{"id":"https://openalex.org/W7128632854","doi":"https://doi.org/10.48550/arxiv.2602.09127","title":"Epistemic Throughput: Fundamental Limits of Attention-Constrained Inference","display_name":"Epistemic Throughput: Fundamental Limits of Attention-Constrained Inference","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128632854","doi":"https://doi.org/10.48550/arxiv.2602.09127"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.09127","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100401826","display_name":"Lei You","orcid":"https://orcid.org/0000-0002-2697-5776"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"You, Lei","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100401826"],"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/T12072","display_name":"Machine Learning and Algorithms","score":0.1981000006198883,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.1981000006198883,"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":0.15199999511241913,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.12330000102519989,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.695900022983551},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6345000267028809},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.557200014591217},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.545199990272522},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.5085999965667725},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.46619999408721924},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.428600013256073},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.3686999976634979}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.695900022983551},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6345000267028809},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.557200014591217},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.545199990272522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5317999720573425},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.5085999965667725},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3652999997138977},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3589000105857849},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3361000120639801},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.335099995136261},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31470000743865967},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C95167961","wikidata":"https://www.wikidata.org/wiki/Q4483495","display_name":"Fiducial inference","level":5,"score":0.2596000134944916},{"id":"https://openalex.org/C2988430800","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Scaling law","level":3,"score":0.2513999938964844},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.25049999356269836},{"id":"https://openalex.org/C94361409","wikidata":"https://www.wikidata.org/wiki/Q7882500","display_name":"Uncertainty reduction theory","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.09127","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.09127","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.09127","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":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.09127","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8244243264198303}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"generative":[1],"and":[2,61,115,117,158],"tool-using":[3],"AI":[4],"systems":[5],"can":[6,22,66,135],"surface":[7],"a":[8,19,28,54,98,107,155],"large":[9],"volume":[10],"of":[11,73],"candidates":[12],"at":[13,70],"low":[14],"marginal":[15],"cost,":[16],"yet":[17],"only":[18,179],"small":[20],"fraction":[21],"be":[23],"checked":[24],"carefully.":[25],"This":[26],"creates":[27],"decoder-side":[29],"bottleneck:":[30],"downstream":[31],"decision-makers":[32],"must":[33],"form":[34],"reliable":[35],"posteriors":[36],"from":[37],"many":[38],"public":[39],"records":[40,60,143],"under":[41],"scarce":[42,138],"attention.":[43],"We":[44,146],"formalize":[45],"this":[46,150],"regime":[47,163],"via":[48],"Attention-Constrained":[49],"Inference":[50],"(ACI),":[51],"in":[52,84,154,160],"which":[53,89],"cheap":[55,133],"screening":[56,129,134],"stage":[57,65],"processes":[58],"$K$":[59],"an":[62,118],"expensive":[63],"verification":[64,114],"follow":[67],"up":[68],"on":[69],"most":[71],"$B$":[72],"them.":[74],"Under":[75],"Bayes":[76],"log-loss,":[77],"we":[78,90],"study":[79],"the":[80,161,176],"maximum":[81],"achievable":[82],"reduction":[83],"posterior":[85],"uncertainty":[86],"per":[87],"window,":[88],"call":[91],"\\emph{epistemic":[92],"throughput}.":[93],"Our":[94],"main":[95],"result":[96],"is":[97,152,178],"``JaKoB''":[99],"scaling":[100,151],"law":[101],"showing":[102],"that":[103,110,122,149,159],"epistemic":[104],"throughput":[105],"has":[106],"baseline":[108],"term":[109,121],"grows":[111],"linearly":[112],"with":[113],"prevalence,":[116],"additional":[119],"\\emph{information-leverage}":[120],"scales":[123],"as":[124],"$\\sqrt{JKB}$,":[125],"where":[126],"$J$":[127],"summarizes":[128],"quality.":[130],"Thus,":[131],"expanding":[132],"nonlinearly":[136],"amplify":[137],"verification,":[139],"even":[140],"when":[141],"informative":[142],"are":[144],"rare.":[145],"further":[147],"show":[148],"tight":[153],"weak-screening":[156],"limit,":[157],"sparse-verification":[162],"($B":[164],"\\ll":[165],"K$),":[166],"substantial":[167],"leverage":[168],"requires":[169],"heavy-tailed":[170],"score":[171],"distributions;":[172],"for":[173],"light-tailed":[174],"scores":[175],"amplification":[177],"logarithmic.":[180]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-12T00:00:00"}