{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KDUKCPMEZGNF5JAWTM5IQ6BMUV","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":"6fa0c0e4b0b5e2e43dfa2fb9415be25c0d7ec6ffdffc7fb83cbe1f1a14732dac","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-06-16T23:32:26Z","title_canon_sha256":"367e2cf290ab6737a79541f58f65a0135d03f82da5036028e0422d6b262feba9"},"schema_version":"1.0","source":{"id":"2506.14058","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.14058","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"2506.14058v1","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14058","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"KDUKCPMEZGNF","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"pith_short_16","alias_value":"KDUKCPMEZGNF5JAW","created_at":"2026-07-05T11:22:48Z"},{"alias_kind":"pith_short_8","alias_value":"KDUKCPME","created_at":"2026-07-05T11:22:48Z"}],"graph_snapshots":[{"event_id":"sha256:3e8dd01bfb9064c7b7cfbe3109ab0c92c56afe4717e65b07f456697af3040b85","target":"graph","created_at":"2026-07-05T11:22:48Z","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/2506.14058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning promises policy improvement from logged interaction data alone, yet state-of-the-art algorithms remain vulnerable to value over-estimation and to violations of domain knowledge such as monotonicity or smoothness. We introduce implicit constraint-aware off-policy correction, a framework that embeds structural priors directly inside every Bellman update. The key idea is to compose the optimal Bellman operator with a proximal projection on a convex constraint set, which produces a new operator that (i) remains a $\\gamma$-contraction, (ii) possesses a unique fixed po","authors_text":"Ali Baheri","cross_cats":["cs.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-06-16T23:32:26Z","title":"Implicit Constraint-Aware Off-Policy Correction for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14058","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":"sha256:82197ab7b93b1690d7bb50fadeaa968eb793519307a931273140142465f304b4","target":"record","created_at":"2026-07-05T11:22:48Z","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":"6fa0c0e4b0b5e2e43dfa2fb9415be25c0d7ec6ffdffc7fb83cbe1f1a14732dac","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2025-06-16T23:32:26Z","title_canon_sha256":"367e2cf290ab6737a79541f58f65a0135d03f82da5036028e0422d6b262feba9"},"schema_version":"1.0","source":{"id":"2506.14058","kind":"arxiv","version":1}},"canonical_sha256":"50e8a13d84c99a5ea4169b3a88782ca5776e4f4c3955e84f1e40f6ad456d72e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50e8a13d84c99a5ea4169b3a88782ca5776e4f4c3955e84f1e40f6ad456d72e2","first_computed_at":"2026-07-05T11:22:48.272496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:48.272496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NUlE9VWjol7s7MkeYeLjDvmRFPbkw1uu/LZXAnvpYpiOkp9bmCpIKF2f9yVeufgRZic/PhdfuCPCHoJwHnysCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:48.273107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.14058","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82197ab7b93b1690d7bb50fadeaa968eb793519307a931273140142465f304b4","sha256:3e8dd01bfb9064c7b7cfbe3109ab0c92c56afe4717e65b07f456697af3040b85"],"state_sha256":"1fd65e91bcdb3382150f20eead5c357f88cc05aa0f8337d4231008ffe348b9c5"}