{"id":"https://openalex.org/W7225007207","doi":"https://doi.org/10.5281/zenodo.23829457","title":"What's in a Soul? A Provenance-Complete Dataset of AI Agent Persona Prompts in the Wild on GitHub","display_name":"What's in a Soul? A Provenance-Complete Dataset of AI Agent Persona Prompts in the Wild on GitHub","publication_year":2026,"publication_date":"2026-10-31","ids":{"openalex":"https://openalex.org/W7225007207","doi":"https://doi.org/10.5281/zenodo.23829457"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23829457","doi":"https://doi.org/10.5281/zenodo.23829457","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23829457","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23829457","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160270181","display_name":"Tom Jaejoon Lee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Tom Jaejoon","raw_affiliation_strings":["ClawSouls, ModuLabs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ClawSouls, ModuLabs","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010553661","display_name":"Eunji Shin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shin, Eunji","raw_affiliation_strings":["ModuLabs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ModuLabs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.3666999936103821,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.3666999936103821,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.30979999899864197,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.07240000367164612,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ai-agent-identity","display_name":"AI agent identity","score":0.5550000071525574},{"id":"https://openalex.org/keywords/github-repositories","display_name":"GitHub repositories","score":0.621999979019165},{"id":"https://openalex.org/keywords/behavioral-rules","display_name":"behavioral rules","score":0.7170000076293945},{"id":"https://openalex.org/keywords/conditional-instructions","display_name":"conditional instructions","score":0.9649999737739563},{"id":"https://openalex.org/keywords/dataset-provenance","display_name":"dataset provenance","score":0.421999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060999870300293},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.5893999934196472},{"id":"https://openalex.org/C313442","wikidata":"https://www.wikidata.org/wiki/Q778556","display_name":"Persona","level":2,"score":0.5859000086784363},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5210999846458435},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4196000099182129},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4097000062465668},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.3596999943256378},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35350000858306885},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.35280001163482666},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3345000147819519},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.29750001430511475},{"id":"https://openalex.org/C136815107","wikidata":"https://www.wikidata.org/wiki/Q154242","display_name":"Nothing","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.25209999084472656},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23829457","doi":"https://doi.org/10.5281/zenodo.23829457","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23829457","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23829458","doi":"https://doi.org/10.5281/zenodo.23829458","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23829458","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23829457","doi":"https://doi.org/10.5281/zenodo.23829457","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23829457","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7214618294","https://openalex.org/W7118182435","https://openalex.org/W7127065051","https://openalex.org/W7163942374","https://openalex.org/W4416035019","https://openalex.org/W7204188512","https://openalex.org/W7224940638","https://openalex.org/W7133569819","https://openalex.org/W7213415131","https://openalex.org/W7160904127"],"abstract_inverted_index":{"AI":[0],"agents":[1],"are":[2,29],"increasingly":[3],"defined":[4],"by":[5,164,245],"documents":[6],"rather":[7],"than":[8],"code.":[9],"Files":[10],"such":[11,197],"as":[12,114,198],"SOUL.md,":[13],"persona.md,":[14],"and":[15,24,27,81,91,95,129,147,200,210,220,225,261],"character":[16],"cards":[17],"declare":[18,59,234],"an":[19],"agent's":[20],"identity,":[21],"values,":[22],"tone,":[23],"behavioral":[25,217],"limits,":[26],"they":[28],"accumulating":[30],"in":[31,44,202],"public":[32,73],"repositories.":[33],"Prior":[34],"work":[35],"that":[36,100,233],"mined":[37],"prompts":[38,70],"from":[39,71,154,181],"repositories":[40,106],"studied":[41],"strings":[42],"embedded":[43],"source":[45,105],"code":[46],"or":[47],"the":[48,61,121,134,190,193,211,242,249],"management":[49],"practices":[50],"around":[51],"prompt":[52],"files,":[53],"but":[54],"not":[55],"what":[56],"these":[57],"files":[58,232],"about":[60],"agent.":[62],"We":[63,205],"release":[64,206],"a":[65,82,110,148],"dataset":[66,255],"of":[67,104,150,195,264],"281":[68],"persona":[69],"168":[72],"GitHub":[74],"repositories,":[75],"collected":[76],"with":[77,231],"five":[78],"path-based":[79],"searches":[80],"manual":[83],"inclusion":[84],"rule.":[85],"Every":[86],"record":[87,115],"pins":[88],"repository,":[89],"path,":[90,241],"commit":[92],"SHA":[93,132],"(281/281)":[94],"was":[96,168],"re-verified":[97],"byte-for-byte":[98],"at":[99],"SHA.":[101],"Because":[102],"42%":[103],"carry":[107],"no":[108],"license,":[109],"redistribution":[111],"gate":[112],"implemented":[113],"fields":[116],"ships":[117],"full":[118,162],"text":[119],"for":[120,133],"179":[122],"records":[123],"(64%)":[124],"whose":[125],"licenses":[126],"permit":[127],"it":[128],"metadata":[130],"plus":[131],"remaining":[135],"102.":[136],"An":[137],"accompanying":[138],"two-axis":[139],"labeling":[140],"scheme":[141],"codes":[142],"content":[143,175],"(nine":[144],"binary":[145],"facets":[146,176],"count":[149],"conditional":[151,221],"clauses)":[152],"separately":[153],"form":[155,167,226],"(an":[156],"ordinal":[157],"prose/flat/full-pack":[158],"scale).":[159],"In":[160],"independent":[161],"coding":[163],"two":[165],"raters,":[166,216],"reliable":[169],"(Krippendorff's":[170],"\u03b1":[171],"=":[172],"0.84)":[173],"while":[174],"fell":[177],"below":[178],"threshold":[179],"(\u03b1":[180],"\u22120.11":[182],"to":[183,228],"0.55).":[184],"Disagreements":[185],"were":[186],"mostly":[187],"one-directional,":[188],"so":[189],"raters":[191],"placed":[192],"boundaries":[194],"concepts":[196],"identity":[199],"goal":[201],"different":[203],"places.":[204],"both":[207,215],"raters'":[208],"labels":[209],"disagreement":[212],"lists.":[213],"Under":[214],"rules":[218],"(83\u201390%)":[219],"instructions":[222],"(72\u201384%)":[223],"dominate,":[224],"skews":[227],"full-pack":[229],"(74\u201378%),":[230],"nothing":[235],"concentrated":[236],"outside":[237],"it.":[238],"The":[239,254],"soul":[240],"most":[243,250],"common":[244],"repository":[246],"count,":[247],"has":[248],"uniform":[251],"writing":[252],"style.":[253],"supports":[256],"persona-fidelity":[257],"stimuli,":[258],"classification-boundary":[259],"studies,":[260],"longitudinal":[262],"tracking":[263],"conventions.":[265],"DOI:":[266],"10.5281/zenodo.23230144.":[267]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-11-01T00:00:00"}