{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EPRW3R3OGRWWGLRKXEBBFB3OSV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"405bfb781851e30fccf1ef3cf49d8207476cc2073decf0802ed0ba49cb7ffa2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-17T08:49:52Z","title_canon_sha256":"7cf6196b35b43965377a8ccae9dd20255e1a3f75af6754088b363f972ed58667"},"schema_version":"1.0","source":{"id":"2605.28855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28855","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28855v1","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28855","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"EPRW3R3OGRWW","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"EPRW3R3OGRWWGLRK","created_at":"2026-05-29T00:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"EPRW3R3O","created_at":"2026-05-29T00:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:a01fc05aedbeda96bc9e7fad7db2f3b751bd52e7d2385616678412a1b574c829","target":"graph","created_at":"2026-05-29T00:04:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.28855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chao Li, Guang Yang, Shangdong Yang, Wenhao Wang, Xingguo Chen, Yuchen Shen, Zhiang He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-17T08:49:52Z","title":"Behavior-Aware Auxiliary Corrections for Off-Policy Temporal-Difference Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28855","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0d88464c0f346b5f40db8d1171957ef2e93fd827228632c479e8dfbc99334df4","target":"record","created_at":"2026-05-29T00:04:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"405bfb781851e30fccf1ef3cf49d8207476cc2073decf0802ed0ba49cb7ffa2f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-17T08:49:52Z","title_canon_sha256":"7cf6196b35b43965377a8ccae9dd20255e1a3f75af6754088b363f972ed58667"},"schema_version":"1.0","source":{"id":"2605.28855","kind":"arxiv","version":1}},"canonical_sha256":"23e36dc76e346d632e2ab90212876e95653709ce07073192e39d6effe44f37f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23e36dc76e346d632e2ab90212876e95653709ce07073192e39d6effe44f37f4","first_computed_at":"2026-05-29T00:04:14.372143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T00:04:14.372143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h4OYTecNlUy4zRvWyOju27kzAvLcArpnvdB6+NP/vLXFB7lkwfARKKMVwRiBriBKDkPcOrAAbagDSNcMWS0SDg==","signature_status":"signed_v1","signed_at":"2026-05-29T00:04:14.372946Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d88464c0f346b5f40db8d1171957ef2e93fd827228632c479e8dfbc99334df4","sha256:a01fc05aedbeda96bc9e7fad7db2f3b751bd52e7d2385616678412a1b574c829"],"state_sha256":"cfad75e400fe509a7e6b6f0f3091a949c3e8119554a935af1ed854173c389930"}