{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GD35PHF5YTOQJE4F3YJI7DJRFH","short_pith_number":"pith:GD35PHF5","canonical_record":{"source":{"id":"2505.19923","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T12:45:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c6ef3d5a89eab05c8aeb5d24a6cb19ed3858c7b2d9621ba0d2b338f7030e42c1","abstract_canon_sha256":"f54741048c5a43382b810cd14bc15a0a75d42622fb617c289498afb4c894f0ef"},"schema_version":"1.0"},"canonical_sha256":"30f7d79cbdc4dd049385de128f8d3129e232b4c1ab7871591e9ddbd1ba847107","source":{"kind":"arxiv","id":"2505.19923","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19923","created_at":"2026-07-05T11:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19923v1","created_at":"2026-07-05T11:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19923","created_at":"2026-07-05T11:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"GD35PHF5YTOQ","created_at":"2026-07-05T11:09:49Z"},{"alias_kind":"pith_short_16","alias_value":"GD35PHF5YTOQJE4F","created_at":"2026-07-05T11:09:49Z"},{"alias_kind":"pith_short_8","alias_value":"GD35PHF5","created_at":"2026-07-05T11:09:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GD35PHF5YTOQJE4F3YJI7DJRFH","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19923","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T12:45:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c6ef3d5a89eab05c8aeb5d24a6cb19ed3858c7b2d9621ba0d2b338f7030e42c1","abstract_canon_sha256":"f54741048c5a43382b810cd14bc15a0a75d42622fb617c289498afb4c894f0ef"},"schema_version":"1.0"},"canonical_sha256":"30f7d79cbdc4dd049385de128f8d3129e232b4c1ab7871591e9ddbd1ba847107","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:49.948628Z","signature_b64":"J5Ly7bu5qwlJIAyCPgeM8DjvGR84fXBLjzS2aD3hwWnB0Ig7loVmXnLRkKs1EjGL8zLn8y1pvmvlZ3H7EroFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30f7d79cbdc4dd049385de128f8d3129e232b4c1ab7871591e9ddbd1ba847107","last_reissued_at":"2026-07-05T11:09:49.948128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:49.948128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19923","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ciBg+akxF1pyGHEOZIrkbXJkMlQjLOtHyPVxJ+hnKby2jc8RAJCRjocxpKEKVSMXbhwp2chaEsEJMq8ItdKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:45:37.957522Z"},"content_sha256":"0354888ba6a1fc8b240d492a1abe24779943d94fe7ff6fdb152f7fafd9df370b","schema_version":"1.0","event_id":"sha256:0354888ba6a1fc8b240d492a1abe24779943d94fe7ff6fdb152f7fafd9df370b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GD35PHF5YTOQJE4F3YJI7DJRFH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ming-Kun Xie, Qin-Wen Luo, Sheng-Jun Huang, Ye-Wen Wang","submitted_at":"2025-05-26T12:45:54Z","abstract_excerpt":"Offline reinforcement learning (RL) aims to learn an effective policy from a static dataset. To alleviate extrapolation errors, existing studies often uniformly regularize the value function or policy updates across all states. However, due to substantial variations in data quality, the fixed regularization strength often leads to a dilemma: Weak regularization strength fails to address extrapolation errors and value overestimation, while strong regularization strength shifts policy learning toward behavior cloning, impeding potential performance enabled by Bellman updates. To address this iss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19923","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/2505.19923/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hWsNzpZOwdekiLDAld7YxgRdCRqigarEE5JsTDjeOqYZINOdmKVCZa2iaGj0vGwniliTKs68mfaKMVUWG3+kCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:45:37.958066Z"},"content_sha256":"9b8dcd74d5cb81dddb176f3482a9cda47c17ac5b13a3dcd560a2ebd2e9ad4fff","schema_version":"1.0","event_id":"sha256:9b8dcd74d5cb81dddb176f3482a9cda47c17ac5b13a3dcd560a2ebd2e9ad4fff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GD35PHF5YTOQJE4F3YJI7DJRFH/bundle.json","state_url":"https://pith.science/pith/GD35PHF5YTOQJE4F3YJI7DJRFH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GD35PHF5YTOQJE4F3YJI7DJRFH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T04:45:37Z","links":{"resolver":"https://pith.science/pith/GD35PHF5YTOQJE4F3YJI7DJRFH","bundle":"https://pith.science/pith/GD35PHF5YTOQJE4F3YJI7DJRFH/bundle.json","state":"https://pith.science/pith/GD35PHF5YTOQJE4F3YJI7DJRFH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GD35PHF5YTOQJE4F3YJI7DJRFH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GD35PHF5YTOQJE4F3YJI7DJRFH","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":"f54741048c5a43382b810cd14bc15a0a75d42622fb617c289498afb4c894f0ef","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T12:45:54Z","title_canon_sha256":"c6ef3d5a89eab05c8aeb5d24a6cb19ed3858c7b2d9621ba0d2b338f7030e42c1"},"schema_version":"1.0","source":{"id":"2505.19923","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19923","created_at":"2026-07-05T11:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19923v1","created_at":"2026-07-05T11:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19923","created_at":"2026-07-05T11:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"GD35PHF5YTOQ","created_at":"2026-07-05T11:09:49Z"},{"alias_kind":"pith_short_16","alias_value":"GD35PHF5YTOQJE4F","created_at":"2026-07-05T11:09:49Z"},{"alias_kind":"pith_short_8","alias_value":"GD35PHF5","created_at":"2026-07-05T11:09:49Z"}],"graph_snapshots":[{"event_id":"sha256:9b8dcd74d5cb81dddb176f3482a9cda47c17ac5b13a3dcd560a2ebd2e9ad4fff","target":"graph","created_at":"2026-07-05T11:09:49Z","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/2505.19923/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) aims to learn an effective policy from a static dataset. To alleviate extrapolation errors, existing studies often uniformly regularize the value function or policy updates across all states. However, due to substantial variations in data quality, the fixed regularization strength often leads to a dilemma: Weak regularization strength fails to address extrapolation errors and value overestimation, while strong regularization strength shifts policy learning toward behavior cloning, impeding potential performance enabled by Bellman updates. To address this iss","authors_text":"Ming-Kun Xie, Qin-Wen Luo, Sheng-Jun Huang, Ye-Wen Wang","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T12:45:54Z","title":"Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19923","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":"sha256:0354888ba6a1fc8b240d492a1abe24779943d94fe7ff6fdb152f7fafd9df370b","target":"record","created_at":"2026-07-05T11:09:49Z","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":"f54741048c5a43382b810cd14bc15a0a75d42622fb617c289498afb4c894f0ef","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T12:45:54Z","title_canon_sha256":"c6ef3d5a89eab05c8aeb5d24a6cb19ed3858c7b2d9621ba0d2b338f7030e42c1"},"schema_version":"1.0","source":{"id":"2505.19923","kind":"arxiv","version":1}},"canonical_sha256":"30f7d79cbdc4dd049385de128f8d3129e232b4c1ab7871591e9ddbd1ba847107","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30f7d79cbdc4dd049385de128f8d3129e232b4c1ab7871591e9ddbd1ba847107","first_computed_at":"2026-07-05T11:09:49.948128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:49.948128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J5Ly7bu5qwlJIAyCPgeM8DjvGR84fXBLjzS2aD3hwWnB0Ig7loVmXnLRkKs1EjGL8zLn8y1pvmvlZ3H7EroFAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:49.948628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19923","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0354888ba6a1fc8b240d492a1abe24779943d94fe7ff6fdb152f7fafd9df370b","sha256:9b8dcd74d5cb81dddb176f3482a9cda47c17ac5b13a3dcd560a2ebd2e9ad4fff"],"state_sha256":"82b8494e7e697e350c9a92d0ac7e6b96e04a437a843b1458063a40d456364afe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J8EAqYlnIm/iL0zrTsSlLlfEyM2MGVC/GQnrjDYxLUJDw7b4/HcMM4N0LQPcGL1wjO/JzFb7XzQeYGS4fFpuBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:45:37.961824Z","bundle_sha256":"fe781d3f8f112b72d6de6fb9bdf7020ccca0d3123c46ecb002dc1bcf5ec1f8d1"}}