{"id":"https://openalex.org/W7214925719","doi":"https://doi.org/10.48550/arxiv.2609.37470","title":"Probability Contracts: Accuracy, Coherence, and Decisions Across LLM Interfaces","display_name":"Probability Contracts: Accuracy, Coherence, and Decisions Across LLM Interfaces","publication_year":2026,"publication_date":"2026-09-27","ids":{"openalex":"https://openalex.org/W7214925719","doi":"https://doi.org/10.48550/arxiv.2609.37470"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37470","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37470","pdf_url":"https://arxiv.org/pdf/2609.37470","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.37470","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153583060","display_name":"Han Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5153655688","display_name":"Yingrui Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yingrui","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":4,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.1914999932050705,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.1914999932050705,"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":0.16439999639987946,"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":0.09619999676942825,"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":0.8669999837875366},{"id":"https://openalex.org/keywords/interface-coherence","display_name":"interface coherence","score":0.6700000166893005},{"id":"https://openalex.org/keywords/decision-evaluation","display_name":"decision evaluation","score":0.5270000100135803},{"id":"https://openalex.org/keywords/event-alignment","display_name":"event alignment","score":0.578000009059906},{"id":"https://openalex.org/keywords/brier-score","display_name":"Brier score","score":0.6000000238418579},{"id":"https://openalex.org/keywords/scoring-rules","display_name":"scoring rules","score":0.7350000143051147},{"id":"https://openalex.org/keywords/deferral","display_name":"deferral","score":0.5519999861717224},{"id":"https://openalex.org/keywords/decision-costs","display_name":"decision costs","score":0.3959999978542328}],"concepts":[{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7199000120162964},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.6793000102043152},{"id":"https://openalex.org/C35405484","wikidata":"https://www.wikidata.org/wiki/Q4967066","display_name":"Brier score","level":2,"score":0.6664999723434448},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6532999873161316},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6151999831199646},{"id":"https://openalex.org/C3309909","wikidata":"https://www.wikidata.org/wiki/Q864155","display_name":"Binary decision diagram","level":2,"score":0.5311999917030334},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4796999990940094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44449999928474426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.43939998745918274},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4196000099182129},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C186116695","wikidata":"https://www.wikidata.org/wiki/Q5249226","display_name":"Decision analysis","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C150325174","wikidata":"https://www.wikidata.org/wiki/Q4335500","display_name":"Optimal decision","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C2780841128","wikidata":"https://www.wikidata.org/wiki/Q5073781","display_name":"Characterization (materials science)","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C84839998","wikidata":"https://www.wikidata.org/wiki/Q5249245","display_name":"Decision rule","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C97933134","wikidata":"https://www.wikidata.org/wiki/Q5374249","display_name":"Empirical probability","level":4,"score":0.26660001277923584},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26660001277923584},{"id":"https://openalex.org/C97399411","wikidata":"https://www.wikidata.org/wiki/Q825367","display_name":"Coin flipping","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25360000133514404},{"id":"https://openalex.org/C205706631","wikidata":"https://www.wikidata.org/wiki/Q2319304","display_name":"Expected utility hypothesis","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37470","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37470","pdf_url":"https://arxiv.org/pdf/2609.37470","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"},{"id":"doi:10.48550/arxiv.2609.37470","doi":"https://doi.org/10.48550/arxiv.2609.37470","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37470","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:2609.37470","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37470","pdf_url":"https://arxiv.org/pdf/2609.37470","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214925719.pdf","grobid_xml":"https://content.openalex.org/works/W7214925719.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W7128361140","https://openalex.org/W7162674038","https://openalex.org/W7165159037","https://openalex.org/W7170149988","https://openalex.org/W7172534091","https://openalex.org/W7196931901","https://openalex.org/W7208794441","https://openalex.org/W7214049921","https://openalex.org/W7214052905","https://openalex.org/W7214057440","https://openalex.org/W7214118858","https://openalex.org/W7214189993","https://openalex.org/W7214235453","https://openalex.org/W7214313011","https://openalex.org/W7214329963"],"related_works":["https://openalex.org/W7220667046","https://openalex.org/W7214718640","https://openalex.org/W7214776449","https://openalex.org/W4391420976","https://openalex.org/W7128361140","https://openalex.org/W7204531613","https://openalex.org/W7221813087","https://openalex.org/W7223068368","https://openalex.org/W7171949655","https://openalex.org/W7208138553"],"abstract_inverted_index":{"Equivalent":[0],"probability":[1,16,182,186],"requests":[2],"can":[3],"lead":[4],"to":[5,114],"different":[6],"decisions":[7],"even":[8],"when":[9],"both":[10,130,142],"reports":[11],"are":[12],"valid.":[13],"We":[14],"introduce":[15],"contracts,":[17],"a":[18,104,120,133,157],"benchmark":[19],"that":[20,82],"connects":[21],"exact":[22],"finite-world":[23],"posteriors,":[24],"validated":[25],"event":[26,197],"alignment,":[27],"interface":[28,116],"coherence,":[29],"and":[30,53,63,92,103,169,202],"failure-aware":[31],"decision":[32,203],"evaluation.":[33],"Across":[34],"four":[35],"model-interface":[36],"configurations":[37],"on":[38,70,132],"1,000":[39],"worlds,":[40],"Kev":[41],"has":[42],"lower":[43],"aggregate":[44],"canonical":[45],"posterior":[46,199],"error":[47,91],"than":[48],"Jev":[49],"but":[50,118],"larger":[51],"complement":[52],"coarsening":[54],"residuals;":[55],"accuracy":[56,187],"ordering":[57],"varies":[58],"by":[59,195],"stratum.":[60],"Jev's":[61],"Event":[62],"Choice":[64],"interfaces":[65],"change":[66],"the":[67],"binary":[68,89],"action":[69],"32.8%":[71],"of":[72,87],"valid":[73,181],"pairs":[74],"at":[75,123],"defer":[76],"cost":[77,204],"0.10.":[78],"Post-hoc":[79],"analyses":[80],"show":[81],"disagreement":[83],"certifies":[84],"only":[85],"11-52%":[86],"mean":[88],"pair":[90],"does":[93],"not":[94,119],"consistently":[95],"outperform":[96],"confidence":[97],"for":[98,136],"selection.":[99],"An":[100],"action-region":[101],"characterization":[102],"standard":[105],"scoring-rule":[106],"identity":[107],"explain":[108],"averaging's":[109],"expected":[110],"Brier":[111],"guarantee":[112,122],"relative":[113],"random":[115],"selection,":[117],"decision-loss":[121],"each":[124],"cost.":[125],"The":[126],"loss":[127],"contrast":[128],"takes":[129],"signs":[131],"99-cost":[134],"grid":[135],"every":[137],"configuration;":[138],"small":[139],"penalties":[140],"where":[141,161],"policies":[143],"beat":[144],"deferral":[145],"have":[146],"pointwise":[147],"intervals":[148],"containing":[149],"zero.":[150],"Secondary":[151],"checks":[152],"specified":[153],"before":[154],"collection":[155],"include":[156],"separate":[158],"400-root":[159],"cohort,":[160],"Event/Choice":[162],"effects":[163],"remain":[164],"configuration-dependent.":[165],"A":[166],"joint":[167],"surface-order":[168],"answer-ID":[170],"intervention":[171],"shifts":[172],"posttrained":[173],"probabilities.":[174],"Both":[175],"bounded":[176],"reasoning":[177],"arms":[178],"yield":[179],"no":[180],"reports,":[183],"leaving":[184],"their":[185],"undefined.":[188],"Probability":[189],"contracts":[190],"make":[191],"these":[192],"distinctions":[193],"measurable":[194],"evaluating":[196],"semantics,":[198],"error,":[200],"coverage,":[201],"together.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-01T00:00:00"}