{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3W7OS5CBNYZQIEXVYDM2XADOXF","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":"48e281b45390cf9e2137120ac0477b41d9a54c8e7d583129e20fbb2562b7b2de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-05T19:48:46Z","title_canon_sha256":"dd3d9dcc035538b0b3095ad4b70d089724d1ad024cac9a35889a31fa43b4eab5"},"schema_version":"1.0","source":{"id":"2511.03828","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.03828","created_at":"2026-05-20T00:04:16Z"},{"alias_kind":"arxiv_version","alias_value":"2511.03828v3","created_at":"2026-05-20T00:04:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.03828","created_at":"2026-05-20T00:04:16Z"},{"alias_kind":"pith_short_12","alias_value":"3W7OS5CBNYZQ","created_at":"2026-05-20T00:04:16Z"},{"alias_kind":"pith_short_16","alias_value":"3W7OS5CBNYZQIEXV","created_at":"2026-05-20T00:04:16Z"},{"alias_kind":"pith_short_8","alias_value":"3W7OS5CB","created_at":"2026-05-20T00:04:16Z"}],"graph_snapshots":[{"event_id":"sha256:513dbb9b531421d5223cc9925af59587fb658747957a06cde0d5d2d64fc3bef0","target":"graph","created_at":"2026-05-20T00:04:16Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We provide a theoretical analysis showing that behavior-based sample exchange consistently improves the distinction between offline-like and online-like subsets. DARE is the first to condition constraint release on behavioral consistency via a posterior-induced exchange mechanism, moving beyond a binary offline/online data distinction."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that a learned behavior model can reliably produce a posterior that accurately measures per-sample behavioral consistency for the exchange mechanism, and that this consistency metric remains meaningful as the policy evolves during fine-tuning (abstract, paragraph on DARE framework)."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"DARE provides a distribution-aware sample-level constraint release mechanism for offline-to-online RL based on behavioral consistency with a behavior model, supported by theoretical analysis and D4RL experiments showing improved stability and performance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"DARE releases constraints at the sample level in offline-to-online reinforcement learning by measuring behavioral consistency instead of data origin."}],"snapshot_sha256":"bd1a0d42a69636c9e08005d7b586a5f6672e8301c9ef1e7cb74897e30c641afb"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ab8ee580afabd57cad2ca9161f612484cdaa8e5636be86c7a2e60fafcecdbb50"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2511.03828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline-to-online reinforcement learning (O2O RL) faces a central challenge between retaining offline conservatism and adapting to online feedback under distribution shift. This challenge arises because data behavior evolves during fine-tuning, rendering data origin a misleading basis for constraint handling and thereby leading to objective-data mismatch. We therefore propose Dynamic Alignment for RElaxation (DARE), a distribution-aware framework for sample-level constraint relaxation based on the behavioral consistency with a behavior model. To our knowledge, DARE is the first to condition co","authors_text":"Lipeng Zu, Shayok Chakraborty, Xiaonan Zhang, Yu Qian","cross_cats":[],"headline":"DARE releases constraints at the sample level in offline-to-online reinforcement learning by measuring behavioral consistency instead of data origin.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-05T19:48:46Z","title":"From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.03828","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-18T00:33:05.695345Z","id":"e07e4a47-0996-4507-88b4-cb081da7b491","model_set":{"reader":"grok-4.3"},"one_line_summary":"DARE provides a distribution-aware sample-level constraint release mechanism for offline-to-online RL based on behavioral consistency with a behavior model, supported by theoretical analysis and D4RL experiments showing improved stability and performance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"DARE releases constraints at the sample level in offline-to-online reinforcement learning by measuring behavioral consistency instead of data origin.","strongest_claim":"We provide a theoretical analysis showing that behavior-based sample exchange consistently improves the distinction between offline-like and online-like subsets. DARE is the first to condition constraint release on behavioral consistency via a posterior-induced exchange mechanism, moving beyond a binary offline/online data distinction.","weakest_assumption":"The assumption that a learned behavior model can reliably produce a posterior that accurately measures per-sample behavioral consistency for the exchange mechanism, and that this consistency metric remains meaningful as the policy evolves during fine-tuning (abstract, paragraph on DARE framework)."}},"verdict_id":"e07e4a47-0996-4507-88b4-cb081da7b491"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:486ae56c394a28d12d42c66232a8210a168a697e4bbac1d9ad087b90bcb423a8","target":"record","created_at":"2026-05-20T00:04:16Z","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":"48e281b45390cf9e2137120ac0477b41d9a54c8e7d583129e20fbb2562b7b2de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-05T19:48:46Z","title_canon_sha256":"dd3d9dcc035538b0b3095ad4b70d089724d1ad024cac9a35889a31fa43b4eab5"},"schema_version":"1.0","source":{"id":"2511.03828","kind":"arxiv","version":3}},"canonical_sha256":"ddbee974416e330412f5c0d9ab806eb9417a0dc3b6ddad55bbb0bd2b32113879","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddbee974416e330412f5c0d9ab806eb9417a0dc3b6ddad55bbb0bd2b32113879","first_computed_at":"2026-05-20T00:04:16.798543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:16.798543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kibYWNNxMTaVZ2nYOQ7GZsN5yXhg3Ad5uUZwUd7ZAEAmEvw4G1XJtQ+9ow/LZp6lB6l+IN+EtXacYBTPm5OuDw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:16.799604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.03828","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:486ae56c394a28d12d42c66232a8210a168a697e4bbac1d9ad087b90bcb423a8","sha256:513dbb9b531421d5223cc9925af59587fb658747957a06cde0d5d2d64fc3bef0"],"state_sha256":"69c79f7d485859bc9689e8c1ecd4f0d4d8a5c3ab7bfcb54a9890002b663caba5"}