{"id":"https://openalex.org/W7225433681","doi":"https://doi.org/10.5281/zenodo.24012523","title":"The Gap Between Self-Reported Success and External Acceptance: A Single-Case Study of an AI Agent with a Prediction Ledger","display_name":"The Gap Between Self-Reported Success and External Acceptance: A Single-Case Study of an AI Agent with a Prediction Ledger","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225433681","doi":"https://doi.org/10.5281/zenodo.24012523"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24012523","doi":"https://doi.org/10.5281/zenodo.24012523","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24012523","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","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24012523","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161050400","display_name":"ShuQing Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guo, ShuQing","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161050400"],"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/T10260","display_name":"Software Engineering Research","score":0.22939999401569366,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.22939999401569366,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.2206999957561493,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.09719999879598618,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/acceptance-criteria","display_name":"acceptance criteria","score":0.46799999475479126},{"id":"https://openalex.org/keywords/falsifiability","display_name":"falsifiability","score":0.8579999804496765},{"id":"https://openalex.org/keywords/external-review","display_name":"external review","score":0.4490000009536743},{"id":"https://openalex.org/keywords/ai-coding-agents","display_name":"coding agents","score":0.5759999752044678},{"id":"https://openalex.org/keywords/coverage-rate","display_name":"coverage rate","score":0.4740000069141388}],"concepts":[{"id":"https://openalex.org/C97399411","wikidata":"https://www.wikidata.org/wiki/Q825367","display_name":"Coin flipping","level":2,"score":0.5611000061035156},{"id":"https://openalex.org/C91302708","wikidata":"https://www.wikidata.org/wiki/Q2732056","display_name":"Ledger","level":2,"score":0.5167999863624573},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4871000051498413},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4681999981403351},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3691999912261963},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.35519999265670776},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28859999775886536},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C163164238","wikidata":"https://www.wikidata.org/wiki/Q2737027","display_name":"Failure rate","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2565999925136566}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24012523","doi":"https://doi.org/10.5281/zenodo.24012523","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24012523","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.24012524","doi":"https://doi.org/10.5281/zenodo.24012524","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24012524","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.24012523","doi":"https://doi.org/10.5281/zenodo.24012523","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24012523","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/W7219119611","https://openalex.org/W7223227692","https://openalex.org/W7220891520","https://openalex.org/W7171331735","https://openalex.org/W7225095518","https://openalex.org/W7220860411","https://openalex.org/W7171926261","https://openalex.org/W7222150483","https://openalex.org/W7213577503","https://openalex.org/W7160897323"],"abstract_inverted_index":{"When":[0],"an":[1],"AI":[2],"agent":[3,28,38,67,204],"reports":[4],"that":[5,12,111,126,151,171,211,225,265],"a":[6,20,24,31,41,133,155,162,187,195,209,212],"task":[7],"succeeded,":[8],"how":[9,50,54,60,198],"much":[10],"of":[11,23,44,95,107,157,164,197,203,231,264],"report":[13,125],"has":[14],"been":[15],"independently":[16],"checked?":[17],"We":[18,123,167,182,235],"present":[19],"single-case":[21],"study":[22],"locally":[25],"deployed":[26],"coding":[27],"equipped":[29],"with":[30,140],"prediction":[32],"ledger:":[33],"before":[34],"any":[35,115],"modification,":[36],"the":[37,71,83,96,108,127,141,158,172,192,200,223,226,232,239,248,259,262],"must":[39],"record":[40,247],"bet":[42],"consisting":[43],"four":[45],"questions":[46],"(what":[47],"will":[48,52],"succeed,":[49],"it":[51],"fail,":[53],"failure":[55],"would":[56,62],"be":[57,63],"detected,":[58],"and":[59,148,189,208,244],"success":[61,86,213],"recognized).":[64],"A":[65],"separate":[66],"then":[68],"evaluates":[69],"whether":[70],"stated":[72],"acceptance":[73],"criterion":[74],"is":[75,88,154,194,219,229],"falsifiable.":[76],"Across":[77],"147":[78],"recorded":[79],"bets":[80,99,110],"(116":[81],"settled),":[82],"agent's":[84],"own":[85],"rate":[87,214],"104/116":[89],"=":[90,105,121],"89.7%,":[91],"while":[92,143],"only":[93,220],"16":[94,117],"116":[97],"settled":[98],"were":[100,118],"ever":[101],"externally":[102],"reviewed":[103,227,252],"(16/116":[104],"13.8%);":[106],"25":[109],"entered":[112],"review":[113],"at":[114,242],"time,":[116],"rejected":[119],"(16/25":[120],"64.0%).":[122],"further":[124],"measured":[128],"coverage":[129],"ratio":[130],"shifts":[131],"on":[132],"six-minute":[134],"scale,":[135],"because":[136,176],"its":[137,144],"numerator":[138],"grows":[139],"sample":[142,238],"denominator":[145],"does":[146],"not,":[147],"we":[149,255],"argue":[150],"this":[152,165,185],"instability":[153],"property":[156],"metric":[159],"rather":[160],"than":[161],"defect":[163],"system.":[166],"find":[168],"no":[169,177],"evidence":[170],"ledger":[173],"improves":[174],"outcomes,":[175],"control":[178],"condition":[179],"was":[180],"run.":[181],"accordingly":[183],"frame":[184],"as":[186],"negative":[188],"diagnostic":[190],"result:":[191],"contribution":[193],"measurement":[196],"large":[199],"unchecked":[201],"fraction":[202],"self-assessment":[205],"can":[206,256],"be,":[207],"warning":[210],"computed":[215],"over":[216],"self-reported":[217],"outcomes":[218],"informative":[221],"to":[222],"extent":[224],"subset":[228],"representative":[230],"unreviewed":[233,240],"one.":[234],"did":[236,245],"not":[237,246],"cards":[241],"random":[243],"selection":[249],"rationale":[250],"for":[251],"cards,":[253],"so":[254],"establish":[257],"neither":[258],"direction":[260],"nor":[261],"magnitude":[263],"non-representativeness.":[266]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}