{"id":"https://openalex.org/W7224108274","doi":"https://doi.org/10.5281/zenodo.23730509","title":"Confidence-Aware Action Selection: Adjusting Decisions According to the Reliability of Predicted Outcomes","display_name":"Confidence-Aware Action Selection: Adjusting Decisions According to the Reliability of Predicted Outcomes","publication_year":2026,"publication_date":"2026-10-28","ids":{"openalex":"https://openalex.org/W7224108274","doi":"https://doi.org/10.5281/zenodo.23730509"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23730509","doi":"https://doi.org/10.5281/zenodo.23730509","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23730509","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","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23730509","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100638045","display_name":"Jincheng Zhang","orcid":"https://orcid.org/0000-0001-7332-6704","observed_orcids":["https://orcid.org/0000-0001-7332-6704","https://orcid.org/0009-0005-1860-0009"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Jincheng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0005-1860-0009","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100638045"],"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7964000105857849,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7964000105857849,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.09139999747276306,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0348999984562397,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/forecast-uncertainty","display_name":"forecast uncertainty","score":0.7369999885559082},{"id":"https://openalex.org/keywords/forecast-calibration","display_name":"forecast calibration","score":0.6330000162124634},{"id":"https://openalex.org/keywords/epistemic-uncertainty","display_name":"epistemic uncertainty","score":0.8159999847412109},{"id":"https://openalex.org/keywords/outcome-variability","display_name":"outcome variability","score":0.5699999928474426},{"id":"https://openalex.org/keywords/risk-sensitive-decision-making","display_name":"risk-sensitive decision making","score":0.7760000228881836},{"id":"https://openalex.org/keywords/value-of-information","display_name":"value of information","score":0.8629999756813049},{"id":"https://openalex.org/keywords/decision-making-under-uncertainty","display_name":"decision making under uncertainty","score":0.7059999704360962},{"id":"https://openalex.org/keywords/autonomous-agents","display_name":"autonomous agents","score":0.43299999833106995},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5699999928474426}],"concepts":[{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.7186999917030334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.654699981212616},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5706999897956848},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.534500002861023},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5203999876976013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48010000586509705},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47760000824928284},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.4666000008583069},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4553999900817871},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.3919999897480011},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.3285999894142151},{"id":"https://openalex.org/C2779351106","wikidata":"https://www.wikidata.org/wiki/Q24965456","display_name":"Decision quality","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C84839998","wikidata":"https://www.wikidata.org/wiki/Q5249245","display_name":"Decision rule","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C103402496","wikidata":"https://www.wikidata.org/wiki/Q1106171","display_name":"Prediction interval","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3127000033855438},{"id":"https://openalex.org/C205706631","wikidata":"https://www.wikidata.org/wiki/Q2319304","display_name":"Expected utility hypothesis","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2784000039100647},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C156201811","wikidata":"https://www.wikidata.org/wiki/Q5418360","display_name":"Evidential reasoning approach","level":4,"score":0.26170000433921814},{"id":"https://openalex.org/C47385372","wikidata":"https://www.wikidata.org/wiki/Q7098943","display_name":"Optimal distinctiveness theory","level":2,"score":0.2603999972343445}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23730509","doi":"https://doi.org/10.5281/zenodo.23730509","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23730509","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.23730510","doi":"https://doi.org/10.5281/zenodo.23730510","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23730510","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.23730509","doi":"https://doi.org/10.5281/zenodo.23730509","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23730509","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":["https://openalex.org/W4407186934","https://openalex.org/W4229486644","https://openalex.org/W7152340149","https://openalex.org/W7214123367","https://openalex.org/W7171390682","https://openalex.org/W7208778593","https://openalex.org/W7214286946","https://openalex.org/W2014315935","https://openalex.org/W4408105791","https://openalex.org/W7133519707"],"abstract_inverted_index":{"Intelligent":[0],"systems":[1],"increasingly":[2],"select":[3],"actions":[4,39,222],"according":[5,76],"to":[6,77,179],"predictions":[7],"of":[8,81,91,109,220,239],"their":[9],"future":[10],"consequences.":[11],"However,":[12],"a":[13,16,25,68,85,89,118],"prediction":[14,27,130,140],"with":[15,103,182,247],"high":[17],"estimated":[18,79],"outcome":[19,125],"value":[20],"may":[21,28],"be":[22,29,180,242],"unreliable,":[23],"while":[24],"lower-valued":[26],"supported":[30],"by":[31,41],"substantially":[32],"stronger":[33],"evidence.":[34],"Decision":[35],"mechanisms":[36],"that":[37,72,200],"rank":[38],"exclusively":[40],"predicted":[42,82],"utility":[43,98],"can":[44,206],"therefore":[45],"behave":[46],"poorly":[47],"when":[48,217],"the":[49,78,96,107,110,144,218],"predictive":[50,100,193,204],"model":[51],"is":[52,177,199],"uncertain,":[53],"miscalibrated,":[54],"or":[55],"operating":[56],"outside":[57],"its":[58],"training":[59,166],"distribution.":[60],"This":[61],"paper":[62],"proposes":[63],"Confidence-Aware":[64],"Action":[65],"Selection":[66],"(CAAS),":[67],"general":[69],"decision-making":[70],"framework":[71,123,176],"adjusts":[73],"action":[74,116],"selection":[75],"reliability":[80,108,205],"outcomes.":[83],"Given":[84],"current":[86],"state":[87],"and":[88,99,113,135,159,170,191,210,237,254],"set":[90],"candidate":[92],"actions,":[93],"CAAS":[94,240],"estimates":[95],"expected":[97],"uncertainty":[101],"associated":[102],"each":[104],"candidate,":[105],"evaluates":[106],"corresponding":[111],"predictions,":[112],"selects":[114],"an":[115,138],"using":[117],"confidence-sensitive":[119],"decision":[120,194,208],"rule.":[121],"The":[122,175,233],"distinguishes":[124],"variability":[126],"from":[127,132,141],"epistemic":[128],"uncertainty,":[129,215],"calibration":[131],"ranking":[133],"accuracy,":[134],"confidence":[136,142],"in":[137,143,230],"individual":[139],"relative":[145],"comparison":[146],"between":[147],"actions.":[148],"It":[149],"introduces":[150],"uncertainty-adjusted":[151],"utility,":[152],"risk-sensitive":[153,250],"selection,":[154],"confidence-dependent":[155],"verification,":[156],"adaptive":[157],"abstention,":[158],"value-of-information-based":[160],"computation":[161],"allocation.":[162],"A":[163],"mathematical":[164],"formulation,":[165],"objectives,":[167],"inference":[168],"algorithm,":[169],"experimental":[171,226],"protocol":[172],"are":[173,223,228],"presented.":[174],"designed":[178],"compatible":[181],"reinforcement":[183],"learning,":[184],"model-based":[185],"planning,":[186],"generative":[187],"systems,":[188],"autonomous":[189],"agents,":[190],"other":[192],"processes.":[195],"Its":[196],"central":[197],"hypothesis":[198],"explicitly":[201],"incorporating":[202],"calibrated":[203],"improve":[207],"quality":[209],"reduce":[211],"harmful":[212],"decisions":[213],"under":[214],"particularly":[216],"consequences":[219],"incorrect":[221],"substantial.":[224],"No":[225],"results":[227],"claimed":[229],"this":[231],"paper.":[232],"effectiveness,":[234],"computational":[235],"advantages,":[236],"distinctiveness":[238],"must":[241],"established":[243],"through":[244],"controlled":[245],"comparisons":[246],"uncertainty-aware":[248],"decision-making,":[249],"optimization,":[251],"selective":[252],"prediction,":[253],"value-of-information":[255],"methods.":[256]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-10-29T00:00:00"}