{"id":"https://openalex.org/W7162459962","doi":"https://doi.org/10.48550/arxiv.2605.24756","title":"Proper Scoring Rules for Agentic Uncertainty Quantification","display_name":"Proper Scoring Rules for Agentic Uncertainty Quantification","publication_year":2026,"publication_date":"2026-05-23","ids":{"openalex":"https://openalex.org/W7162459962","doi":"https://doi.org/10.48550/arxiv.2605.24756"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.24756","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24756","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.24756","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137067296","display_name":"Suresh Raghu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raghu, Suresh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101336497","display_name":"Satwik Pandey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pandey, Satwik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051142062","display_name":"Shashwat Pandey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pandey, Shashwat","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":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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.16769999265670776,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.16769999265670776,"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":0.12219999730587006,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10679999738931656,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/trajectory","display_name":"Trajectory","score":0.8173999786376953},{"id":"https://openalex.org/keywords/scoring-rule","display_name":"Scoring rule","score":0.6682000160217285},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6489999890327454},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5490999817848206},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.4878999888896942},{"id":"https://openalex.org/keywords/conflation","display_name":"Conflation","score":0.4097999930381775},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.36719998717308044},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3668000102043152}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.8173999786376953},{"id":"https://openalex.org/C63002673","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring rule","level":2,"score":0.6682000160217285},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6489999890327454},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5490999817848206},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.508899986743927},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4284000098705292},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40130001306533813},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33959999680519104},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.30320000648498535},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.28360000252723694},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.25929999351501465},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.24756","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24756","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.24756","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24756","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.538443386554718}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Language-model":[0],"agents":[1],"increasingly":[2],"emit":[3],"uncertainty":[4,76],"signals":[5],"throughout":[6],"a":[7,64,80,130],"trajectory,":[8],"but":[9,37],"existing":[10],"agentic":[11],"UQ":[12],"evaluations":[13],"often":[14],"conflate":[15],"ranking":[16],"usefulness":[17],"with":[18],"probabilistic":[19],"truthfulness.":[20],"AUROC,":[21],"AUPRC,":[22],"risk-coverage,":[23],"Trajectory":[24,60,153,159],"ECE,":[25],"and":[26,102,129,175,197],"scalarized":[27,158],"trajectory":[28,142],"scores":[29],"evaluate":[30],"discrimination,":[31],"binwise":[32],"calibration,":[33],"or":[34],"collapsed":[35,164],"summaries,":[36],"do":[38],"not":[39,166],"strictly":[40,68,89],"elicit":[41],"the":[42,59,91,98,107,115,119,148,163,167,198,204],"full":[43,149,168],"prefix-conditioned":[44,150],"success-probability":[45,92],"trace":[46],"$q_t":[47],"=":[48],"P^\u03c0(Y=1":[49],"|":[50],"H_t)$.":[51],"Building":[52],"on":[53,171],"prequential":[54],"proper":[55,69],"scoring,":[56],"we":[57],"introduce":[58],"Proper":[61],"Score":[62],"(TPS),":[63],"predictor-agnostic":[65],"family":[66,101],"of":[67,82],"trajectory-level":[70],"scoring":[71],"rules":[72],"for":[73],"any":[74],"per-step":[75],"signal":[77],"calibrated":[78],"into":[79],"probability":[81,151,185],"eventual":[83],"success.":[84],"We":[85,105,137],"prove":[86],"that":[87,140,178],"TPS":[88,190],"elicits":[90,161],"process":[93],"under":[94],"complete":[95],"observation,":[96],"within":[97],"chosen":[99],"score":[100,117,128],"weight":[103],"schedule.":[104],"extend":[106],"construction":[108],"to":[109,207],"administratively":[110],"censored":[111,200],"trajectories":[112],"by":[113],"projecting":[114],"complete-data":[116],"onto":[118],"observable":[120],"stopped":[121],"prefix,":[122],"yielding":[123],"an":[124],"exact":[125],"$q_Z$-weighted":[126],"reduced":[127],"tractable":[131,199],"approximation":[132,201],"when":[133],"$q_Z$":[134],"is":[135,155],"unestimated.":[136],"further":[138],"show":[139,177],"common":[141],"evaluators":[143],"target":[144],"weaker":[145],"objects":[146],"than":[147],"process:":[152],"ECE":[154],"resolution-blind,":[156],"while":[157,191],"Brier":[160],"only":[162],"scalar,":[165],"trace.":[169],"Experiments":[170],"StrategyQA,":[172],"Tau2-Bench,":[173],"HotpotQA,":[174],"WebShop":[176],"these":[179],"theoretical":[180],"distinctions":[181],"are":[182],"operationally":[183],"visible:":[184],"recalibration":[186],"can":[187,202],"substantially":[188],"change":[189,203],"leaving":[192],"rank":[193],"metrics":[194],"nearly":[195],"unchanged,":[196],"verdict":[205],"relative":[206],"complete-only":[208],"evaluation.":[209]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-27T00:00:00"}