{"id":"https://openalex.org/W7225463473","doi":"https://doi.org/10.5281/zenodo.24043622","title":"Certified Benchmarks as Honest Evaluation Instruments: Measured Failures of Small Models on Unique-Solution Puzzles","display_name":"Certified Benchmarks as Honest Evaluation Instruments: Measured Failures of Small Models on Unique-Solution Puzzles","publication_year":2026,"publication_date":"2026-11-07","ids":{"openalex":"https://openalex.org/W7225463473","doi":"https://doi.org/10.5281/zenodo.24043622"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24043622","doi":"https://doi.org/10.5281/zenodo.24043622","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24043622","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":null,"license_id":null,"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.24043622","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134982800","display_name":"Stephen P. Lutar","orcid":"https://orcid.org/0009-0001-0110-4173","observed_orcids":["https://orcid.org/0009-0001-0110-4173"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lutar, Stephen P.","raw_affiliation_strings":["SZL Holdings"],"raw_orcid":"https://orcid.org/0009-0001-0110-4173","affiliations":[{"raw_affiliation_string":"SZL Holdings","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5134982800"],"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.07599999755620956,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.07599999755620956,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.05260000005364418,"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/T10028","display_name":"Topic Modeling","score":0.050700001418590546,"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/small-language-models","display_name":"small language models","score":0.7049999833106995},{"id":"https://openalex.org/keywords/model-evaluation","display_name":"model evaluation","score":0.5379999876022339},{"id":"https://openalex.org/keywords/confabulation","display_name":"confabulation","score":0.7710000276565552},{"id":"https://openalex.org/keywords/ablation-study","display_name":"ablation study","score":0.5550000071525574},{"id":"https://openalex.org/keywords/continuous-certification","display_name":"continuous certification","score":0.49300000071525574}],"concepts":[{"id":"https://openalex.org/C46304622","wikidata":"https://www.wikidata.org/wiki/Q374814","display_name":"Certification","level":2,"score":0.6654000282287598},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6538000106811523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5146999955177307},{"id":"https://openalex.org/C2779765954","wikidata":"https://www.wikidata.org/wiki/Q5159625","display_name":"Confabulation (neural networks)","level":3,"score":0.39489999413490295},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.37049999833106995},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2806999981403351},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.2678000032901764},{"id":"https://openalex.org/C148417208","wikidata":"https://www.wikidata.org/wiki/Q4825882","display_name":"Authentication (law)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2623000144958496},{"id":"https://openalex.org/C97399411","wikidata":"https://www.wikidata.org/wiki/Q825367","display_name":"Coin flipping","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24043622","doi":"https://doi.org/10.5281/zenodo.24043622","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24043622","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.24043623","doi":"https://doi.org/10.5281/zenodo.24043623","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24043623","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24043622","doi":"https://doi.org/10.5281/zenodo.24043622","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24043622","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":null,"license_id":null,"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/W7223130874","https://openalex.org/W7125955153","https://openalex.org/W7225413020","https://openalex.org/W7201992892","https://openalex.org/W7203914498","https://openalex.org/W7204130475","https://openalex.org/W7143431599","https://openalex.org/W7225454594","https://openalex.org/W7220673324","https://openalex.org/W7128698239"],"abstract_inverted_index":{"The":[0],"Behnamian-collaboration":[1],"preprint:":[2],"certified":[3],"unique-solution":[4],"puzzles":[5],"as":[6],"the":[7,40,50],"evaluation":[8],"instrument":[9],"against":[10],"which":[11],"honest":[12],"failure":[13],"is":[14],"measurable.":[15],"Measured":[16],"confabulation":[17],"across":[18],"a":[19,27,36],"small-model":[20],"fleet":[21],"(0.3%-2.7%":[22],"grounding-gate":[23],"acceptance;":[24],"gate-assisted":[25],"1.3%),":[26],"three-condition":[28],"ablation":[29],"with":[30],"irreducible":[31],"variability":[32],"(4/6,":[33],"3/6,":[34],"5/6),":[35],"contamination":[37],"audit":[38],"of":[39],"estate's":[41],"own":[42],"corpus":[43],"(8/16":[44],"rows,":[45],"fixed":[46],"and":[47,49],"measured),":[48],"continuous-certification":[51],"contribution":[52],"(stratified":[53],"re-proof":[54],"every":[55],"commit,":[56],"full":[57],"242-certificate":[58],"bank":[59],"weekly,":[60],"fail-closed).":[61]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-08T00:00:00"}
