{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AAEYXUL262XVZIZGXPOUN7KP3Q","short_pith_number":"pith:AAEYXUL2","schema_version":"1.0","canonical_sha256":"00098bd17af6af5ca326bbdd46fd4fdc168f42b3ecc81db4d13701d3cb89f2d7","source":{"kind":"arxiv","id":"2102.10527","version":3},"attestation_state":"computed","paper":{"title":"Delayed Rewards Calibration via Reward Empirical Sufficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hu Wang, Liuyue Jiang, Minhui Xue, Xiaowei Wang, Xiaoyue Sun, Yixuan Liu","submitted_at":"2021-02-21T06:42:31Z","abstract_excerpt":"Appropriate credit assignment for delay rewards is a fundamental challenge for reinforcement learning. To tackle this problem, we introduce a delay reward calibration paradigm inspired from a classification perspective. We hypothesize that well-represented state vectors share similarities with each other since they contain the same or equivalent essential information. To this end, we define an empirical sufficient distribution, where the state vectors within the distribution will lead agents to environmental reward signals in the consequent steps. Therefore, a purify-trained classifier is desi"},"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":"2102.10527","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-21T06:42:31Z","cross_cats_sorted":[],"title_canon_sha256":"b66309e121fc627064fec13814c068a33599e33760fdf5b288aa4e6b4714bc0e","abstract_canon_sha256":"c25fe457f0d6084629cfad9c4892999f13d55e4b2d5e141f0db8600fc9f5580f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:44.066052Z","signature_b64":"D+4dy3yoNcuEDIG1u+AjJjQFMlm5xd08w89y/cRwNB8kXAwSB+JM0/Und7ev3EvFZU1NOxYB+WuRLVPRFqseDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00098bd17af6af5ca326bbdd46fd4fdc168f42b3ecc81db4d13701d3cb89f2d7","last_reissued_at":"2026-07-05T03:08:44.065615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:44.065615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Delayed Rewards Calibration via Reward Empirical Sufficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hu Wang, Liuyue Jiang, Minhui Xue, Xiaowei Wang, Xiaoyue Sun, Yixuan Liu","submitted_at":"2021-02-21T06:42:31Z","abstract_excerpt":"Appropriate credit assignment for delay rewards is a fundamental challenge for reinforcement learning. To tackle this problem, we introduce a delay reward calibration paradigm inspired from a classification perspective. We hypothesize that well-represented state vectors share similarities with each other since they contain the same or equivalent essential information. To this end, we define an empirical sufficient distribution, where the state vectors within the distribution will lead agents to environmental reward signals in the consequent steps. Therefore, a purify-trained classifier is desi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10527","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/2102.10527/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":"2102.10527","created_at":"2026-07-05T03:08:44.065670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.10527v3","created_at":"2026-07-05T03:08:44.065670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10527","created_at":"2026-07-05T03:08:44.065670+00:00"},{"alias_kind":"pith_short_12","alias_value":"AAEYXUL262XV","created_at":"2026-07-05T03:08:44.065670+00:00"},{"alias_kind":"pith_short_16","alias_value":"AAEYXUL262XVZIZG","created_at":"2026-07-05T03:08:44.065670+00:00"},{"alias_kind":"pith_short_8","alias_value":"AAEYXUL2","created_at":"2026-07-05T03:08:44.065670+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/AAEYXUL262XVZIZGXPOUN7KP3Q","json":"https://pith.science/pith/AAEYXUL262XVZIZGXPOUN7KP3Q.json","graph_json":"https://pith.science/api/pith-number/AAEYXUL262XVZIZGXPOUN7KP3Q/graph.json","events_json":"https://pith.science/api/pith-number/AAEYXUL262XVZIZGXPOUN7KP3Q/events.json","paper":"https://pith.science/paper/AAEYXUL2"},"agent_actions":{"view_html":"https://pith.science/pith/AAEYXUL262XVZIZGXPOUN7KP3Q","download_json":"https://pith.science/pith/AAEYXUL262XVZIZGXPOUN7KP3Q.json","view_paper":"https://pith.science/paper/AAEYXUL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.10527&json=true","fetch_graph":"https://pith.science/api/pith-number/AAEYXUL262XVZIZGXPOUN7KP3Q/graph.json","fetch_events":"https://pith.science/api/pith-number/AAEYXUL262XVZIZGXPOUN7KP3Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AAEYXUL262XVZIZGXPOUN7KP3Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AAEYXUL262XVZIZGXPOUN7KP3Q/action/storage_attestation","attest_author":"https://pith.science/pith/AAEYXUL262XVZIZGXPOUN7KP3Q/action/author_attestation","sign_citation":"https://pith.science/pith/AAEYXUL262XVZIZGXPOUN7KP3Q/action/citation_signature","submit_replication":"https://pith.science/pith/AAEYXUL262XVZIZGXPOUN7KP3Q/action/replication_record"}},"created_at":"2026-07-05T03:08:44.065670+00:00","updated_at":"2026-07-05T03:08:44.065670+00:00"}