{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LDWZ75T2TUJMWBEB6BO3IDTVUR","short_pith_number":"pith:LDWZ75T2","canonical_record":{"source":{"id":"2608.03108","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T04:30:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c0e62fae92747dee23950a0fa3c9a67ee713c0879bd2a158dd7140d079f269f3","abstract_canon_sha256":"d405aad442ca5734aca131b19a590168c1852c92058748f89898cf7db509de89"},"schema_version":"1.0"},"canonical_sha256":"58ed9ff67a9d12cb0481f05db40e75a44f750da65ad1139c655a41f8d15f1d4b","source":{"kind":"arxiv","id":"2608.03108","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03108","created_at":"2026-08-05T00:45:42Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03108v1","created_at":"2026-08-05T00:45:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03108","created_at":"2026-08-05T00:45:42Z"},{"alias_kind":"pith_short_12","alias_value":"LDWZ75T2TUJM","created_at":"2026-08-05T00:45:42Z"},{"alias_kind":"pith_short_16","alias_value":"LDWZ75T2TUJMWBEB","created_at":"2026-08-05T00:45:42Z"},{"alias_kind":"pith_short_8","alias_value":"LDWZ75T2","created_at":"2026-08-05T00:45:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LDWZ75T2TUJMWBEB6BO3IDTVUR","target":"record","payload":{"canonical_record":{"source":{"id":"2608.03108","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T04:30:02Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"c0e62fae92747dee23950a0fa3c9a67ee713c0879bd2a158dd7140d079f269f3","abstract_canon_sha256":"d405aad442ca5734aca131b19a590168c1852c92058748f89898cf7db509de89"},"schema_version":"1.0"},"canonical_sha256":"58ed9ff67a9d12cb0481f05db40e75a44f750da65ad1139c655a41f8d15f1d4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:45:42.015511Z","signature_b64":"jETxkSo4E5hHI95C1lS6+B9OcUft2k1gIXnqlBS56+T+/lceoA/0VuZhOkhnEJl+AEd0v0d7Z2DV5pa3g7ioDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58ed9ff67a9d12cb0481f05db40e75a44f750da65ad1139c655a41f8d15f1d4b","last_reissued_at":"2026-08-05T00:45:42.012275Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:45:42.012275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.03108","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":"2026-08-05T00:45:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UPivvyqOmlI3MtINRxnP1XKdDY98RaEOT8wj6LZQ/yo5jD7RtvJJoZ2T2pRm/rNNncnc9r2gIjNRpjqExFlvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:47:05.415605Z"},"content_sha256":"02992a707ab81cf76a43728e3166b080fc1e17a4f94b35986afbca8d81481efb","schema_version":"1.0","event_id":"sha256:02992a707ab81cf76a43728e3166b080fc1e17a4f94b35986afbca8d81481efb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LDWZ75T2TUJMWBEB6BO3IDTVUR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convex-Hull-Neighborhood Smooth Dual Generalization: Controlling Local Correction Propagation in Offline RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hanlei Li, Lvqing Yang, Mingfeng Lv, Yi Yang, Zhengsen Ruan, Zhennan Chen","submitted_at":"2026-08-04T04:30:02Z","abstract_excerpt":"Offline reinforcement learning (offline RL) can benefit from nearby out-of-distribution (OOD) actions, but estimation errors at these actions may be amplified by bootstrapping. Existing regularization and local-generalization methods control either the admissible OOD region or the influence of generalized targets, often through separate mechanisms. We propose Convex Hull Neighborhood Smooth Dual Generalization (CSDG), which expresses the Bellman backup as an in-sample value target plus a CHN-local correction. This formulation makes the generalized contribution explicit and separates it from th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03108","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/2608.03108/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":"2026-08-05T00:45:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A2ietLAWXJ93Kf05t+61R6JLTMkhXABqxfCQUmIEDq+L2+lhYLtcsirnMT5Na0AaykPU5r8DG6RrFbM3CEqxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:47:05.416115Z"},"content_sha256":"c42d67dfbf1dd4a43f305683d57fba1f902d3a63f61247381247b1a81777a115","schema_version":"1.0","event_id":"sha256:c42d67dfbf1dd4a43f305683d57fba1f902d3a63f61247381247b1a81777a115"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LDWZ75T2TUJMWBEB6BO3IDTVUR/bundle.json","state_url":"https://pith.science/pith/LDWZ75T2TUJMWBEB6BO3IDTVUR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LDWZ75T2TUJMWBEB6BO3IDTVUR/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":"2026-08-17T18:47:05Z","links":{"resolver":"https://pith.science/pith/LDWZ75T2TUJMWBEB6BO3IDTVUR","bundle":"https://pith.science/pith/LDWZ75T2TUJMWBEB6BO3IDTVUR/bundle.json","state":"https://pith.science/pith/LDWZ75T2TUJMWBEB6BO3IDTVUR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LDWZ75T2TUJMWBEB6BO3IDTVUR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LDWZ75T2TUJMWBEB6BO3IDTVUR","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":"d405aad442ca5734aca131b19a590168c1852c92058748f89898cf7db509de89","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T04:30:02Z","title_canon_sha256":"c0e62fae92747dee23950a0fa3c9a67ee713c0879bd2a158dd7140d079f269f3"},"schema_version":"1.0","source":{"id":"2608.03108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03108","created_at":"2026-08-05T00:45:42Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03108v1","created_at":"2026-08-05T00:45:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03108","created_at":"2026-08-05T00:45:42Z"},{"alias_kind":"pith_short_12","alias_value":"LDWZ75T2TUJM","created_at":"2026-08-05T00:45:42Z"},{"alias_kind":"pith_short_16","alias_value":"LDWZ75T2TUJMWBEB","created_at":"2026-08-05T00:45:42Z"},{"alias_kind":"pith_short_8","alias_value":"LDWZ75T2","created_at":"2026-08-05T00:45:42Z"}],"graph_snapshots":[{"event_id":"sha256:c42d67dfbf1dd4a43f305683d57fba1f902d3a63f61247381247b1a81777a115","target":"graph","created_at":"2026-08-05T00:45:42Z","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/2608.03108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (offline RL) can benefit from nearby out-of-distribution (OOD) actions, but estimation errors at these actions may be amplified by bootstrapping. Existing regularization and local-generalization methods control either the admissible OOD region or the influence of generalized targets, often through separate mechanisms. We propose Convex Hull Neighborhood Smooth Dual Generalization (CSDG), which expresses the Bellman backup as an in-sample value target plus a CHN-local correction. This formulation makes the generalized contribution explicit and separates it from th","authors_text":"Hanlei Li, Lvqing Yang, Mingfeng Lv, Yi Yang, Zhengsen Ruan, Zhennan Chen","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T04:30:02Z","title":"Convex-Hull-Neighborhood Smooth Dual Generalization: Controlling Local Correction Propagation in Offline RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03108","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":"sha256:02992a707ab81cf76a43728e3166b080fc1e17a4f94b35986afbca8d81481efb","target":"record","created_at":"2026-08-05T00:45:42Z","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":"d405aad442ca5734aca131b19a590168c1852c92058748f89898cf7db509de89","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T04:30:02Z","title_canon_sha256":"c0e62fae92747dee23950a0fa3c9a67ee713c0879bd2a158dd7140d079f269f3"},"schema_version":"1.0","source":{"id":"2608.03108","kind":"arxiv","version":1}},"canonical_sha256":"58ed9ff67a9d12cb0481f05db40e75a44f750da65ad1139c655a41f8d15f1d4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58ed9ff67a9d12cb0481f05db40e75a44f750da65ad1139c655a41f8d15f1d4b","first_computed_at":"2026-08-05T00:45:42.012275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T00:45:42.012275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jETxkSo4E5hHI95C1lS6+B9OcUft2k1gIXnqlBS56+T+/lceoA/0VuZhOkhnEJl+AEd0v0d7Z2DV5pa3g7ioDw==","signature_status":"signed_v1","signed_at":"2026-08-05T00:45:42.015511Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02992a707ab81cf76a43728e3166b080fc1e17a4f94b35986afbca8d81481efb","sha256:c42d67dfbf1dd4a43f305683d57fba1f902d3a63f61247381247b1a81777a115"],"state_sha256":"1ca47fc3e82f6bf8894b32fb71faffe49cab5a9203981d149b44f8fee9d3b417"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gZnLM3/7JHfXYTZb3zLWI0wZLubZZ2/a/F2tUVKCwS7zVqjTyMWIjKTnPtmJoPdrecbDJ49kheOi60/8q04JBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:47:05.421334Z","bundle_sha256":"5477ce69f22b4306564b11e96be526dcf88a4cb33b21086de23e53e89af7c507"}}