{"id":"https://openalex.org/W7225614016","doi":"https://doi.org/10.5281/zenodo.24090559","title":"Guessing Without Momentum: A Language Model States the Rules but Skips the Test","display_name":"Guessing Without Momentum: A Language Model States the Rules but Skips the Test","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225614016","doi":"https://doi.org/10.5281/zenodo.24090559"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24090559","doi":"https://doi.org/10.5281/zenodo.24090559","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24090559","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.24090559","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093054926","display_name":"Andrei C. Aioanei","orcid":"https://orcid.org/0000-0001-5547-9969","observed_orcids":["https://orcid.org/0000-0001-5547-9969"]},"institutions":[{"id":"https://openalex.org/I2802635041","display_name":"Technische Informationsbibliothek (TIB)","ror":"https://ror.org/04aj4c181","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2802635041","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"AIOANEI, ANDREI","raw_affiliation_strings":["Technische Informationsbibliothek (TIB)"],"raw_orcid":"https://orcid.org/0000-0001-5547-9969","affiliations":[{"raw_affiliation_string":"Technische Informationsbibliothek (TIB)","institution_ids":["https://openalex.org/I2802635041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067133778","display_name":"Jens Lehmann","orcid":"https://orcid.org/0000-0001-9108-4278","observed_orcids":["https://orcid.org/0000-0001-9108-4278","https://orcid.org/0000-0001-8407-0417"]},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]},{"id":"https://openalex.org/I4405263462","display_name":"Institut f\u00fcr Angewandte Informatik (InfAI) e. V.","ror":"https://ror.org/01f7nea92","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I4405263462"]},{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lehmann, Jens","raw_affiliation_strings":["Technische Universit\u00e4t Dresden","Amazon (Germany)","Institute for Applied Informatics (InfAI)"],"raw_orcid":"https://orcid.org/0000-0001-9108-4278","affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Dresden","institution_ids":["https://openalex.org/I78650965"]},{"raw_affiliation_string":"Amazon (Germany)","institution_ids":["https://openalex.org/I4210089985"]},{"raw_affiliation_string":"Institute for Applied Informatics (InfAI)","institution_ids":["https://openalex.org/I4405263462"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102785999","display_name":"Sahar Vahdati","orcid":"https://orcid.org/0000-0002-7171-169X","observed_orcids":["https://orcid.org/0000-0002-7171-169X"]},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]},{"id":"https://openalex.org/I2802635041","display_name":"Technische Informationsbibliothek (TIB)","ror":"https://ror.org/04aj4c181","country_code":"DE","type":"archive","lineage":["https://openalex.org/I2802635041","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vahdati, Sahar","raw_affiliation_strings":["Technische Informationsbibliothek (TIB)","Leibniz University Hannover"],"raw_orcid":"https://orcid.org/0000-0002-7171-169X","affiliations":[{"raw_affiliation_string":"Technische Informationsbibliothek (TIB)","institution_ids":["https://openalex.org/I2802635041"]},{"raw_affiliation_string":"Leibniz University Hannover","institution_ids":["https://openalex.org/I114112103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.4018999934196472,"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"}},"topics":[{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.4018999934196472,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.16110000014305115,"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/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","score":0.07639999687671661,"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":[],"concepts":[{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7125999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840999722480774},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.6535000205039978},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.6510000228881836},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5929999947547913},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5579000115394592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5442000031471252},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4165000021457672},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4016000032424927},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3012999892234802},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28870001435279846},{"id":"https://openalex.org/C165825675","wikidata":"https://www.wikidata.org/wiki/Q1399743","display_name":"Model-based testing","level":4,"score":0.27090001106262207},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C2982912361","wikidata":"https://www.wikidata.org/wiki/Q1851867","display_name":"Mental model","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24090559","doi":"https://doi.org/10.5281/zenodo.24090559","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24090559","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.24090560","doi":"https://doi.org/10.5281/zenodo.24090560","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24090560","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.24090559","doi":"https://doi.org/10.5281/zenodo.24090559","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24090559","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":[],"abstract_inverted_index":{"A":[0,179],"language-model":[1],"agent":[2],"can":[3,270],"reach":[4],"a":[5,27,53,89,94,101,139,169,246,276],"goal":[6,269],"in":[7,31,177,198,258],"an":[8,33,182,263,281],"unfamiliar":[9],"environment":[10],"while":[11],"its":[12,213,250],"account":[13],"of":[14,55,128,150,244,283],"the":[15,76,97,107,114,117,136,151,165,185,210,229,242,268,284],"rules":[16,37,214],"remains":[17,295],"inadequate":[18],"for":[19],"later":[20],"levels.":[21,161],"We":[22,65,274],"study":[23],"this":[24,145],"gap":[25],"with":[26,111,144,158,192,201],"quantised":[28],"Qwen3.8-Flash-Next":[29],"model":[30,77,108,186,211,254],"ARC-AGI-3,":[32],"interactive":[34],"benchmark":[35],"whose":[36],"and":[38,60,79,84,96,105,112,218,253,293],"goals":[39],"must":[40,141],"be":[41,142,272,297],"discovered":[42],"through":[43],"play.":[44],"The":[45],"philosopher":[46],"Charles":[47],"Sanders":[48],"Peirce":[49],"described":[50],"inquiry":[51,289],"as":[52,280],"cycle":[54],"proposing":[56],"explanations,":[57],"deriving":[58],"predictions,":[59],"testing":[61],"them":[62],"against":[63],"experience.":[64],"use":[66],"these":[67],"stages":[68],"to":[69,74,154,181,261,278,296],"analyse":[70],"recorded":[71],"plays,":[72,126],"changes":[73],"what":[75],"observes":[78],"which":[80,240],"tools":[81],"it":[82,223],"has,":[83],"preliminary":[85],"fine-tuning.":[86],"To":[87],"test":[88],"proposed":[90],"fix,":[91,115],"we":[92],"restore":[93],"game":[95,152],"model\u2019s":[98],"conversation":[99],"at":[100,195,205],"chosen":[102],"decision":[103],"point":[104],"let":[106],"continue":[109],"repeatedly,":[110],"without":[113,131],"under":[116,228],"same":[118,230],"token":[119],"budget.":[120],"At":[121],"four":[122],"points":[123,197],"from":[124],"failed":[125],"19":[127],"40":[129],"continuations":[130],"any":[132],"fix":[133,140],"still":[134],"completed":[135,160,224],"level,":[137],"so":[138],"compared":[143],"unaided":[146],"recovery.":[147],"Computed":[148],"summaries":[149],"added":[153],"every":[155],"turn":[156],"coincided":[157,191],"fewer":[159,225],"Factual":[162],"notes":[163],"improved":[164],"next":[166],"response,":[167],"but":[168,222],"broader":[170],"correction":[171],"package":[172],"produced":[173],"no":[174,202],"detectable":[175],"gain":[176],"score.":[178],"cue":[180],"intermediate":[183],"board":[184],"had":[187],"not":[188,236],"been":[189],"shown":[190],"higher":[193],"completion":[194],"selected":[196],"one":[199],"game,":[200],"detected":[203],"benefit":[204],"three":[206],"others.":[207],"Fine-tuning":[208],"made":[209],"check":[212,247],"far":[215],"more":[216],"often":[217],"write":[219],"longer":[220],"replies,":[221],"held-out":[226],"levels":[227],"time":[231],"limits.":[232],"More":[233],"checking":[234],"did":[235],"mean":[237],"better":[238],"play,":[239],"raises":[241],"question":[243],"when":[245,267],"is":[248],"worth":[249],"cost.":[251],"Human":[252],"traces":[255],"motivate":[256],"momentum":[257],"inquiry:":[259],"continuing":[260],"investigate":[262],"unresolved":[264],"relation":[265],"even":[266],"already":[271],"reached.":[273],"propose":[275],"drive":[277],"understand":[279],"explanation":[282],"human":[285],"pattern.":[286],"Whether":[287],"such":[288],"improves":[290],"rule":[291],"revision":[292],"transfer":[294],"tested.":[298]},"counts_by_year":[],"updated_date":"2026-11-10T13:44:29.811591","created_date":"2026-11-10T00:00:00"}