{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UD24X5XIA5OFCQ2LU4F4HUHAWF","short_pith_number":"pith:UD24X5XI","canonical_record":{"source":{"id":"2206.06426","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-13T19:11:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bbfe992e326784a605414b8c082cdeef3472843e70efc06991cfeca031ebddad","abstract_canon_sha256":"47c2247b2523be6b5846acf0f87c69f6c5d5dec8f326400b10fa29d4e4cf7221"},"schema_version":"1.0"},"canonical_sha256":"a0f5cbf6e8075c51434ba70bc3d0e0b155f89c29696b0eb839b042bf9db5b9cc","source":{"kind":"arxiv","id":"2206.06426","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.06426","created_at":"2026-07-05T06:02:28Z"},{"alias_kind":"arxiv_version","alias_value":"2206.06426v2","created_at":"2026-07-05T06:02:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06426","created_at":"2026-07-05T06:02:28Z"},{"alias_kind":"pith_short_12","alias_value":"UD24X5XIA5OF","created_at":"2026-07-05T06:02:28Z"},{"alias_kind":"pith_short_16","alias_value":"UD24X5XIA5OFCQ2L","created_at":"2026-07-05T06:02:28Z"},{"alias_kind":"pith_short_8","alias_value":"UD24X5XI","created_at":"2026-07-05T06:02:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UD24X5XIA5OFCQ2LU4F4HUHAWF","target":"record","payload":{"canonical_record":{"source":{"id":"2206.06426","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-13T19:11:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bbfe992e326784a605414b8c082cdeef3472843e70efc06991cfeca031ebddad","abstract_canon_sha256":"47c2247b2523be6b5846acf0f87c69f6c5d5dec8f326400b10fa29d4e4cf7221"},"schema_version":"1.0"},"canonical_sha256":"a0f5cbf6e8075c51434ba70bc3d0e0b155f89c29696b0eb839b042bf9db5b9cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:28.456091Z","signature_b64":"YW402v7Q0ECDvXfG1w0sCXescitvD7A7dAKXpOmfqOSo7vov04P/zUaJIJcA+ITraRL0IOZ592KGVBqWS/bRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0f5cbf6e8075c51434ba70bc3d0e0b155f89c29696b0eb839b042bf9db5b9cc","last_reissued_at":"2026-07-05T06:02:28.455583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:28.455583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.06426","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:02:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YsQu2cy06Zwr43i4hFu9p5V52p1DlnnKX/vlIVTURH+d6wNbjQ8p9clSDM/OScFpXAO9vJqqHod8l+ndzf1cCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:25:57.644661Z"},"content_sha256":"8dbeb2428a97e4520ff5a93910f82dcb337203cda389ed39152d2a22bdbd42ef","schema_version":"1.0","event_id":"sha256:8dbeb2428a97e4520ff5a93910f82dcb337203cda389ed39152d2a22bdbd42ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UD24X5XIA5OFCQ2LU4F4HUHAWF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Shaofeng Zou, Tengyu Xu, Yingbin Liang, Yue Wang","submitted_at":"2022-06-13T19:11:22Z","abstract_excerpt":"The remarkable success of reinforcement learning (RL) heavily relies on observing the reward of every visited state-action pair. In many real world applications, however, an agent can observe only a score that represents the quality of the whole trajectory, which is referred to as the {\\em trajectory-wise reward}. In such a situation, it is difficult for standard RL methods to well utilize trajectory-wise reward, and large bias and variance errors can be incurred in policy evaluation. In this work, we propose a novel offline RL algorithm, called Pessimistic vAlue iteRaTion with rEward Decompos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06426","kind":"arxiv","version":2},"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/2206.06426/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":"2026-07-05T06:02:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tEcdHM8h+llqHaKomG/CVq8+XRwTIY1UcN+2E5utpTYq9nESPZ+3MLI5zNzbTEuI0iYKb4C4OTyhJlCoU8ZzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:25:57.645768Z"},"content_sha256":"6aa6767cc2c450ddeb2145b327faf22e186ba2f7d27932bc8773ead6d03f6d66","schema_version":"1.0","event_id":"sha256:6aa6767cc2c450ddeb2145b327faf22e186ba2f7d27932bc8773ead6d03f6d66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UD24X5XIA5OFCQ2LU4F4HUHAWF/bundle.json","state_url":"https://pith.science/pith/UD24X5XIA5OFCQ2LU4F4HUHAWF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UD24X5XIA5OFCQ2LU4F4HUHAWF/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":"2026-08-11T16:25:57Z","links":{"resolver":"https://pith.science/pith/UD24X5XIA5OFCQ2LU4F4HUHAWF","bundle":"https://pith.science/pith/UD24X5XIA5OFCQ2LU4F4HUHAWF/bundle.json","state":"https://pith.science/pith/UD24X5XIA5OFCQ2LU4F4HUHAWF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UD24X5XIA5OFCQ2LU4F4HUHAWF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UD24X5XIA5OFCQ2LU4F4HUHAWF","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":"47c2247b2523be6b5846acf0f87c69f6c5d5dec8f326400b10fa29d4e4cf7221","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-13T19:11:22Z","title_canon_sha256":"bbfe992e326784a605414b8c082cdeef3472843e70efc06991cfeca031ebddad"},"schema_version":"1.0","source":{"id":"2206.06426","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.06426","created_at":"2026-07-05T06:02:28Z"},{"alias_kind":"arxiv_version","alias_value":"2206.06426v2","created_at":"2026-07-05T06:02:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06426","created_at":"2026-07-05T06:02:28Z"},{"alias_kind":"pith_short_12","alias_value":"UD24X5XIA5OF","created_at":"2026-07-05T06:02:28Z"},{"alias_kind":"pith_short_16","alias_value":"UD24X5XIA5OFCQ2L","created_at":"2026-07-05T06:02:28Z"},{"alias_kind":"pith_short_8","alias_value":"UD24X5XI","created_at":"2026-07-05T06:02:28Z"}],"graph_snapshots":[{"event_id":"sha256:6aa6767cc2c450ddeb2145b327faf22e186ba2f7d27932bc8773ead6d03f6d66","target":"graph","created_at":"2026-07-05T06:02:28Z","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/2206.06426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The remarkable success of reinforcement learning (RL) heavily relies on observing the reward of every visited state-action pair. In many real world applications, however, an agent can observe only a score that represents the quality of the whole trajectory, which is referred to as the {\\em trajectory-wise reward}. In such a situation, it is difficult for standard RL methods to well utilize trajectory-wise reward, and large bias and variance errors can be incurred in policy evaluation. In this work, we propose a novel offline RL algorithm, called Pessimistic vAlue iteRaTion with rEward Decompos","authors_text":"Shaofeng Zou, Tengyu Xu, Yingbin Liang, Yue Wang","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-13T19:11:22Z","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06426","kind":"arxiv","version":2},"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":"sha256:8dbeb2428a97e4520ff5a93910f82dcb337203cda389ed39152d2a22bdbd42ef","target":"record","created_at":"2026-07-05T06:02:28Z","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":"47c2247b2523be6b5846acf0f87c69f6c5d5dec8f326400b10fa29d4e4cf7221","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-13T19:11:22Z","title_canon_sha256":"bbfe992e326784a605414b8c082cdeef3472843e70efc06991cfeca031ebddad"},"schema_version":"1.0","source":{"id":"2206.06426","kind":"arxiv","version":2}},"canonical_sha256":"a0f5cbf6e8075c51434ba70bc3d0e0b155f89c29696b0eb839b042bf9db5b9cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0f5cbf6e8075c51434ba70bc3d0e0b155f89c29696b0eb839b042bf9db5b9cc","first_computed_at":"2026-07-05T06:02:28.455583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:02:28.455583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YW402v7Q0ECDvXfG1w0sCXescitvD7A7dAKXpOmfqOSo7vov04P/zUaJIJcA+ITraRL0IOZ592KGVBqWS/bRBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:02:28.456091Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.06426","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dbeb2428a97e4520ff5a93910f82dcb337203cda389ed39152d2a22bdbd42ef","sha256:6aa6767cc2c450ddeb2145b327faf22e186ba2f7d27932bc8773ead6d03f6d66"],"state_sha256":"38d05b8cdcc5b4ac4194a67a0bdc97b88271e76f309efa17d2d44cb41c64753b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UXGlQgkeREniaztzBK6ted9qixYTjv2dilnpk68v2JG4SfK1GPrNVO7VN+HPgAF7k6Y1iryS77KhupnQFuhpBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T16:25:57.651691Z","bundle_sha256":"d96bfea631c47323048538af0f15ec217ecea0a826d87021eeaddd7accb06546"}}