{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:77CUO2CQBRXGBJ5KHDMY2B65VK","short_pith_number":"pith:77CUO2CQ","canonical_record":{"source":{"id":"2503.05207","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-07T07:55:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dd43ca5fee50134a30b01ea75b90906a6ebb4ef94332b843756eff783e513566","abstract_canon_sha256":"d041af4aea96f72803ec08f96deae71b1130efa26f668e7b696a4b165ed81b93"},"schema_version":"1.0"},"canonical_sha256":"ffc54768500c6e60a7aa38d98d07ddaa996c9bd3b01aa45883d1bef2f25591db","source":{"kind":"arxiv","id":"2503.05207","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05207","created_at":"2026-07-05T10:26:23Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05207v1","created_at":"2026-07-05T10:26:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05207","created_at":"2026-07-05T10:26:23Z"},{"alias_kind":"pith_short_12","alias_value":"77CUO2CQBRXG","created_at":"2026-07-05T10:26:23Z"},{"alias_kind":"pith_short_16","alias_value":"77CUO2CQBRXGBJ5K","created_at":"2026-07-05T10:26:23Z"},{"alias_kind":"pith_short_8","alias_value":"77CUO2CQ","created_at":"2026-07-05T10:26:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:77CUO2CQBRXGBJ5KHDMY2B65VK","target":"record","payload":{"canonical_record":{"source":{"id":"2503.05207","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-07T07:55:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dd43ca5fee50134a30b01ea75b90906a6ebb4ef94332b843756eff783e513566","abstract_canon_sha256":"d041af4aea96f72803ec08f96deae71b1130efa26f668e7b696a4b165ed81b93"},"schema_version":"1.0"},"canonical_sha256":"ffc54768500c6e60a7aa38d98d07ddaa996c9bd3b01aa45883d1bef2f25591db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:23.780460Z","signature_b64":"5E1iJIyo/Kb9snWDXbC00aVrm/4NI89RKU8yRAwzHclGw9gj/ao9D2RVo8jnhTu2YK178uomE1ew7sn1ghuDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffc54768500c6e60a7aa38d98d07ddaa996c9bd3b01aa45883d1bef2f25591db","last_reissued_at":"2026-07-05T10:26:23.779934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:23.779934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.05207","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":"2026-07-05T10:26:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V7Fkq3R7BXEFtNKVQHsrXTgc/wk5P5KL5XBOitugnN4Tga6o1F2CJfnhMZOEpgl9kaKbyazrkx9byYL0rLA/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:02:50.610322Z"},"content_sha256":"c714863a5d7f17980207237bf870b4d7b347e051489d81c3a58c51e858514f4e","schema_version":"1.0","event_id":"sha256:c714863a5d7f17980207237bf870b4d7b347e051489d81c3a58c51e858514f4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:77CUO2CQBRXGBJ5KHDMY2B65VK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Constraint by Only Support Constraint for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fan Wu, Jiaming Guo, Rui Zhang, Yunkai Gao","submitted_at":"2025-03-07T07:55:51Z","abstract_excerpt":"Offline reinforcement learning (RL) aims to optimize a policy by using pre-collected datasets, to maximize cumulative rewards. However, offline reinforcement learning suffers challenges due to the distributional shift between the learned and behavior policies, leading to errors when computing Q-values for out-of-distribution (OOD) actions. To mitigate this issue, policy constraint methods aim to constrain the learned policy's distribution with the distribution of the behavior policy or confine action selection within the support of the behavior policy. However, current policy constraint method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05207","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/2503.05207/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":"2026-07-05T10:26:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ITymp/wXp12iLuAg3CHB4iAP4Da6uxE7bkGNZFFwXCJ3GnlR3OydbLFvChHy0U0xdHUFFCBXn06+4YeVtjaMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:02:50.610820Z"},"content_sha256":"09a9618f44767788f9c08745a67fe84a3e7e0d47b72d995e37c07ec6e106177f","schema_version":"1.0","event_id":"sha256:09a9618f44767788f9c08745a67fe84a3e7e0d47b72d995e37c07ec6e106177f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77CUO2CQBRXGBJ5KHDMY2B65VK/bundle.json","state_url":"https://pith.science/pith/77CUO2CQBRXGBJ5KHDMY2B65VK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77CUO2CQBRXGBJ5KHDMY2B65VK/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":"2026-08-05T22:02:50Z","links":{"resolver":"https://pith.science/pith/77CUO2CQBRXGBJ5KHDMY2B65VK","bundle":"https://pith.science/pith/77CUO2CQBRXGBJ5KHDMY2B65VK/bundle.json","state":"https://pith.science/pith/77CUO2CQBRXGBJ5KHDMY2B65VK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77CUO2CQBRXGBJ5KHDMY2B65VK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:77CUO2CQBRXGBJ5KHDMY2B65VK","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":"d041af4aea96f72803ec08f96deae71b1130efa26f668e7b696a4b165ed81b93","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-07T07:55:51Z","title_canon_sha256":"dd43ca5fee50134a30b01ea75b90906a6ebb4ef94332b843756eff783e513566"},"schema_version":"1.0","source":{"id":"2503.05207","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.05207","created_at":"2026-07-05T10:26:23Z"},{"alias_kind":"arxiv_version","alias_value":"2503.05207v1","created_at":"2026-07-05T10:26:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05207","created_at":"2026-07-05T10:26:23Z"},{"alias_kind":"pith_short_12","alias_value":"77CUO2CQBRXG","created_at":"2026-07-05T10:26:23Z"},{"alias_kind":"pith_short_16","alias_value":"77CUO2CQBRXGBJ5K","created_at":"2026-07-05T10:26:23Z"},{"alias_kind":"pith_short_8","alias_value":"77CUO2CQ","created_at":"2026-07-05T10:26:23Z"}],"graph_snapshots":[{"event_id":"sha256:09a9618f44767788f9c08745a67fe84a3e7e0d47b72d995e37c07ec6e106177f","target":"graph","created_at":"2026-07-05T10:26:23Z","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/2503.05207/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) aims to optimize a policy by using pre-collected datasets, to maximize cumulative rewards. However, offline reinforcement learning suffers challenges due to the distributional shift between the learned and behavior policies, leading to errors when computing Q-values for out-of-distribution (OOD) actions. To mitigate this issue, policy constraint methods aim to constrain the learned policy's distribution with the distribution of the behavior policy or confine action selection within the support of the behavior policy. However, current policy constraint method","authors_text":"Fan Wu, Jiaming Guo, Rui Zhang, Yunkai Gao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-07T07:55:51Z","title":"Policy Constraint by Only Support Constraint for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05207","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:c714863a5d7f17980207237bf870b4d7b347e051489d81c3a58c51e858514f4e","target":"record","created_at":"2026-07-05T10:26:23Z","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":"d041af4aea96f72803ec08f96deae71b1130efa26f668e7b696a4b165ed81b93","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-07T07:55:51Z","title_canon_sha256":"dd43ca5fee50134a30b01ea75b90906a6ebb4ef94332b843756eff783e513566"},"schema_version":"1.0","source":{"id":"2503.05207","kind":"arxiv","version":1}},"canonical_sha256":"ffc54768500c6e60a7aa38d98d07ddaa996c9bd3b01aa45883d1bef2f25591db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffc54768500c6e60a7aa38d98d07ddaa996c9bd3b01aa45883d1bef2f25591db","first_computed_at":"2026-07-05T10:26:23.779934Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:23.779934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5E1iJIyo/Kb9snWDXbC00aVrm/4NI89RKU8yRAwzHclGw9gj/ao9D2RVo8jnhTu2YK178uomE1ew7sn1ghuDBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:23.780460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.05207","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c714863a5d7f17980207237bf870b4d7b347e051489d81c3a58c51e858514f4e","sha256:09a9618f44767788f9c08745a67fe84a3e7e0d47b72d995e37c07ec6e106177f"],"state_sha256":"d608ebe3174fa005153af45bf78d06bc04d421afc9e8e155f57221a43f3c58d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FXuujieup6y1drqKuE4JAmo42MHKWUrhv87m10cErkh1Yu+2EyhanPDnGOnPtRWiujg4r15hGpWDepONnUwxAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:02:50.614633Z","bundle_sha256":"9cbd3af1ac0f449d1b19e5171f979b719c41e95ac29e6a32d1e48d4902662fe2"}}