{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TNJKNAHQXG37B7X5S7STNVDBEQ","short_pith_number":"pith:TNJKNAHQ","canonical_record":{"source":{"id":"2407.04451","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-05T12:05:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"03197d4a277593b3da9aa851bfa21d678a52cc7d9c8bf34f2cc32a7b257a04a5","abstract_canon_sha256":"7e63c4fe31cf127041c201b039151fad14941e0e0fdb851d757d968539e2ae79"},"schema_version":"1.0"},"canonical_sha256":"9b52a680f0b9b7f0fefd97e536d461241c84e9c9e33d8994924a6b628d5748ae","source":{"kind":"arxiv","id":"2407.04451","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04451","created_at":"2026-07-05T08:40:33Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04451v1","created_at":"2026-07-05T08:40:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04451","created_at":"2026-07-05T08:40:33Z"},{"alias_kind":"pith_short_12","alias_value":"TNJKNAHQXG37","created_at":"2026-07-05T08:40:33Z"},{"alias_kind":"pith_short_16","alias_value":"TNJKNAHQXG37B7X5","created_at":"2026-07-05T08:40:33Z"},{"alias_kind":"pith_short_8","alias_value":"TNJKNAHQ","created_at":"2026-07-05T08:40:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TNJKNAHQXG37B7X5S7STNVDBEQ","target":"record","payload":{"canonical_record":{"source":{"id":"2407.04451","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-05T12:05:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"03197d4a277593b3da9aa851bfa21d678a52cc7d9c8bf34f2cc32a7b257a04a5","abstract_canon_sha256":"7e63c4fe31cf127041c201b039151fad14941e0e0fdb851d757d968539e2ae79"},"schema_version":"1.0"},"canonical_sha256":"9b52a680f0b9b7f0fefd97e536d461241c84e9c9e33d8994924a6b628d5748ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:33.847666Z","signature_b64":"X6Nv6LGG+tJWodDp5nIcjgsBZxaBWT2KOu7FtcFg3cH45t+FRRcKDj5HzaOae63qmg/S7+6I0wNX4ge5SQg5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b52a680f0b9b7f0fefd97e536d461241c84e9c9e33d8994924a6b628d5748ae","last_reissued_at":"2026-07-05T08:40:33.847163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:33.847163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.04451","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":"2026-07-05T08:40:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PtwyNXPzt0DaavrZK3/v7tD8WMY4YkTbYrJhGBpukDvnnOpou9uCa87Pjj9cOZtVvWetLS8+nFt1PGOJyC7DCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:56:13.870165Z"},"content_sha256":"d2df2f7bcc6ca821a0ff55c669cb3c921fea7487a9adf06401afd40894a19275","schema_version":"1.0","event_id":"sha256:d2df2f7bcc6ca821a0ff55c669cb3c921fea7487a9adf06401afd40894a19275"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TNJKNAHQXG37B7X5S7STNVDBEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenjun Xiao, Chen-Xiao Gao, Shengjun Fang, Yang Yu, Zongzhang Zhang","submitted_at":"2024-07-05T12:05:37Z","abstract_excerpt":"Offline preference-based reinforcement learning (RL), which focuses on optimizing policies using human preferences between pairs of trajectory segments selected from an offline dataset, has emerged as a practical avenue for RL applications. Existing works rely on extracting step-wise reward signals from trajectory-wise preference annotations, assuming that preferences correlate with the cumulative Markovian rewards. However, such methods fail to capture the holistic perspective of data annotation: Humans often assess the desirability of a sequence of actions by considering the overall outcome "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04451","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/2407.04451/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":"2026-07-05T08:40:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yqg2uI53Co/v53LzLjWg359jTMeuFUi0Xbs8dXBJHfyKBkns7lrYJOUV0k1iVIugAqj8VMwWGNcbkZ3bEJ/ACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:56:13.871389Z"},"content_sha256":"fcff7d90fd77f0b68d4b8a5956c9d5819c0190c481f7060be084a5e925d509be","schema_version":"1.0","event_id":"sha256:fcff7d90fd77f0b68d4b8a5956c9d5819c0190c481f7060be084a5e925d509be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TNJKNAHQXG37B7X5S7STNVDBEQ/bundle.json","state_url":"https://pith.science/pith/TNJKNAHQXG37B7X5S7STNVDBEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TNJKNAHQXG37B7X5S7STNVDBEQ/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":"2026-08-09T05:56:13Z","links":{"resolver":"https://pith.science/pith/TNJKNAHQXG37B7X5S7STNVDBEQ","bundle":"https://pith.science/pith/TNJKNAHQXG37B7X5S7STNVDBEQ/bundle.json","state":"https://pith.science/pith/TNJKNAHQXG37B7X5S7STNVDBEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TNJKNAHQXG37B7X5S7STNVDBEQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TNJKNAHQXG37B7X5S7STNVDBEQ","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":"7e63c4fe31cf127041c201b039151fad14941e0e0fdb851d757d968539e2ae79","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-05T12:05:37Z","title_canon_sha256":"03197d4a277593b3da9aa851bfa21d678a52cc7d9c8bf34f2cc32a7b257a04a5"},"schema_version":"1.0","source":{"id":"2407.04451","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04451","created_at":"2026-07-05T08:40:33Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04451v1","created_at":"2026-07-05T08:40:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04451","created_at":"2026-07-05T08:40:33Z"},{"alias_kind":"pith_short_12","alias_value":"TNJKNAHQXG37","created_at":"2026-07-05T08:40:33Z"},{"alias_kind":"pith_short_16","alias_value":"TNJKNAHQXG37B7X5","created_at":"2026-07-05T08:40:33Z"},{"alias_kind":"pith_short_8","alias_value":"TNJKNAHQ","created_at":"2026-07-05T08:40:33Z"}],"graph_snapshots":[{"event_id":"sha256:fcff7d90fd77f0b68d4b8a5956c9d5819c0190c481f7060be084a5e925d509be","target":"graph","created_at":"2026-07-05T08:40:33Z","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/2407.04451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline preference-based reinforcement learning (RL), which focuses on optimizing policies using human preferences between pairs of trajectory segments selected from an offline dataset, has emerged as a practical avenue for RL applications. Existing works rely on extracting step-wise reward signals from trajectory-wise preference annotations, assuming that preferences correlate with the cumulative Markovian rewards. However, such methods fail to capture the holistic perspective of data annotation: Humans often assess the desirability of a sequence of actions by considering the overall outcome ","authors_text":"Chenjun Xiao, Chen-Xiao Gao, Shengjun Fang, Yang Yu, Zongzhang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-05T12:05:37Z","title":"Hindsight Preference Learning for Offline Preference-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04451","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:d2df2f7bcc6ca821a0ff55c669cb3c921fea7487a9adf06401afd40894a19275","target":"record","created_at":"2026-07-05T08:40:33Z","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":"7e63c4fe31cf127041c201b039151fad14941e0e0fdb851d757d968539e2ae79","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-05T12:05:37Z","title_canon_sha256":"03197d4a277593b3da9aa851bfa21d678a52cc7d9c8bf34f2cc32a7b257a04a5"},"schema_version":"1.0","source":{"id":"2407.04451","kind":"arxiv","version":1}},"canonical_sha256":"9b52a680f0b9b7f0fefd97e536d461241c84e9c9e33d8994924a6b628d5748ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b52a680f0b9b7f0fefd97e536d461241c84e9c9e33d8994924a6b628d5748ae","first_computed_at":"2026-07-05T08:40:33.847163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:33.847163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X6Nv6LGG+tJWodDp5nIcjgsBZxaBWT2KOu7FtcFg3cH45t+FRRcKDj5HzaOae63qmg/S7+6I0wNX4ge5SQg5AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:33.847666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04451","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2df2f7bcc6ca821a0ff55c669cb3c921fea7487a9adf06401afd40894a19275","sha256:fcff7d90fd77f0b68d4b8a5956c9d5819c0190c481f7060be084a5e925d509be"],"state_sha256":"8992ecb2adb578eb04c921af613065cbab06db020c7a5bcb9103372d60df0766"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9VWBRO5YpNOTxYeg1xrsOS7rGmVC3pvGz3k81u/jNUvGPuF3d45zTEziJWSxI13YP9npUCZzCK6UvOLfdfpKBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:56:13.879696Z","bundle_sha256":"51adfb027886fd491edc000927ae386ae81ff8927f454d98392b518fe478412f"}}