{"id":"https://openalex.org/W7220690107","doi":"https://doi.org/10.48550/arxiv.2610.04737","title":"PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution","display_name":"PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution","publication_year":2026,"publication_date":"2026-10-03","ids":{"openalex":"https://openalex.org/W7220690107","doi":"https://doi.org/10.48550/arxiv.2610.04737"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.04737","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04737","pdf_url":"https://arxiv.org/pdf/2610.04737","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.04737","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007938204","display_name":"Pierre-Luc St-Charles","orcid":"https://orcid.org/0000-0001-7761-2839","observed_orcids":["https://orcid.org/0000-0001-7761-2839"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"St-Charles, Pierre-Luc","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030498265","display_name":"Alessandro Palmas","orcid":"https://orcid.org/0000-0001-5773-9349","observed_orcids":["https://orcid.org/0000-0001-5773-9349"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Palmas, Alessandro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134098489","display_name":"Damiano Fornasiere","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fornasiere, Damiano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157698221","display_name":"Storm Lei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Storm","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028787566","display_name":"Mirko Bronzi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bronzi, Mirko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012477311","display_name":"Jean-Pierre Ren\u00e9 Falet","orcid":"https://orcid.org/0000-0002-7576-2347","observed_orcids":["https://orcid.org/0000-0002-7576-2347"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Falet, Jean-Pierre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034688833","display_name":"Iulian Vlad Serban","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Serban, Iulian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086198262","display_name":"Yoshua Bengio","orcid":"https://orcid.org/0000-0002-9322-3515","observed_orcids":["https://orcid.org/0000-0002-9322-3515"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bengio, Yoshua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":true,"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":0.47780001163482666,"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":0.47780001163482666,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.29030001163482666,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.08569999784231186,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/shortcut-learning","display_name":"shortcut learning","score":0.46299999952316284},{"id":"https://openalex.org/keywords/execution-traces","display_name":"execution traces","score":0.6050000190734863},{"id":"https://openalex.org/keywords/counterfactual-evaluation","display_name":"counterfactual evaluation","score":0.7459999918937683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8174999952316284},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7114999890327454},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.7046999931335449},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.5663999915122986},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5551000237464905},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5504000186920166},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45739999413490295},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4381999969482422},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4284000098705292},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.36329999566078186},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C164155591","wikidata":"https://www.wikidata.org/wiki/Q2067766","display_name":"Satisfiability modulo theories","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3224000036716461},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.295199990272522},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2784999907016754},{"id":"https://openalex.org/C69637215","wikidata":"https://www.wikidata.org/wiki/Q702362","display_name":"Default","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C20574231","wikidata":"https://www.wikidata.org/wiki/Q844605","display_name":"Backward compatibility","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25589999556541443},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.04737","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04737","pdf_url":"https://arxiv.org/pdf/2610.04737","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.04737","doi":"https://doi.org/10.48550/arxiv.2610.04737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.04737","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"pmh:oai:arXiv.org:2610.04737","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.04737","pdf_url":"https://arxiv.org/pdf/2610.04737","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220690107.pdf","grobid_xml":"https://content.openalex.org/works/W7220690107.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416932218","https://openalex.org/W4416932930","https://openalex.org/W7154354850","https://openalex.org/W4417068520","https://openalex.org/W7130861386","https://openalex.org/W7127116451","https://openalex.org/W4417068656","https://openalex.org/W7223379962","https://openalex.org/W7128796982","https://openalex.org/W7135192748"],"abstract_inverted_index":{"Reasoning":[0],"models":[1],"can":[2,34,86,189],"remain":[3],"capable":[4],"of":[5,177,193],"solving":[6],"a":[7,19,24,51,63,102,135,171,232],"task":[8,71,84],"while":[9,145,207],"still":[10,146],"defaulting":[11],"to":[12,219],"cheaper":[13],"but":[14,31,214],"misleading":[15,151],"shortcuts.":[16],"This":[17],"creates":[18],"central":[20],"oversight":[21,57,238],"problem:":[22],"when":[23,150],"model":[25,137],"gives":[26],"an":[27,35],"answer":[28],"with":[29,127,155],"plausible":[30],"incomplete":[32],"reasoning,":[33],"overseer":[36],"determine":[37],"whether":[38],"that":[39,138,182,196,240],"output":[40],"should":[41],"be":[42,87],"trusted?":[43],"To":[44],"study":[45],"this":[46,178,227],"problem,":[47],"we":[48,133],"introduce":[49],"PyINE,":[50,68],"framework":[52,99],"for":[53,78,121,236],"scalable":[54],"elicitation":[55],"and":[56,80,83,113,170,217,244],"using":[58],"instrumented":[59],"Python":[60],"programs":[61,69],"as":[62,175],"verifiable":[64,128],"execution":[65,73,111,143],"substrate.":[66],"In":[67],"define":[70],"environments,":[72],"traces":[74,112],"provide":[75],"authoritative":[76],"labels":[77],"outcomes":[79,144],"intermediate":[81],"facts,":[82],"variants":[85,119],"generated":[88],"mechanically":[89],"rather":[90],"than":[91],"through":[92],"static":[93],"human":[94],"annotation.":[95],"We":[96,160,180],"instantiate":[97],"the":[98,156,186,194],"in":[100],"PyINE-v1,":[101],"first":[103],"release":[104],"built":[105],"from":[106],"nearly":[107],"one":[108],"million":[109],"deterministic":[110],"over":[114],"500,000":[115],"matched":[116],"LLM-generated":[117],"code":[118],"used":[120],"counterfactual":[122],"evaluation.":[123],"Using":[124],"standard":[125],"RL":[126],"rewards":[129],"on":[130],"cue-varied":[131],"tasks,":[132],"train":[134],"shortcut-following":[136],"improves":[139],"substantially":[140,215],"at":[141,185],"predicting":[142],"making":[147],"systematic":[148],"errors":[149],"human-facing":[152],"cues":[153],"conflict":[154],"program's":[157],"realized":[158],"behavior.":[159],"then":[161],"evaluate":[162],"activation":[163],"probes,":[164],"trained":[165],"text":[166],"classifiers,":[167],"prompted":[168],"judges,":[169],"lightweight":[172],"debate":[173],"protocol":[174],"overseers":[176,201],"model.":[179],"find":[181],"performance":[183],"pooled":[184],"dataset":[187],"level":[188],"hide":[190],"weak":[191],"coverage":[192,229],"failures":[195],"matter":[197],"most:":[198],"cheap":[199],"learned":[200],"often":[202],"miss":[203],"rare":[204],"shortcut-driven":[205],"errors,":[206],"stronger":[208],"model-based":[209],"checks":[210],"are":[211,241],"more":[212],"balanced":[213],"costlier":[216],"harder":[218],"turn":[220],"into":[221,231],"reliable":[222],"thresholded":[223],"decisions.":[224],"PyINE-v1":[225],"turns":[226],"failure-mode":[228],"problem":[230],"reusable":[233],"experimental":[234],"setting":[235],"developing":[237],"methods":[239],"verifiable,":[242],"failure-mode-aware,":[243],"cost-sensitive.":[245]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-07T00:00:00"}