{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:R26Q7EGUKKIOBHCHV4CUK5KVVA","short_pith_number":"pith:R26Q7EGU","canonical_record":{"source":{"id":"2506.08417","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T03:43:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77de8aa3de3d103eb769ea18e7acec87fb803d2ae926a5667d8b88e29dd5d5ab","abstract_canon_sha256":"2c38395125338ac162147859a374ea0e08b1ef9ed700bd557ef923afcb66eec7"},"schema_version":"1.0"},"canonical_sha256":"8ebd0f90d45290e09c47af05457555a82cac051069e7c89650b81e3af7e451a4","source":{"kind":"arxiv","id":"2506.08417","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08417","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08417v1","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08417","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"pith_short_12","alias_value":"R26Q7EGUKKIO","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"pith_short_16","alias_value":"R26Q7EGUKKIOBHCH","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"pith_short_8","alias_value":"R26Q7EGU","created_at":"2026-07-05T11:18:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:R26Q7EGUKKIOBHCHV4CUK5KVVA","target":"record","payload":{"canonical_record":{"source":{"id":"2506.08417","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T03:43:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77de8aa3de3d103eb769ea18e7acec87fb803d2ae926a5667d8b88e29dd5d5ab","abstract_canon_sha256":"2c38395125338ac162147859a374ea0e08b1ef9ed700bd557ef923afcb66eec7"},"schema_version":"1.0"},"canonical_sha256":"8ebd0f90d45290e09c47af05457555a82cac051069e7c89650b81e3af7e451a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:49.223491Z","signature_b64":"7X0oArZWD1TEFcQ0Jv9vEAeqKxffke8iSVT/V0r+DIFvQpLhQPJkdkoqse2LG3/DEb6CRjvtujRBdw9qJy0jDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ebd0f90d45290e09c47af05457555a82cac051069e7c89650b81e3af7e451a4","last_reissued_at":"2026-07-05T11:18:49.222888Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:49.222888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.08417","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":"2026-07-05T11:18:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eG+11jOCz8wsb+Jg/ZfPdIeC6wM80GVe1S+SEjNbVHGZLCz8ciyIOq4n9HgQIhESoyZTP/+goDmjCIVV7P+cCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:43:49.927348Z"},"content_sha256":"352ef12c1c7a57dc3bbe4874c64a543e8c139fa15bba0db1d9515923afb2cf01","schema_version":"1.0","event_id":"sha256:352ef12c1c7a57dc3bbe4874c64a543e8c139fa15bba0db1d9515923afb2cf01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:R26Q7EGUKKIOBHCHV4CUK5KVVA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Faguo Wu, Jianxiang Liu, Qingmao Yao, Tianyuan Chen, Xiao Zhang, Xuefan Chen, Zhichao Lei, Ziyue Yuan","submitted_at":"2025-06-10T03:43:22Z","abstract_excerpt":"Offline Reinforcement Learning (RL) struggles with distributional shifts, leading to the $Q$-value overestimation for out-of-distribution (OOD) actions. Existing methods address this issue by imposing constraints; however, they often become overly conservative when evaluating OOD regions, which constrains the $Q$-function generalization. This over-constraint issue results in poor $Q$-value estimation and hinders policy improvement. In this paper, we introduce a novel approach to achieve better $Q$-value estimation by enhancing $Q$-function generalization in OOD regions within Convex Hull and i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08417","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/2506.08417/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":"2026-07-05T11:18:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tH7p+PiexK10L7cFR2xnUmKwGdPUOj0ZJ0YRd74TVt2YrPuxQNPc+7IUC1Dvjf0ouU6yMTbJGR/bz4MVJ0IrAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:43:49.928266Z"},"content_sha256":"b2448358a0a2b9f9d1d451b513c8a45e8af3e32a9b39795f9aadaf666d85fad2","schema_version":"1.0","event_id":"sha256:b2448358a0a2b9f9d1d451b513c8a45e8af3e32a9b39795f9aadaf666d85fad2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R26Q7EGUKKIOBHCHV4CUK5KVVA/bundle.json","state_url":"https://pith.science/pith/R26Q7EGUKKIOBHCHV4CUK5KVVA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R26Q7EGUKKIOBHCHV4CUK5KVVA/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":"2026-08-18T01:43:49Z","links":{"resolver":"https://pith.science/pith/R26Q7EGUKKIOBHCHV4CUK5KVVA","bundle":"https://pith.science/pith/R26Q7EGUKKIOBHCHV4CUK5KVVA/bundle.json","state":"https://pith.science/pith/R26Q7EGUKKIOBHCHV4CUK5KVVA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R26Q7EGUKKIOBHCHV4CUK5KVVA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R26Q7EGUKKIOBHCHV4CUK5KVVA","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":"2c38395125338ac162147859a374ea0e08b1ef9ed700bd557ef923afcb66eec7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T03:43:22Z","title_canon_sha256":"77de8aa3de3d103eb769ea18e7acec87fb803d2ae926a5667d8b88e29dd5d5ab"},"schema_version":"1.0","source":{"id":"2506.08417","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08417","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08417v1","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08417","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"pith_short_12","alias_value":"R26Q7EGUKKIO","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"pith_short_16","alias_value":"R26Q7EGUKKIOBHCH","created_at":"2026-07-05T11:18:49Z"},{"alias_kind":"pith_short_8","alias_value":"R26Q7EGU","created_at":"2026-07-05T11:18:49Z"}],"graph_snapshots":[{"event_id":"sha256:b2448358a0a2b9f9d1d451b513c8a45e8af3e32a9b39795f9aadaf666d85fad2","target":"graph","created_at":"2026-07-05T11:18:49Z","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/2506.08417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline Reinforcement Learning (RL) struggles with distributional shifts, leading to the $Q$-value overestimation for out-of-distribution (OOD) actions. Existing methods address this issue by imposing constraints; however, they often become overly conservative when evaluating OOD regions, which constrains the $Q$-function generalization. This over-constraint issue results in poor $Q$-value estimation and hinders policy improvement. In this paper, we introduce a novel approach to achieve better $Q$-value estimation by enhancing $Q$-function generalization in OOD regions within Convex Hull and i","authors_text":"Faguo Wu, Jianxiang Liu, Qingmao Yao, Tianyuan Chen, Xiao Zhang, Xuefan Chen, Zhichao Lei, Ziyue Yuan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T03:43:22Z","title":"Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08417","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":"sha256:352ef12c1c7a57dc3bbe4874c64a543e8c139fa15bba0db1d9515923afb2cf01","target":"record","created_at":"2026-07-05T11:18:49Z","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":"2c38395125338ac162147859a374ea0e08b1ef9ed700bd557ef923afcb66eec7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T03:43:22Z","title_canon_sha256":"77de8aa3de3d103eb769ea18e7acec87fb803d2ae926a5667d8b88e29dd5d5ab"},"schema_version":"1.0","source":{"id":"2506.08417","kind":"arxiv","version":1}},"canonical_sha256":"8ebd0f90d45290e09c47af05457555a82cac051069e7c89650b81e3af7e451a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ebd0f90d45290e09c47af05457555a82cac051069e7c89650b81e3af7e451a4","first_computed_at":"2026-07-05T11:18:49.222888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:49.222888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7X0oArZWD1TEFcQ0Jv9vEAeqKxffke8iSVT/V0r+DIFvQpLhQPJkdkoqse2LG3/DEb6CRjvtujRBdw9qJy0jDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:49.223491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08417","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:352ef12c1c7a57dc3bbe4874c64a543e8c139fa15bba0db1d9515923afb2cf01","sha256:b2448358a0a2b9f9d1d451b513c8a45e8af3e32a9b39795f9aadaf666d85fad2"],"state_sha256":"764d4e22331c8026c49cbade8fd316018b8e46a30e3af811c1944c74379358e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DVfzaMfDkkBAyhWfgaV6nUoUvETF7QPjlaipuepo9ZsO1j6c8dd04a8FlU2WyLuXk3OAlCeZBtlffm6nTG4EAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T01:43:49.934486Z","bundle_sha256":"877758dc90e712dc8d0d8fef1abb91561dd05640bf996236bde6cb52e8071766"}}