{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TFSUPNYSL7O36NM3Q2YVIXDKV6","short_pith_number":"pith:TFSUPNYS","canonical_record":{"source":{"id":"2202.06239","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-13T07:38:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bfe4e9543898a6befed70931b5a72f4efd5e77bd6ccc68489122448dfee1d762","abstract_canon_sha256":"1474e82c935a1d0f9edf953c6d22cd63dc85953041674de8fd93093f63151854"},"schema_version":"1.0"},"canonical_sha256":"996547b7125fddbf359b86b1545c6aaf879c1f68a56b7d4b92b6bcd0c079e10e","source":{"kind":"arxiv","id":"2202.06239","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.06239","created_at":"2026-07-05T05:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2202.06239v3","created_at":"2026-07-05T05:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06239","created_at":"2026-07-05T05:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"TFSUPNYSL7O3","created_at":"2026-07-05T05:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"TFSUPNYSL7O36NM3","created_at":"2026-07-05T05:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"TFSUPNYS","created_at":"2026-07-05T05:05:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TFSUPNYSL7O36NM3Q2YVIXDKV6","target":"record","payload":{"canonical_record":{"source":{"id":"2202.06239","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-13T07:38:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bfe4e9543898a6befed70931b5a72f4efd5e77bd6ccc68489122448dfee1d762","abstract_canon_sha256":"1474e82c935a1d0f9edf953c6d22cd63dc85953041674de8fd93093f63151854"},"schema_version":"1.0"},"canonical_sha256":"996547b7125fddbf359b86b1545c6aaf879c1f68a56b7d4b92b6bcd0c079e10e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:45.506679Z","signature_b64":"+Gbyojfy56VgpiYOo/72AAuKXsg92wx69zsGqGmmFCTTUcrnHbkSQpgJdLf381ctE6Flno5Z4zZ7NBV3ppZKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"996547b7125fddbf359b86b1545c6aaf879c1f68a56b7d4b92b6bcd0c079e10e","last_reissued_at":"2026-07-05T05:05:45.506154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:45.506154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.06239","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:05:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WIWPLpDfyEnI8A3usB3gc6E4AJrXIkmQqK3YXiW9kknnLCZ9SZ30csIAbVW7V6O9ZLTSwlexCo4S5CDp+TbTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:20:28.237535Z"},"content_sha256":"ec11065949920974259ee72df8fad29b6dafeb83960d3d5f9f63eb241c3cf9e3","schema_version":"1.0","event_id":"sha256:ec11065949920974259ee72df8fad29b6dafeb83960d3d5f9f63eb241c3cf9e3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TFSUPNYSL7O36NM3Q2YVIXDKV6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Supported Policy Optimization for Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haixu Wu, Jialong Wu, Jianmin Wang, Mingsheng Long, Zihan Qiu","submitted_at":"2022-02-13T07:38:36Z","abstract_excerpt":"Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy. The elaborative designs of parameterization methods usually intrude into the policy networks, which may bring extra inference cost and cannot take full advantage of well-established online methods. Regularization methods reduce the divergence between the learned policy and the behavior policy, which may mismatch the inherent density-based definition of support set thereby failing to avo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06239","kind":"arxiv","version":3},"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/2202.06239/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":"2026-07-05T05:05:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nsI1DUoKBXSfngibie61Wnz4yM9OK3guRsMcrSQdGk8NBcSt8IkBlTekE1D/KkHYi6YX/fCW9Xnu9wVxsNd9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:20:28.238412Z"},"content_sha256":"c7dcc96a74196f9a333ffcecc439c0c7cbf07809e4c06c922a7ed22b5631f563","schema_version":"1.0","event_id":"sha256:c7dcc96a74196f9a333ffcecc439c0c7cbf07809e4c06c922a7ed22b5631f563"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TFSUPNYSL7O36NM3Q2YVIXDKV6/bundle.json","state_url":"https://pith.science/pith/TFSUPNYSL7O36NM3Q2YVIXDKV6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TFSUPNYSL7O36NM3Q2YVIXDKV6/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":"2026-08-04T12:20:28Z","links":{"resolver":"https://pith.science/pith/TFSUPNYSL7O36NM3Q2YVIXDKV6","bundle":"https://pith.science/pith/TFSUPNYSL7O36NM3Q2YVIXDKV6/bundle.json","state":"https://pith.science/pith/TFSUPNYSL7O36NM3Q2YVIXDKV6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TFSUPNYSL7O36NM3Q2YVIXDKV6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TFSUPNYSL7O36NM3Q2YVIXDKV6","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":"1474e82c935a1d0f9edf953c6d22cd63dc85953041674de8fd93093f63151854","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-13T07:38:36Z","title_canon_sha256":"bfe4e9543898a6befed70931b5a72f4efd5e77bd6ccc68489122448dfee1d762"},"schema_version":"1.0","source":{"id":"2202.06239","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.06239","created_at":"2026-07-05T05:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2202.06239v3","created_at":"2026-07-05T05:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06239","created_at":"2026-07-05T05:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"TFSUPNYSL7O3","created_at":"2026-07-05T05:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"TFSUPNYSL7O36NM3","created_at":"2026-07-05T05:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"TFSUPNYS","created_at":"2026-07-05T05:05:45Z"}],"graph_snapshots":[{"event_id":"sha256:c7dcc96a74196f9a333ffcecc439c0c7cbf07809e4c06c922a7ed22b5631f563","target":"graph","created_at":"2026-07-05T05:05:45Z","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/2202.06239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy. The elaborative designs of parameterization methods usually intrude into the policy networks, which may bring extra inference cost and cannot take full advantage of well-established online methods. Regularization methods reduce the divergence between the learned policy and the behavior policy, which may mismatch the inherent density-based definition of support set thereby failing to avo","authors_text":"Haixu Wu, Jialong Wu, Jianmin Wang, Mingsheng Long, Zihan Qiu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-13T07:38:36Z","title":"Supported Policy Optimization for Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06239","kind":"arxiv","version":3},"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:ec11065949920974259ee72df8fad29b6dafeb83960d3d5f9f63eb241c3cf9e3","target":"record","created_at":"2026-07-05T05:05:45Z","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":"1474e82c935a1d0f9edf953c6d22cd63dc85953041674de8fd93093f63151854","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-13T07:38:36Z","title_canon_sha256":"bfe4e9543898a6befed70931b5a72f4efd5e77bd6ccc68489122448dfee1d762"},"schema_version":"1.0","source":{"id":"2202.06239","kind":"arxiv","version":3}},"canonical_sha256":"996547b7125fddbf359b86b1545c6aaf879c1f68a56b7d4b92b6bcd0c079e10e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"996547b7125fddbf359b86b1545c6aaf879c1f68a56b7d4b92b6bcd0c079e10e","first_computed_at":"2026-07-05T05:05:45.506154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:45.506154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Gbyojfy56VgpiYOo/72AAuKXsg92wx69zsGqGmmFCTTUcrnHbkSQpgJdLf381ctE6Flno5Z4zZ7NBV3ppZKAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:45.506679Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.06239","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec11065949920974259ee72df8fad29b6dafeb83960d3d5f9f63eb241c3cf9e3","sha256:c7dcc96a74196f9a333ffcecc439c0c7cbf07809e4c06c922a7ed22b5631f563"],"state_sha256":"e4fdd249a0ea38b67a71ecfff003d47511325181b412b5dbdedcdd6376f70b51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w0tckNf51dTD0mSJfocMAlOoV1z8BsQAiXAOcz5Q8cMtr4MY8Lq53FaUFQJaCIPZo/GdjXS6dILU3enCn0YVBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:20:28.242105Z","bundle_sha256":"53230035dd1b311a555b2c9f881ac6e2b99b85c6dea9159720444724499d775f"}}