/2024/05/22/ai-allucinazioni/), gli errori fattuali dei chatbot, che spesso inventano fatti e dettagli. - - - #[[Clip]] [[15-06-2025]] 16:10 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - il materiale di partenza su cui sono stati addestrati è incompleto, e le AI sono costrette a riempire le lacune, inventando di fatto informazioni (che sono comunque grammaticalmente corrette). - - - #[[Clip]] [[15-06-2025]] 16:10 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - Un esempio recente riguarda il quotidiano statunitense che ha [pubblicato](https://www.ilpost.it/2025/05/21/lista-consigli-libri-intelligenza-artificiale/) una lista di libri consigliati per l’estate, includendo titoli non esistenti, generati da un’intelligenza artificiale. - - - #[[Clip]] [[15-06-2025]] 16:11 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - Il settore dove questa tecnologia sta avendo l’impatto più profondo è probabilmente quello della programmazione informatica, tanto che in aziende come Microsoft [il 30 per cento del codice](https://www.cnbc.com/2025/04/29/satya-nadella-says-as-much-as-30percent-of-microsoft-code-is-written-by-ai.html) viene già scritto da AI. - - - #[[Clip]] [[15-06-2025]] 16:12 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - Ma le AI possono essere usate anche per scrivere (o tradurre) mail e documenti aziendali, o generare slide per presentazioni, mentre è nota da tempo la loro [inaffidabilità](https://www.ilpost.it/2024/07/28/matematica-intelligenza-artificiale/) nei calcoli matematici - - - #[[Clip]] [[15-06-2025]] 16:13 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - Il settore legale è stato uno dei primi a scontrarsi con le allucinazioni delle AI, come [dimostrato](https://www.businessinsider.com/increasing-ai-hallucinations-fake-citations-court-records-data-2025-5) dai molti casi in cui hanno prodotto documenti legali con riferimenti a leggi o sentenze del tutto inventati. Le allucinazioni sono così diffuse nell’ambiente legale da aver spinto l’avvocato francese Damien Charlotin a creare un sito che [raccoglie](https://www.damiencharlotin.com/hallucinations/) errori di questo tipo man mano che vengono scoperti. - - - #[[Clip]] [[15-06-2025]] 16:13 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - Le aziende che li sviluppano, infatti, sono sempre più in competizione tra loro e hanno capito che la maggioranza degli utenti preferisce un’AI che risponde sempre rispetto a una più cauta. - - - #[[Clip]] [[15-06-2025]] 16:14 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - intelligenze artificiali ruffiane” - - - #[[Clip]] [[15-06-2025]] 16:14 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - Dopo le critiche ricevute, l’azienda ha modificato le impostazioni ordinando al modello di «interagire con l’utente in modo caloroso ma onesto», mantenendo una certa «professionalità». - - - #[[Clip]] [[15-06-2025]] 16:15 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - «sacrificare, in alcuni casi, la veridicità in favore della ossequiosità». - - - #[[Clip]] [[15-06-2025]] 16:15 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - Verbosity Compensation, o «compensazione della verbosità», il fenomeno per cui i chatbot sembrano dare risposte più lunghe alle domande su cui sono più incerti, a causa della scarsità di informazioni disponibili. - - - #[[Clip]] [[15-06-2025]] 16:16 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - Il grande successo commerciale di sistemi da ChatGPT in poi ha cambiato l’approccio di molte aziende, che hanno abbandonato parte dell’iniziale cautela sul contenuto delle risposte per offrire un servizio che dia sempre una risposta agli utenti. - - - #[[Clip]] [[15-06-2025]] 16:21 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) - In questo contesto, un fattore importante è la memoria, ovvero la capacità di ricordare determinati precedenti delle loro conversazioni con l’utente e usarli per adattare le loro risposte future. - - [Una lista di libri consigliati che non esistono - Il Post](https://www.ilpost.it/2025/05/21/lista-consigli-libri-intelligenza-artificiale/) - - [Why is ChatGPT so bad at math? | TechCrunch](https://techcrunch.com/2024/10/02/why-is-chatgpt-so-bad-at-math/) \ No newline at end of file +- ## Notes + - DONE Recuperare qualche esempio di software engineering and AI + - TODO Sviluppare qualche esempio con VSCode e ChatGPT + - Mostrare qualche challenge + - DONE Introdurre all'AI facendo qualche esempio di sistema di raccomandazione ? + - Esempio di Netflix o di scelta di un ristorante + - ### Origini reti neurali + - ### 🧠 **Anni '40: Origini teoriche** + - **1943**: **Warren McCulloch** e **Walter Pitts** pubblicano il celebre articolo *“A Logical Calculus of the Ideas Immanent in Nervous Activity”*. + + 👉 È il primo **modello matematico di neurone artificiale**, noto come **neurone di McCulloch-Pitts**. + + --- + - ### 🔁 **Anni '50: Apprendimento** + - **1958**: **Frank Rosenblatt** introduce il **perceptron**, il primo modello di rete neurale con capacità di **apprendimento supervisionato** (algoritmo di aggiornamento dei pesi). + + 👉 Viene considerato un passo fondamentale per l'addestramento automatico. + + --- + - ### 🚫 **Anni '60-70: Crisi e rallentamento** + - **1969**: Marvin **Minsky** e Seymour **Papert** pubblicano *"Perceptrons"*, mostrando i limiti teorici dei perceptron (es. incapacità di risolvere il problema XOR). + + 👉 Questo porta a un **declino di interesse** per le reti neurali per circa un decennio (prima "AI Winter"). + + --- + - ### 🔄 **Anni '80: Rinascita** + - **1986**: **Rumelhart, Hinton e Williams** propongono la **retropropagazione dell’errore (backpropagation)** per l’addestramento di reti neurali multilivello (MLP). + + 👉 È il vero rilancio della teoria e pratica delle reti neurali profonde. + + --- + - ### ⚡ **Anni 2000-2010: Deep Learning** + - Con l’aumento della potenza computazionale e dei dati, modelli **deep neural networks** (reti profonde) diventano praticabili. + - **2012**: **AlexNet** (Krizhevsky et al.) vince la competizione ImageNet, segnando l’inizio dell’era moderna del **deep learning**. + + --- + - ### In sintesi: + + | Periodo | Evento chiave | Contributori principali | + | ---- | ---- | ---- | + | 1943 | Neurone artificiale (teoria) | McCulloch, Pitts | + | 1958 | Perceptron | Rosenblatt | + | 1969 | Critica ai limiti del perceptron | Minsky, Papert | + | 1986 | Backpropagation | Rumelhart, Hinton, Williams | + | 2012 | Rivoluzione deep learning | Krizhevsky et al. (AlexNet) | + + Se ti servono riferimenti bibliografici precisi o un approfondimento su uno di questi momenti, fammi sapere! + - ##### You said: + + Sono coloro che hanno preso il nobel? + + McCulloch-Pitts. + - ###### ChatGPT said: + + No, **Warren McCulloch** e **Walter Pitts** **non hanno ricevuto il Premio Nobel**. + + --- + - ### 🔍 Alcuni chiarimenti importanti: + - **McCulloch e Pitts** sono considerati i **padri fondatori** del concetto di neurone artificiale, grazie al loro lavoro del 1943. Tuttavia, il loro contributo, sebbene seminale, è rimasto confinato principalmente alla teoria e alla neurocibernetica, e **non è stato premiato con un Nobel**. + - Il **Premio Nobel** in ambito scientifico (Fisica, Chimica, Medicina) raramente viene assegnato per contributi all’**informatica** o all’**intelligenza artificiale**, poiché non esiste una categoria specifica per l'informatica (a differenza, ad esempio, del **Turing Award**). + + --- + - ### 💡 Premi più vicini all’IA e alle reti neurali: + - **Geoffrey Hinton**, **Yann LeCun**, e **Yoshua Bengio** hanno ricevuto nel **2018** il **Turing Award** (spesso chiamato "il Nobel dell'informatica") per i contributi fondamentali al **deep learning** e alle **reti neurali profonde**. + + --- + - ### In sintesi: + + | Persona | Premio Nobel? | Premio rilevante | + | ---- | ---- | ---- | + | Warren McCulloch | ❌ | Nessuno specifico | + | Walter Pitts | ❌ | Nessuno specifico | + | Hinton, LeCun, Bengio | ❌ | ✔ Turing Award (2018) | + + Se vuoi ti posso fornire una panoramica anche dei premiati in AI e machine learning. + - ### TIMELINE (circa 110 min) + - #### Chi sono (5min) + - #### Cos'è l'Intelligenza Artificiale (15 min) + - #### Introduzione ai LLMs (20 min) + - #### Informatica (12 min) + - #### LLM e Informatica (5 + 25 min) + - #### Mini tutorial live (20-25 min) + - Scriviamo un'app “Lista della spesa” in Python usando Copilot + - ```python + # Crea un'applicazione CLI in Python che consenta a un utente di: + # 1. Aggiungere elementi a una lista della spesa + # 2. Rimuovere elementi + # 3. Visualizzare la lista + # 4. Uscire + ``` + - Revisioni e miglioramenti + - ```python + # Aggiungi salvataggio su file della lista + ``` + - Aggiunta documentazione (Attenzione al risultato) + - ```python + Puoi aggiungere la documentazione di tutti i metodi? + ``` + - Generazione casi di testi + - ```python + Potresti generare i test per tutti i metodi? + ``` + - ![image.png](../assets/image_1750241099606_0.png){:height 730, :width 244} + - CTRL+SHIFT+P + - ![image.png](../assets/image_1750241756355_0.png) + - ![image.png](../assets/image_1750241967042_0.png) + - Generazione plantUML + - ```potresti generare un plantuml file che mi rappresenti graficamente la struttura del codice? + potresti generare un plantuml file che mi rappresenti graficamente la struttura del codice? + ``` + - ![image.png](../assets/image_1750241493088_0.png) + - Attività interattiva + - ## 🟣 **Attività 2 – “Scrivi tu il prompt!”** + - ### 📍 Obiettivo: + + Far riflettere su quanto sia importante formulare bene le richieste all’AI (sfida: *prompt engineering*). + - ### 🛠️ Modalità: + - Dai un obiettivo generico: + + > + + “Voglio che l’AI mi aiuti a fare un’app che salvi una lista di libri preferiti” + - Chiedi a 2-3 volontarie di **scrivere un prompt diverso** per descrivere lo stesso obiettivo. + - Mostra i risultati ottenuti da Copilot/ChatGPT per ciascun prompt. + - Confronta e discuti: Quale era il più chiaro? Quale ha funzionato meglio? + - ## Possiamo sempre fidarci? + - ```python + def is_prime(n): + for i in range(2, n): + if n % i == 0: + return False + return True + ``` + - funziona correttamente solo per valori di n >= 2, ma non gestisce i casi limite (n = 0 e n = 1), che non sono numeri primi. + - #Definition: Un numero primo è un ==numero intero maggiore di 1 che ha esattamente due divisori distinti: 1 e sé stesso==. In altre parole, un numero primo non può essere diviso esattamente da nessun altro numero intero oltre a 1 e al numero stesso. Ad esempio, 2, 3, 5, 7, 11, 13 sono numeri primi. Il numero 1 non è considerato primo, perché ha un solo divisore, ovvero sé stesso. + - ### **Cosa succede nei casi limite?** + - #### 🔸 Caso `n = 1` + - Il range `range(2, 1)` è **vuoto**, quindi il ciclo **non viene mai eseguito**. + - Si salta direttamente a `return True` + - 🔴 **Errore**: la funzione restituisce `True`, ma 1 **non è un numero primo**. + - #### 🔸 Caso `n = 0` + - Anche `range(2, 0)` è vuoto → stesso comportamento + - 🔴 **Errore**: restituisce `True`, ma 0 **non è un numero primo** + - Versione corretta + - ```python + def is_prime(n): + if n < 2: + return False + for i in range(2, n): + if n % i == 0: + return False + return True + + ``` + - #### LLM e Ingegneria del Software (10 min) + - #### Agentic AI (10 min) + - #### Sfide, rischi e opportunità (10 min) + - +- ## Schedule preparazione + - DONE [[16-06-2025]] Primo draft completo presentazione con l'aver definito tutti gli ingredienti + - DONE [[17-06-2025]] Secondo draft completo con aver recuperato tutti gli ingredienti ed inseriti nelle slide + :LOGBOOK: + CLOCK: [2025-06-17 Tue 16:45:19]--[2025-06-17 Tue 16:45:20] => 00:00:01 + :END: + - Forse qualcosa da prendere dalla tesi di Marco Giarrusso + - TODO [[18-08-2025]] Raffinamento contenuti e grafica delle slides +- ## Struttura intervento di circa 2 ore + - Dalle 11:15 alle 13:00 + - ![Orario definitivo prima settimana.pdf](../assets/Orario_definitivo_prima_settimana_1750056154238_0.pdf) + - ((684fbd0a-e948-4f25-9fd4-4ca045edad83)) + - Outline + - ### 🔹 **1. Apertura e orientamento (10 min)** + - Saluti iniziali e presentazione personale + - Cosa faremo oggi e cosa faremo domani + - Obiettivo: esplorare il mondo dell’AI generativa applicata all’informatica + - ### 🔹 **2. Che cos’è l’AI generativa? (15 min)** + Spiegazione accessibile ma non semplicistica + - Differenza tra AI “tradizionale” e AI generativa + - I Large Language Models (LLM): che cosa sono e come funzionano (semplificato) + - Concetti base: token, training, probabilità, completamento + - Esempio pratico: predizione della parola successiva + + --- + - ### 🔹 **3. Dove vediamo l’AI generativa oggi? (10 min)** + Contestualizzazione nel quotidiano + - Chatbot (es. ChatGPT), creazione immagini (es. DALL·E), scrittura assistita + - Usabilità accessibile: dall’industria ai social + - ### 🔹 **4. LLM e Ingegneria del Software (25 min)** + Collegamento diretto all’informatica + - Come un LLM può aiutare chi sviluppa software: + - Scrivere codice (es. GitHub Copilot) + - Spiegare cosa fa un programma + - Generare test + - Automatizzare documentazione + - Assistere nella progettazione (es. generazione di UML) + - Mini demo (anche video) con prompt tipo: + - “Scrivi un programma che calcoli l’area di un triangolo” + - “Genera il diagramma delle classi per un’app ToDo” + + --- + - ### 🔹 **5. Sfide, rischi e opportunità (15 min)** + Pensiero critico e riflessivo + - Bias nei modelli e responsabilità d’uso + - L’importanza della supervisione umana + - Opportunità per *nuove professioni*: chi crea AI, chi la guida, chi la interpreta + - ### 🔹 **6. Interazione finale e preview del laboratorio (20 min)** + Attivazione e coinvolgimento + - Mini quiz/gioco (es. “Chi ha scritto questa frase: umana o AI?”) + - Confronto su dubbi e curiosità + - Anticipazione del laboratorio: + - Domani proverete a scrivere prompt e far generare codice e progetti all’AI + - Lavorerete in gruppi per *guidare* l’intelligenza artificiale, non solo usarla + - ## [[References]] per preparare l'intervento + - [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + id:: 684ed422-c5f8-4bdb-99af-7c9fe1476021 + collapsed:: true + - - #[[Clip]] [[15-06-2025]] 16:10 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + Quando parliamo di AI generative ci riferiamo a modelli linguistici di grandi dimensioni (o LLM), un tipo di tecnologia in cui reti neurali profonde vengono addestrate con enormi quantità di documenti per elaborare e generare testi. + - - #[[Clip]] [[15-06-2025]] 16:10 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + In molti casi, questi modelli non sono in grado di capire quando una domanda è al di là delle loro capacità, e provano comunque a rispondere. + - - #[[Clip]] [[15-06-2025]] 16:10 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + i LLM hanno ancora un problema con le cosiddette [allucinazioni](https://www.ilpost.it/2024/05/22/ai-allucinazioni/), gli errori fattuali dei chatbot, che spesso inventano fatti e dettagli. + - - #[[Clip]] [[15-06-2025]] 16:10 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + il materiale di partenza su cui sono stati addestrati è incompleto, e le AI sono costrette a riempire le lacune, inventando di fatto informazioni (che sono comunque grammaticalmente corrette). + - - #[[Clip]] [[15-06-2025]] 16:10 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + Un esempio recente riguarda il quotidiano statunitense che ha [pubblicato](https://www.ilpost.it/2025/05/21/lista-consigli-libri-intelligenza-artificiale/) una lista di libri consigliati per l’estate, includendo titoli non esistenti, generati da un’intelligenza artificiale. + - - #[[Clip]] [[15-06-2025]] 16:11 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + Il settore dove questa tecnologia sta avendo l’impatto più profondo è probabilmente quello della programmazione informatica, tanto che in aziende come Microsoft [il 30 per cento del codice](https://www.cnbc.com/2025/04/29/satya-nadella-says-as-much-as-30percent-of-microsoft-code-is-written-by-ai.html) viene già scritto da AI. + - - #[[Clip]] [[15-06-2025]] 16:12 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + Ma le AI possono essere usate anche per scrivere (o tradurre) mail e documenti aziendali, o generare slide per presentazioni, mentre è nota da tempo la loro [inaffidabilità](https://www.ilpost.it/2024/07/28/matematica-intelligenza-artificiale/) nei calcoli matematici + - - #[[Clip]] [[15-06-2025]] 16:13 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + Il settore legale è stato uno dei primi a scontrarsi con le allucinazioni delle AI, come [dimostrato](https://www.businessinsider.com/increasing-ai-hallucinations-fake-citations-court-records-data-2025-5) dai molti casi in cui hanno prodotto documenti legali con riferimenti a leggi o sentenze del tutto inventati. Le allucinazioni sono così diffuse nell’ambiente legale da aver spinto l’avvocato francese Damien Charlotin a creare un sito che [raccoglie](https://www.damiencharlotin.com/hallucinations/) errori di questo tipo man mano che vengono scoperti. + - - #[[Clip]] [[15-06-2025]] 16:13 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + Le aziende che li sviluppano, infatti, sono sempre più in competizione tra loro e hanno capito che la maggioranza degli utenti preferisce un’AI che risponde sempre rispetto a una più cauta. + - - #[[Clip]] [[15-06-2025]] 16:14 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + intelligenze artificiali ruffiane” + - - #[[Clip]] [[15-06-2025]] 16:14 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + Dopo le critiche ricevute, l’azienda ha modificato le impostazioni ordinando al modello di «interagire con l’utente in modo caloroso ma onesto», mantenendo una certa «professionalità». + - - #[[Clip]] [[15-06-2025]] 16:15 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + «sacrificare, in alcuni casi, la veridicità in favore della ossequiosità». + - - #[[Clip]] [[15-06-2025]] 16:15 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + Verbosity Compensation, o «compensazione della verbosità», il fenomeno per cui i chatbot sembrano dare risposte più lunghe alle domande su cui sono più incerti, a causa della scarsità di informazioni disponibili. + - - #[[Clip]] [[15-06-2025]] 16:16 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + Il grande successo commerciale di sistemi da ChatGPT in poi ha cambiato l’approccio di molte aziende, che hanno abbandonato parte dell’iniziale cautela sul contenuto delle risposte per offrire un servizio che dia sempre una risposta agli utenti. + - - #[[Clip]] [[15-06-2025]] 16:21 [Perché spesso ChatGPT si inventa le cose - Il Post](https://www.ilpost.it/2025/06/10/perche-chatgpt-inventa-cose/) + In questo contesto, un fattore importante è la memoria, ovvero la capacità di ricordare determinati precedenti delle loro conversazioni con l’utente e usarli per adattare le loro risposte future. + - [Una lista di libri consigliati che non esistono - Il Post](https://www.ilpost.it/2025/05/21/lista-consigli-libri-intelligenza-artificiale/) + - [Why is ChatGPT so bad at math? | TechCrunch](https://techcrunch.com/2024/10/02/why-is-chatgpt-so-bad-at-math/) +- ## Approfondimento + collapsed:: true + - Si puo pensare di far realizzare alle studentesse un GPT specifico per il task di interesse. Realizzare un chatbot? + - L'anno scorso le ragazze avevano fatto un GPT per gestire l'ansia + - ![image.png](../assets/image_1749464049205_0.png) + - I tutor sono: + - Isabella + - Gennaro + - Alina + - Oggi [[10-06-2025]] abbiamo avuto una call con i tutor. Si e' deciso di investigare la strada di progettare una sessione di approfindimento che coinvolta tutte le fase principali relative all'uso di strumenti LLM etc. +- \ No newline at end of file diff --git a/pages/Presentazione dei documenti di monitoraggio.md b/pages/Presentazione dei documenti di monitoraggio.md new file mode 100644 index 00000000..4184f73e --- /dev/null +++ b/pages/Presentazione dei documenti di monitoraggio.md @@ -0,0 +1,5 @@ +tags:: #todoist-task, [[SERVICES/PHDICT]] +date:: [[16-06-2025]] - 16:49 +progress:: {{renderer :todomaster}} + +- ![image.png](../assets/image_1750085408113_0.png){:height 244, :width 1010} \ No newline at end of file diff --git a/pages/SERVICES___PHDICT.md b/pages/SERVICES___PHDICT.md index cfc20cfd..9be100e4 100644 --- a/pages/SERVICES___PHDICT.md +++ b/pages/SERVICES___PHDICT.md @@ -291,7 +291,10 @@ progress:: {{renderer :todomaster}} - Vedi Art 12 del [Regolamento](https://www.univaq.it/include/utilities/blob.php?table=regolamento&id=64&item=file) - - ## 2025/2026 #XLI ciclo + - CALENDARIO + - ![Bando Dottorato di Ricerca XLI ciclo_Comunicazione.pdf](../assets/Bando_Dottorato_di_Ricerca_XLI_ciclo_Comunicazione_1750159552604_0.pdf) - Overview borse (totale 14 con borsa, 4 senza): + collapsed:: true - [MODELLO](https://dottorati.mur.gov.it/php5/compilazione/2025/vis_modello.php?amm=0&codice=3907831713T97VJY3J86094281322294397041&c=DO&PREF_X_TABELLE=DOTT25&modello=A&db=MIUR9&chiave=7TKD5JWN9GHQRUM1295875256&x=15&y=23) - 6 MUR - 5 Regione @@ -314,7 +317,14 @@ progress:: {{renderer :todomaster}} - ((67d8451e-abb9-4a76-9982-be8e0d8b7507)) - Questo anche e' da vedere!!! - ## 2024/2025 #DM629 #DM630 #[[XL Ciclo]] - collapsed:: true + - ### Lavori commissione ammissione + - [Scheda informativa](https://www.univaq.it/include/utilities/blob.php?table=corso_dottorato&id=283&item=scheda_informativa) + [Commissione giudicatrice](https://www.univaq.it/include/utilities/blob.php?table=corso_dottorato&id=283&item=commissione) + [Elenco candidati ammessi](https://www.univaq.it/include/utilities/blob.php?table=corso_dottorato&id=283&item=ammessi) + [Verbale preliminare - Criteri](https://www.univaq.it/include/utilities/blob.php?table=corso_dottorato&id=283&item=verbale_preliminare_criteri) + [Risultati della valutazione dei titoli](https://www.univaq.it/include/utilities/blob.php?table=corso_dottorato&id=283&item=risultati_valutazione_titoli) + [Approvazione atti e graduatoria](https://www.univaq.it/include/utilities/blob.php?table=corso_dottorato&id=283&item=graduatoria) + - [Domande prova orale](https://www.univaq.it/include/utilities/blob.php?table=corso_dottorato&id=283&item=domanda_prova_orale) - ### #DM629 #DM630 - Passaggi importanti: - 1. il DM 629 (ex 118 - dottorati PNRR) assegna 779 borse  con finanziamento da 70mila euro (e 15+15 borse ai due dottorati nazionali accreditati nel 37° ciclo); @@ -368,7 +378,6 @@ progress:: {{renderer :todomaster}} - - - ## 2022/2023 #DM351 #DM352 #[[XXXVIII Ciclo]] - collapsed:: true - Decreti Ministeriali n. 351, n. 352 del 9 aprile 2022 e n. 925 del 29 luglio 2022 - ## REGOLAMENTI - [[@REGOLAMENTO_Dottorati_Ricerca_Modifica_DR_rep_597_01_06_2023.pdf]] [[STAR]] diff --git a/pages/SWEN.md b/pages/SWEN.md new file mode 100644 index 00000000..41256f9d --- /dev/null +++ b/pages/SWEN.md @@ -0,0 +1,3 @@ +### Meetings + - {{query (and [[meeting]] [[SWEN]])}} + query-table:: true \ No newline at end of file diff --git a/pages/TODOIST-LOGSEQED.md b/pages/TODOIST-LOGSEQED.md index b8a83525..b806b5bf 100644 --- a/pages/TODOIST-LOGSEQED.md +++ b/pages/TODOIST-LOGSEQED.md @@ -24,10 +24,10 @@ progress:: {{renderer :todomaster}} - TODO [#A] [[Progettazione Offerta Formativa]] todoist-desc:: logseq://graph/Logseq?page=Progettazione%20Offerta%20Formativa todoist-id:: [9205819498](https://app.todoist.com/app/task/9205819498) - SCHEDULED: <2025-06-17 Tue> -- TODO [#A] [[Missione STAF 2025]] + SCHEDULED: <2025-06-23 Mon> +- TODO [#C] [[Missione STAF 2025]] todoist-id:: [9135141990](https://app.todoist.com/app/task/9135141990) - SCHEDULED: <2025-06-15 Sun> + SCHEDULED: <2025-06-19 Thu> :LOGBOOK: CLOCK: [2025-06-11 Wed 11:37:54]--[2025-06-15 Sun 19:24:44] => 103:46:50 :END: @@ -47,7 +47,7 @@ progress:: {{renderer :todomaster}} - TODO [#B] [[Call per posizioni MOSAICO]] todoist-desc:: logseq://graph/Logseq?page=Call%20per%20posizioni%20MOSAICO todoist-id:: [8663268357](https://app.todoist.com/app/task/8663268357) - SCHEDULED: <2025-06-16 Mon> + SCHEDULED: <2025-06-20 Fri> :LOGBOOK: CLOCK: [2025-06-14 Sat 11:21:37]--[2025-06-14 Sat 21:27:23] => 10:05:46 :END: @@ -57,26 +57,26 @@ progress:: {{renderer :todomaster}} - TODO [#B] [[PAPERS/MOSAICO-Technical-Report]] todoist-desc:: logseq://graph/Logseq?page=PAPERS%2FMOSAICO-Technical-Report todoist-id:: [9187744429](https://app.todoist.com/app/task/9187744429) - SCHEDULED: <2025-06-17 Tue> + SCHEDULED: <2025-06-19 Thu> :LOGBOOK: CLOCK: [2025-06-07 Sat 13:49:10]--[2025-06-08 Sun 21:19:31] => 31:30:21 CLOCK: [2025-06-13 Fri 12:00:06]--[2025-06-14 Sat 09:56:22] => 21:56:16 :END: -- TODO [#A] [[Preparazione Intervento PINKAMP]] +- DONE [#A] [[Preparazione Intervento PINKAMP]] todoist-id:: [9179967916](https://app.todoist.com/app/task/9179967916) - SCHEDULED: <2025-06-16 Mon> -- TODO [#A] [[Aggiornamento uso fondi progetti]] + SCHEDULED: <2025-06-19 Thu> +- TODO [#B] [[Aggiornamento uso fondi progetti]] todoist-id:: [9143259271](https://app.todoist.com/app/task/9143259271) - SCHEDULED: <2025-06-16 Mon> -- TODO [[[mosaico-all] MOSAICO meetings in Rome July 2025]] + SCHEDULED: <2025-06-20 Fri> +- TODO [#A] [[[mosaico-all] MOSAICO meetings in Rome July 2025]] todoist-desc:: From: zhanna.zhussupova@imt-atlantique.fr todoist-id:: [9224183665](https://app.todoist.com/app/task/9224183665) - SCHEDULED: <2025-06-16 Mon> + SCHEDULED: <2025-06-21 Sat> - TODO [[Invited talk at LLMA4SE Summer School website]] todoist-id:: [9201031612](https://app.todoist.com/app/task/9201031612) todoist-desc:: From: chemacm@unex.es SCHEDULED: <2025-08-18 Mon> -- TODO [#A] [[Missione Emeliot Salerno - Luglio 2025]] +- TODO [#B] [[Missione Emeliot Salerno - Luglio 2025]] todoist-desc:: From: leonardo.mariani@unimib.it todoist-id:: [9161916557](https://app.todoist.com/app/task/9161916557) SCHEDULED: <2025-06-19 Thu> @@ -86,7 +86,29 @@ progress:: {{renderer :todomaster}} - TODO [#B] [[Linee guida afferenza Collegio dottorato ICT]] todoist-desc:: [Linee guida per la valutazione richieste afferenza dottorato ICT.docx](https://univaq-my.sharepoint.com/:w:/g/personal/davide_diruscio_univaq_it/EbLmq-bFlvZDpxTZLeHiQFgBBlAIxRR_3aoAZsNBUHFyXw?e=cXOsS3) todoist-id:: [8912715542](https://app.todoist.com/app/task/8912715542) - SCHEDULED: <2025-06-16 Mon> + SCHEDULED: <2025-06-20 Fri> :LOGBOOK: CLOCK: [2025-06-13 Fri 11:59:57]--[2025-06-14 Sat 09:56:22] => 21:56:25 - :END: \ No newline at end of file + :END: +- TODO [#A] [[Presentazione dei documenti di monitoraggio]] + todoist-desc:: From: [antonio.mecozzi@univaq.it](mailto:antonio.mecozzi@univaq.it) + todoist-id:: [9223534564](https://app.todoist.com/app/task/9223534564) + SCHEDULED: <2025-06-19 Thu> +- TODO [#A] [[🗓 TIASSISTO24 - MEETING BANDO REGIONE ABRUZZO 1.1.1.2]] + todoist-desc:: From: executiveassistant@e.read.ai + todoist-id:: [9248741876](https://app.todoist.com/app/task/9248741876) + SCHEDULED: <2025-06-19 Thu> +- TODO [#A] [[PRIN 2020 - scadenza rendicontazione finale]] + todoist-id:: [9134866367](https://app.todoist.com/app/task/9134866367) + todoist-desc:: From: proget@strutture.univaq.it + SCHEDULED: <2025-06-19 Thu> +- TODO [#C] [[Missione ROMA Mosaico]] + todoist-id:: [9204561368](https://app.todoist.com/app/task/9204561368) + SCHEDULED: <2025-06-20 Fri> +- DONE [#B] [[MODELS: 10 years most infuential paper selection committee]] + todoist-desc:: From: manuel.wimmer@jku.at + todoist-id:: [9153069465](https://app.todoist.com/app/task/9153069465) + SCHEDULED: <2025-06-19 Thu> +- TODO [[PAPERS/2025-LLM-GENERATION]] + todoist-id:: [9273049128](https://app.todoist.com/app/task/9273049128) + SCHEDULED: <2025-06-19 Thu> \ No newline at end of file diff --git a/pages/TOSEM-2024-0648.md b/pages/TOSEM-2024-0648.md index c0a53e68..99315071 100644 --- a/pages/TOSEM-2024-0648.md +++ b/pages/TOSEM-2024-0648.md @@ -13,7 +13,6 @@ parent:: todoist:: https://app.todoist.com/app/task/tosem-2024-0648-reviewer-agreed-6WQgFVcxWqGWQvWg - ### [[Highlights]] - collapsed:: true - # Annotazioni   (16/12/2024, 12:55:04) @@ -121,14 +120,4 @@ todoist:: https://app.todoist.com/app/task/tosem-2024-0648-reviewer-agreed-6WQgF - The description of Figure 1's "Configuration box" could be expanded to include motivations for the refactoring process, such as updating third-party libraries or applying design patterns. - While the paper identifies different root causes and bug symptoms, it could provide more qualitative discussions or examples to help readers understand these categories better. - The distinction between "Initial preconditions" and "Final conditions checking" (e.g., for the "Make Static" refactoring) is unclear. This differentiation should be explained in greater depth. - - The paper mentions that the authors categorized bugs based on four aspects: 1) refactoring type, 2) root cause, 3) symptom, and 4) input characteristics, but it does not clearly explain how these labels were assigned. Explanatory examples and a discussion on the labeling process are necessary. - - #### - - ### [[REVIEWS/Notes]] - - ### YELLOW CONCERNS - background-color:: yellow - - {{query (and [[ffd400]] [[TOSEM-2024-0648]] )}} - collapsed:: true - - ### ❓️Questions - - {{query (and [[question]] [[TOSEM-2024-0648]] )[[question]]}} - query-table:: true - query-properties:: [:block] \ No newline at end of file + - The paper mentions that the authors categorized bugs based on four aspects: 1) refactoring type, 2) root cause, 3) symptom, and 4) input characteristics, but it does not clearly explain how these labels were assigned. Explanatory examples and a discussion on the labeling process are necessary. \ No newline at end of file diff --git a/pages/Writing Challenges.md b/pages/Writing Challenges.md index 21178cf3..e3f0029d 100644 --- a/pages/Writing Challenges.md +++ b/pages/Writing Challenges.md @@ -9,6 +9,8 @@ icon:: 👀 query-sort-by:: block query-sort-desc:: true - --- +- Prompt copilot + - `Vorrei migliorare la mia scrittura creativa prendendo esempio da alcuni classici della letteratura. Puoi aiutarmi con alcuni esempi ed esercizi?` - [[31-05-2025]] collapsed:: true - DONE **🎯 Sfida di scrittura: “Il messaggio nella macchina”** diff --git a/pages/hls__Orario_definitivo_prima_settimana_1750056154238_0.md b/pages/hls__Orario_definitivo_prima_settimana_1750056154238_0.md new file mode 100644 index 00000000..ce986706 --- /dev/null +++ b/pages/hls__Orario_definitivo_prima_settimana_1750056154238_0.md @@ -0,0 +1,8 @@ +file:: [Orario_definitivo_prima_settimana_1750056154238_0.pdf](../assets/Orario_definitivo_prima_settimana_1750056154238_0.pdf) +file-path:: ../assets/Orario_definitivo_prima_settimana_1750056154238_0.pdf + +- Introduzione al dominio applicativo “Generative AI”: Large Language Models e loro uso nell'ingegneria del software(area Informatica)(Davide Di Ruscio + ls-type:: annotation + hl-page:: 1 + hl-color:: green + id:: 684fbd0a-e948-4f25-9fd4-4ca045edad83 \ No newline at end of file diff --git a/pages/🗓 TIASSISTO24 - MEETING BANDO REGIONE ABRUZZO 1.1.1.2.md b/pages/🗓 TIASSISTO24 - MEETING BANDO REGIONE ABRUZZO 1.1.1.2.md new file mode 100644 index 00000000..1daa8169 --- /dev/null +++ b/pages/🗓 TIASSISTO24 - MEETING BANDO REGIONE ABRUZZO 1.1.1.2.md @@ -0,0 +1,5 @@ +tags:: #todoist-task, [[PROJECTS]] +date:: [[19-06-2025]] - 13:11 +progress:: {{renderer :todomaster}} + +- \ No newline at end of file