{"id":"https://openalex.org/W7213675651","doi":null,"title":"Chain-of-Thought Entropy as a Reliability Signal: A Preregistered Reproduction","display_name":"Chain-of-Thought Entropy as a Reliability Signal: A Preregistered Reproduction","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213675651"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.19606","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19606","pdf_url":"https://arxiv.org/pdf/2609.19606","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.19606","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029144152","display_name":"Theodore O. Cochran","orcid":"https://orcid.org/0009-0001-5960-6854","observed_orcids":["https://orcid.org/0009-0001-5960-6854"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cochran, Theodore O.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5029144152"],"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/T10028","display_name":"Topic Modeling","score":0.4738999903202057,"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/T10028","display_name":"Topic Modeling","score":0.4738999903202057,"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":0.12189999967813492,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.07180000096559525,"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/large-language-models","display_name":"large language models","score":0.781000018119812},{"id":"https://openalex.org/keywords/reasoning-reliability","display_name":"reasoning reliability","score":0.4359999895095825},{"id":"https://openalex.org/keywords/gsm8k","display_name":"GSM8K","score":0.9459999799728394},{"id":"https://openalex.org/keywords/math-500","display_name":"MATH-500","score":0.9670000076293945},{"id":"https://openalex.org/keywords/open-weight-models","display_name":"open-weight models","score":0.628000020980835},{"id":"https://openalex.org/keywords/reproducibility","display_name":"reproducibility","score":0.5389999747276306}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6207000017166138},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5349000096321106},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3671000003814697},{"id":"https://openalex.org/C2780990831","wikidata":"https://www.wikidata.org/wiki/Q319141","display_name":"Conjecture","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C91716921","wikidata":"https://www.wikidata.org/wiki/Q1289366","display_name":"Scale parameter","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C60507348","wikidata":"https://www.wikidata.org/wiki/Q6795892","display_name":"Maximum entropy probability distribution","level":3,"score":0.31949999928474426},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C66696666","wikidata":"https://www.wikidata.org/wiki/Q17105612","display_name":"Sample entropy","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C89735579","wikidata":"https://www.wikidata.org/wiki/Q6795894","display_name":"Maximum entropy spectral estimation","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C121864883","wikidata":"https://www.wikidata.org/wiki/Q677916","display_name":"Statistical physics","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2524999976158142},{"id":"https://openalex.org/C44415725","wikidata":"https://www.wikidata.org/wiki/Q4913893","display_name":"Binary entropy function","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2609.19606","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19606","pdf_url":"https://arxiv.org/pdf/2609.19606","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.19606","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19606","pdf_url":"https://arxiv.org/pdf/2609.19606","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":null,"license_id":null,"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/W7213675651.pdf","grobid_xml":"https://content.openalex.org/works/W7213675651.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7139963015","https://openalex.org/W7152570149","https://openalex.org/W7131645936","https://openalex.org/W7154826949","https://openalex.org/W4414448322","https://openalex.org/W4399061837","https://openalex.org/W4392181812","https://openalex.org/W7133202361","https://openalex.org/W7140306783","https://openalex.org/W7127414508"],"abstract_inverted_index":{"This":[0],"empirical":[1],"study":[2,242],"is":[3,29,135,156],"an":[4,199,233],"independent":[5],"reproduction":[6,44,87,245],"of":[7,16,34,105,149,171,246,261,273],"the":[8,26,32,46,62,86,89,108,124,127,146,150,165,168,172,187,191,202,207,225,228,236,247,262,265,277],"dissociation":[9,42],"Zhao":[10],"reported":[11,66],"in":[12,180,211,220],"2026.":[13],"The":[14,41,113,117,241],"shape":[15,63,114,173,209,248],"a":[17,51,75,106,181,244,259],"large":[18],"language":[19],"model's":[20],"chain-of-thought":[21],"entropy":[22,37,152,204],"trajectory":[23],"predicts":[24],"whether":[25],"final":[27],"answer":[28],"correct,":[30],"while":[31,61,145,190],"magnitude":[33,47,118,266],"its":[35],"total":[36,151],"drop":[38,153],"does":[39,238,279],"not.":[40],"merits":[43],"because":[45],"half":[48,64],"rests":[49],"on":[50,70,74,139,143,158,162,176,232],"single":[52],"300-problem":[53],"run":[54],"with":[55,97,154],"one":[56,59,102,178],"model":[57,77,104,126,167],"at":[58,67,80,250],"seed,":[60],"was":[65],"full":[68,251],"scale":[69,253],"both":[71],"benchmarks":[72],"and":[73,92,132,141,160,219,269,271],"second":[76],"family.":[78],"Registered":[79],"OSF":[81],"before":[82],"any":[83],"confirmatory":[84],"run,":[85],"crosses":[88],"complete":[90],"GSM8K":[91,140,159],"MATH-500":[93],"benchmark":[94],"test":[95],"sets":[96],"four":[98,274],"open-weight":[99],"models":[100],"including":[101],"reasoning-distilled":[103,166],"kind":[107],"original":[109,229,237,278],"did":[110],"not":[111,239,280],"test.":[112],"signal":[115,119,174,249,267],"replicates.":[116],"divides":[120],"by":[121,216,224],"setting.":[122],"On":[123,164],"anchor":[125],"accuracy":[128],"gap":[129],"between":[130],"monotone":[131],"non-monotone":[133],"chains":[134],"+9.6":[136],"percentage":[137],"points":[138],"+27.5":[142],"MATH-500,":[144],"rank":[147],"correlation":[148],"correctness":[155],"-0.018":[157],"+0.414":[161],"MATH-500.":[163],"binary":[169,208],"form":[170],"fires":[175],"about":[177],"chain":[179],"hundred,":[182],"too":[183],"few":[184],"to":[185],"estimate":[186],"registered":[188],"contrast,":[189],"graded":[192],"violation":[193],"count":[194],"remains":[195],"predictive":[196],"there.":[197],"In":[198],"exploratory":[200],"comparison":[201],"final-step":[203],"alone":[205],"outperforms":[206],"flag":[210],"all":[212],"eight":[213],"model-by-benchmark":[214],"cells":[215],"ROC":[217],"area,":[218],"six":[221],"or":[222],"seven":[223,255],"risk-coverage":[226],"area":[227],"reports,":[230],"depending":[231],"integration":[234],"range":[235],"state.":[240],"contributes":[243],"test-set":[252],"under":[254],"documented":[256],"protocol":[257,275],"differences,":[258],"map":[260],"settings":[263],"where":[264],"holds":[268],"fails,":[270],"measurements":[272],"dependencies":[276],"report.":[281]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-20T00:00:00"}