[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84357-en":3,"doc-seo-84357-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},84357,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","ArtMine Discovering and Formalizing Artistic Processes","Understanding how artworks are created requires reasoning about iterative decisions, material operations, and contextual influences shaping artistic production. While generative AI can synthesize high-fidelity finished outputs, it mainly models distributions over artifacts rather than the creative process behind them. ArtMine presents a framework that discovers and formalizes artistic processes from heterogeneous historical evidence, builds a structured evidence repository, infers evidence-grounded production steps via Peircean abductive reasoning, and refines outputs through self-reflection against reference artworks, enabling coherent and auditable process representations for human-AI co-creativity.","ArtMine: Discovering and Formalizing Artistic Processes  \nKaustubh Kumar 1 2 Ashutosh Ranjan 1 Vivek Srivastava 1 Blessin Varkey 1 Shirish Karande 1  \narXiv :2607 .0833 1v 1 [ cs .LG] 9 Jul 2026  \nAbstract  \nUnderstanding how artworks are created requires reasoning about the iterative decisions, material operations, and contextual influences that shape artistic production. While recent generative AI systems can synthesize artworks with high fidelity, they primarily model distributions over finished artifacts rather than the creative processes underlying their creation. In practice, artistic workflows are only partially documented through fragmented sources such as archival records, preparatory studies, correspondence, etc., making process-level understanding difficult to formalize computationally. In this work, we introduce ArtMine, a framework for discovering and formalizing artistic processes from heterogeneous historical evidence. Our approach synthesizes heterogeneous artwork evidence into a structured repository, from which a Peircean abductive agent infers evidence-grounded production steps. These steps are converted into a compositional graph and rendering prompt, then optimized through selfreflection over deviations between the generated and reference artworks. We provide a preliminary proof-of-concept case study using open-domain historical sources across multiple artists and artistic movements, demonstrating that fragmented documentary evidence can support coherent, interpretable, and auditable representations of artistic workflows. By modeling creative processes rather than only final artifacts, our work moves toward process-centered human-AI co-creativity systems that can support artistic interpretation, creative education, reflective collaboration, and computational studies of cultural production.  \n1TCS Research, Pune, India 2Indian Institue  \nof Technology, Patna, India. Correspondence to:  \nKaustubh Kumar \u003C2201mm14 [kaustubh@iitp.ac.in](kaustubh@iitp.ac.in) >, Ashutosh Ranjan \u003C[ashutosh.ranjan2@tcs.com](ashutosh.ranjan2@tcs.com) >, Vivek Srivastava \u003C[srivastava.vivek2@tcs.com](srivastava.vivek2@tcs.com) >, Blessin Varkey \u003C[blessin.varkey@tcs.com](blessin.varkey@tcs.com) >, Shirish Karande \u003C[shirish.karande@tcs.com](shirish.karande@tcs.com) > .  \nICML’26 Workshop on Human-AI Co-Creativity, Seoul, South Korea. Copyright 2026 by the author(s) .  \n1. Introduction  \nRecent progress in generative AI has been primarily driven by learning distributions over completed artifacts such as images, text, music, and video (Brown et al., 2020 ; Ho et al., 2020 ; Rombach et al., 2022) . These systems can reproduce the stylistic and semantic properties of humancreated works with remarkable fidelity, but they largely model what creative works look like rather than how they are made. The sequence of decisions, revisions, material operations, and intermediate reasoning that shape creative practice typically remains latent.  \nThis limitation matters for human-AI co-creativity, where collaboration often depends on intermediate processes rather than final outputs alone. Artists iteratively sketch, refine, critique, and revise their work, while current generative systems operate primarily through prompt-to-artifact generation. At the same time, substantial evidence about creative processes already exists outside of the artifact itself. Artist correspondence, preparatory sketches, conservation reports, provenance records, technical imaging, and scholarly critique collectively form a fragmented but information-rich record of artistic production. Human scholars routinely use such evidence to reconstruct plausible production trajectories and understand stylistic evolution. However, despite advances in research agents (Nakano et al., 2021 ; Yao et al., 2022 ; Shinn et al., 2023) and computational creativity (Co  \nhen, 1995 ; Colton, 2012), these documentary records have rarely been treated as supervision to model creative processes.  \nIn th","cbCaio0wHwDvsviA","https://ap.wps.com/l/cbCaio0wHwDvsviA","pdf",19397912,6,1,47,"English","en",105,"# Introduction\n## Process discovery from historical evidence\n## ArtMine framework and workflow","[{\"question\":\"Why are existing generative AI systems limited for understanding artistic creation?\",\"answer\":\"They primarily model distributions over completed artifacts, capturing what works look like rather than the latent sequence of decisions, revisions, and material operations that produced them.\"},{\"question\":\"What is ArtMine designed to do?\",\"answer\":\"ArtMine focuses on discovering and formalizing artistic processes by inferring structured, auditable sequences of production steps from heterogeneous historical documentary evidence.\"},{\"question\":\"How does ArtMine infer and improve the production process it reconstructs?\",\"answer\":\"A deep-research agent organizes evidence into a structured repository, a Peircean abductive agent infers evidence-grounded production trajectories, and self-reflection updates optimize a rendering prompt based on deviations between generated and reference artworks.\"}]",1784195063,118,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"artmine-discovering-and-formalizing-artistic-processes","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/artmine-discovering-and-formalizing-artistic-processes/84357/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-28","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why are existing generative AI systems limited for understanding artistic creation?","Question",{"text":76,"@type":77},"They primarily model distributions over completed artifacts, capturing what works look like rather than the latent sequence of decisions, revisions, and material operations that produced them.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What is ArtMine designed to do?",{"text":81,"@type":77},"ArtMine focuses on discovering and formalizing artistic processes by inferring structured, auditable sequences of production steps from heterogeneous historical documentary evidence.",{"name":83,"@type":74,"acceptedAnswer":84},"How does ArtMine infer and improve the production process it reconstructs?",{"text":85,"@type":77},"A deep-research agent organizes evidence into a structured repository, a Peircean abductive agent infers evidence-grounded production trajectories, and self-reflection updates optimize a rendering prompt based on deviations between generated and reference artworks.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]