{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UMFHH3D6OB5Y52N6STDYCZBWCH","short_pith_number":"pith:UMFHH3D6","schema_version":"1.0","canonical_sha256":"a30a73ec7e707b8ee9be94c781643611cd69868eb7fa8be43526de538cf07d99","source":{"kind":"arxiv","id":"2402.07107","version":3},"attestation_state":"computed","paper":{"title":"Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alex Christopher Stutts, Amit Ranjan Trivedi, Danilo Erricolo, Theja Tulabandhula","submitted_at":"2024-02-11T05:17:56Z","abstract_excerpt":"We present a novel statistical approach to incorporating uncertainty awareness in model-free distributional reinforcement learning involving quantile regression-based deep Q networks. The proposed algorithm, $\\textit{Calibrated Evidential Quantile Regression in Deep Q Networks (CEQR-DQN)}$, aims to address key challenges associated with separately estimating aleatoric and epistemic uncertainty in stochastic environments. It combines deep evidential learning with quantile calibration based on principles of conformal inference to provide explicit, sample-free computations of $\\textit{global}$ un"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.07107","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-11T05:17:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"da953673511b123ccd2063ce4780aa7f9538f27b0d03c6abeda320efbf281858","abstract_canon_sha256":"2ad430371eb9d4cdb454bbd8e53f19f2735a52ac1a4eba62bab12ff07d2f16ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:03.503077Z","signature_b64":"J8OCmg3WSTIr1pTi6Yv37D1SbLUbpr7z9KRs9pdNn5PSrDP5w/Ecw05cUPd83BnDP5D0d/EpSjSIVR4qapz9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a30a73ec7e707b8ee9be94c781643611cd69868eb7fa8be43526de538cf07d99","last_reissued_at":"2026-07-05T08:27:03.502627Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:03.502627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alex Christopher Stutts, Amit Ranjan Trivedi, Danilo Erricolo, Theja Tulabandhula","submitted_at":"2024-02-11T05:17:56Z","abstract_excerpt":"We present a novel statistical approach to incorporating uncertainty awareness in model-free distributional reinforcement learning involving quantile regression-based deep Q networks. The proposed algorithm, $\\textit{Calibrated Evidential Quantile Regression in Deep Q Networks (CEQR-DQN)}$, aims to address key challenges associated with separately estimating aleatoric and epistemic uncertainty in stochastic environments. It combines deep evidential learning with quantile calibration based on principles of conformal inference to provide explicit, sample-free computations of $\\textit{global}$ un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07107","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.07107/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.07107","created_at":"2026-07-05T08:27:03.502684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07107v3","created_at":"2026-07-05T08:27:03.502684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07107","created_at":"2026-07-05T08:27:03.502684+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMFHH3D6OB5Y","created_at":"2026-07-05T08:27:03.502684+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMFHH3D6OB5Y52N6","created_at":"2026-07-05T08:27:03.502684+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMFHH3D6","created_at":"2026-07-05T08:27:03.502684+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UMFHH3D6OB5Y52N6STDYCZBWCH","json":"https://pith.science/pith/UMFHH3D6OB5Y52N6STDYCZBWCH.json","graph_json":"https://pith.science/api/pith-number/UMFHH3D6OB5Y52N6STDYCZBWCH/graph.json","events_json":"https://pith.science/api/pith-number/UMFHH3D6OB5Y52N6STDYCZBWCH/events.json","paper":"https://pith.science/paper/UMFHH3D6"},"agent_actions":{"view_html":"https://pith.science/pith/UMFHH3D6OB5Y52N6STDYCZBWCH","download_json":"https://pith.science/pith/UMFHH3D6OB5Y52N6STDYCZBWCH.json","view_paper":"https://pith.science/paper/UMFHH3D6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07107&json=true","fetch_graph":"https://pith.science/api/pith-number/UMFHH3D6OB5Y52N6STDYCZBWCH/graph.json","fetch_events":"https://pith.science/api/pith-number/UMFHH3D6OB5Y52N6STDYCZBWCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMFHH3D6OB5Y52N6STDYCZBWCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMFHH3D6OB5Y52N6STDYCZBWCH/action/storage_attestation","attest_author":"https://pith.science/pith/UMFHH3D6OB5Y52N6STDYCZBWCH/action/author_attestation","sign_citation":"https://pith.science/pith/UMFHH3D6OB5Y52N6STDYCZBWCH/action/citation_signature","submit_replication":"https://pith.science/pith/UMFHH3D6OB5Y52N6STDYCZBWCH/action/replication_record"}},"created_at":"2026-07-05T08:27:03.502684+00:00","updated_at":"2026-07-05T08:27:03.502684+00:00"}