{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EPRW3R3OGRWWGLRKXEBBFB3OSV","short_pith_number":"pith:EPRW3R3O","schema_version":"1.0","canonical_sha256":"23e36dc76e346d632e2ab90212876e95653709ce07073192e39d6effe44f37f4","source":{"kind":"arxiv","id":"2605.28855","version":1},"attestation_state":"computed","paper":{"title":"Behavior-Aware Auxiliary Corrections for Off-Policy Temporal-Difference Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Li, Guang Yang, Shangdong Yang, Wenhao Wang, Xingguo Chen, Yuchen Shen, Zhiang He","submitted_at":"2026-05-17T08:49:52Z","abstract_excerpt":"Temporal-difference learning with function approximation can be unstable under off-policy sampling. TDC stabilizes off-policy TD through an auxiliary covariance correction, and TDRC further regularizes this correction in a single-timescale recursion. This paper studies a behavior-aware replacement of the auxiliary covariance geometry in the linear prediction setting, which is the standard local model for understanding the feature-space dynamics of value-function approximation. We first replace the TDC auxiliary matrix (C) by the behavior Bellman matrix (A_\\mu), yielding BA-TDC, and then regula"},"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":"2605.28855","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-17T08:49:52Z","cross_cats_sorted":[],"title_canon_sha256":"7cf6196b35b43965377a8ccae9dd20255e1a3f75af6754088b363f972ed58667","abstract_canon_sha256":"405bfb781851e30fccf1ef3cf49d8207476cc2073decf0802ed0ba49cb7ffa2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T00:04:14.372946Z","signature_b64":"h4OYTecNlUy4zRvWyOju27kzAvLcArpnvdB6+NP/vLXFB7lkwfARKKMVwRiBriBKDkPcOrAAbagDSNcMWS0SDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23e36dc76e346d632e2ab90212876e95653709ce07073192e39d6effe44f37f4","last_reissued_at":"2026-05-29T00:04:14.372143Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T00:04:14.372143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Behavior-Aware Auxiliary Corrections for Off-Policy Temporal-Difference Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chao Li, Guang Yang, Shangdong Yang, Wenhao Wang, Xingguo Chen, Yuchen Shen, Zhiang He","submitted_at":"2026-05-17T08:49:52Z","abstract_excerpt":"Temporal-difference learning with function approximation can be unstable under off-policy sampling. TDC stabilizes off-policy TD through an auxiliary covariance correction, and TDRC further regularizes this correction in a single-timescale recursion. This paper studies a behavior-aware replacement of the auxiliary covariance geometry in the linear prediction setting, which is the standard local model for understanding the feature-space dynamics of value-function approximation. We first replace the TDC auxiliary matrix (C) by the behavior Bellman matrix (A_\\mu), yielding BA-TDC, and then regula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28855","kind":"arxiv","version":1},"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/2605.28855/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":"2605.28855","created_at":"2026-05-29T00:04:14.372258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28855v1","created_at":"2026-05-29T00:04:14.372258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28855","created_at":"2026-05-29T00:04:14.372258+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPRW3R3OGRWW","created_at":"2026-05-29T00:04:14.372258+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPRW3R3OGRWWGLRK","created_at":"2026-05-29T00:04:14.372258+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPRW3R3O","created_at":"2026-05-29T00:04:14.372258+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/EPRW3R3OGRWWGLRKXEBBFB3OSV","json":"https://pith.science/pith/EPRW3R3OGRWWGLRKXEBBFB3OSV.json","graph_json":"https://pith.science/api/pith-number/EPRW3R3OGRWWGLRKXEBBFB3OSV/graph.json","events_json":"https://pith.science/api/pith-number/EPRW3R3OGRWWGLRKXEBBFB3OSV/events.json","paper":"https://pith.science/paper/EPRW3R3O"},"agent_actions":{"view_html":"https://pith.science/pith/EPRW3R3OGRWWGLRKXEBBFB3OSV","download_json":"https://pith.science/pith/EPRW3R3OGRWWGLRKXEBBFB3OSV.json","view_paper":"https://pith.science/paper/EPRW3R3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28855&json=true","fetch_graph":"https://pith.science/api/pith-number/EPRW3R3OGRWWGLRKXEBBFB3OSV/graph.json","fetch_events":"https://pith.science/api/pith-number/EPRW3R3OGRWWGLRKXEBBFB3OSV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPRW3R3OGRWWGLRKXEBBFB3OSV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPRW3R3OGRWWGLRKXEBBFB3OSV/action/storage_attestation","attest_author":"https://pith.science/pith/EPRW3R3OGRWWGLRKXEBBFB3OSV/action/author_attestation","sign_citation":"https://pith.science/pith/EPRW3R3OGRWWGLRKXEBBFB3OSV/action/citation_signature","submit_replication":"https://pith.science/pith/EPRW3R3OGRWWGLRKXEBBFB3OSV/action/replication_record"}},"created_at":"2026-05-29T00:04:14.372258+00:00","updated_at":"2026-05-29T00:04:14.372258+00:00"}