{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TMIJ5XJMAGLVXLZV5CZTKMU5SW","short_pith_number":"pith:TMIJ5XJM","canonical_record":{"source":{"id":"2408.04190","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-08T03:18:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0235c71e4ba02e42f77c866063f80c1bd58045e4958cf5c84830cfc74825ea4f","abstract_canon_sha256":"8a54efa11331171c746f373941bdf3d612e135d287df516a2b457cc12b128f8c"},"schema_version":"1.0"},"canonical_sha256":"9b109edd2c01975baf35e8b335329d95961cc5599d7e73719d117fbffe88e003","source":{"kind":"arxiv","id":"2408.04190","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04190","created_at":"2026-07-05T08:53:29Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04190v1","created_at":"2026-07-05T08:53:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04190","created_at":"2026-07-05T08:53:29Z"},{"alias_kind":"pith_short_12","alias_value":"TMIJ5XJMAGLV","created_at":"2026-07-05T08:53:29Z"},{"alias_kind":"pith_short_16","alias_value":"TMIJ5XJMAGLVXLZV","created_at":"2026-07-05T08:53:29Z"},{"alias_kind":"pith_short_8","alias_value":"TMIJ5XJM","created_at":"2026-07-05T08:53:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TMIJ5XJMAGLVXLZV5CZTKMU5SW","target":"record","payload":{"canonical_record":{"source":{"id":"2408.04190","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-08T03:18:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0235c71e4ba02e42f77c866063f80c1bd58045e4958cf5c84830cfc74825ea4f","abstract_canon_sha256":"8a54efa11331171c746f373941bdf3d612e135d287df516a2b457cc12b128f8c"},"schema_version":"1.0"},"canonical_sha256":"9b109edd2c01975baf35e8b335329d95961cc5599d7e73719d117fbffe88e003","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:29.548633Z","signature_b64":"MbnriVJ4sL8zQuvn99mSSgDm1Pkc9PO4KjkyV0XA8pE8LjvVfcutlvuYRMxrlYbfJrzH1qo3T8z3b7DrcgI1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b109edd2c01975baf35e8b335329d95961cc5599d7e73719d117fbffe88e003","last_reissued_at":"2026-07-05T08:53:29.548220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:29.548220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.04190","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":"2026-07-05T08:53:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iKL+om+RqKLMbZA5Xwt7gbIIMSxCAXr+m0vBU8Pw9VVzYyufsiso9j8LUSs/6C8S5XIXgqqVa7YjjKLvV454Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:30:51.718245Z"},"content_sha256":"ce2275d8a52a0cb98bc7c915e95ae2d08fe92970ad6cc8754052a9ac884377c0","schema_version":"1.0","event_id":"sha256:ce2275d8a52a0cb98bc7c915e95ae2d08fe92970ad6cc8754052a9ac884377c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TMIJ5XJMAGLVXLZV5CZTKMU5SW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Listwise Reward Estimation 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":"Heewoong Choi, Hongjoon Ahn, Sangwon Jung, Taesup Moon","submitted_at":"2024-08-08T03:18:42Z","abstract_excerpt":"In Reinforcement Learning (RL), designing precise reward functions remains to be a challenge, particularly when aligning with human intent. Preference-based RL (PbRL) was introduced to address this problem by learning reward models from human feedback. However, existing PbRL methods have limitations as they often overlook the second-order preference that indicates the relative strength of preference. In this paper, we propose Listwise Reward Estimation (LiRE), a novel approach for offline PbRL that leverages second-order preference information by constructing a Ranked List of Trajectories (RLT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04190","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/2408.04190/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":"2026-07-05T08:53:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"clIr8qcKl5qpe3GyDnhFCnzgJFxergsJGgiPgziHAYfHpiC9iOrcNNwayHWf7jWGavM+xmC4BU1CeOlKAuaODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:30:51.718747Z"},"content_sha256":"5b3477fc86af3f7299960f795a95bff2a584a3e294bc5e95eefd343860350406","schema_version":"1.0","event_id":"sha256:5b3477fc86af3f7299960f795a95bff2a584a3e294bc5e95eefd343860350406"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TMIJ5XJMAGLVXLZV5CZTKMU5SW/bundle.json","state_url":"https://pith.science/pith/TMIJ5XJMAGLVXLZV5CZTKMU5SW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TMIJ5XJMAGLVXLZV5CZTKMU5SW/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":"2026-08-09T07:30:51Z","links":{"resolver":"https://pith.science/pith/TMIJ5XJMAGLVXLZV5CZTKMU5SW","bundle":"https://pith.science/pith/TMIJ5XJMAGLVXLZV5CZTKMU5SW/bundle.json","state":"https://pith.science/pith/TMIJ5XJMAGLVXLZV5CZTKMU5SW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TMIJ5XJMAGLVXLZV5CZTKMU5SW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TMIJ5XJMAGLVXLZV5CZTKMU5SW","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":"8a54efa11331171c746f373941bdf3d612e135d287df516a2b457cc12b128f8c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-08T03:18:42Z","title_canon_sha256":"0235c71e4ba02e42f77c866063f80c1bd58045e4958cf5c84830cfc74825ea4f"},"schema_version":"1.0","source":{"id":"2408.04190","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04190","created_at":"2026-07-05T08:53:29Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04190v1","created_at":"2026-07-05T08:53:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04190","created_at":"2026-07-05T08:53:29Z"},{"alias_kind":"pith_short_12","alias_value":"TMIJ5XJMAGLV","created_at":"2026-07-05T08:53:29Z"},{"alias_kind":"pith_short_16","alias_value":"TMIJ5XJMAGLVXLZV","created_at":"2026-07-05T08:53:29Z"},{"alias_kind":"pith_short_8","alias_value":"TMIJ5XJM","created_at":"2026-07-05T08:53:29Z"}],"graph_snapshots":[{"event_id":"sha256:5b3477fc86af3f7299960f795a95bff2a584a3e294bc5e95eefd343860350406","target":"graph","created_at":"2026-07-05T08:53:29Z","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/2408.04190/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Reinforcement Learning (RL), designing precise reward functions remains to be a challenge, particularly when aligning with human intent. Preference-based RL (PbRL) was introduced to address this problem by learning reward models from human feedback. However, existing PbRL methods have limitations as they often overlook the second-order preference that indicates the relative strength of preference. In this paper, we propose Listwise Reward Estimation (LiRE), a novel approach for offline PbRL that leverages second-order preference information by constructing a Ranked List of Trajectories (RLT","authors_text":"Heewoong Choi, Hongjoon Ahn, Sangwon Jung, Taesup Moon","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-08T03:18:42Z","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04190","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:ce2275d8a52a0cb98bc7c915e95ae2d08fe92970ad6cc8754052a9ac884377c0","target":"record","created_at":"2026-07-05T08:53:29Z","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":"8a54efa11331171c746f373941bdf3d612e135d287df516a2b457cc12b128f8c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-08T03:18:42Z","title_canon_sha256":"0235c71e4ba02e42f77c866063f80c1bd58045e4958cf5c84830cfc74825ea4f"},"schema_version":"1.0","source":{"id":"2408.04190","kind":"arxiv","version":1}},"canonical_sha256":"9b109edd2c01975baf35e8b335329d95961cc5599d7e73719d117fbffe88e003","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b109edd2c01975baf35e8b335329d95961cc5599d7e73719d117fbffe88e003","first_computed_at":"2026-07-05T08:53:29.548220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:29.548220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MbnriVJ4sL8zQuvn99mSSgDm1Pkc9PO4KjkyV0XA8pE8LjvVfcutlvuYRMxrlYbfJrzH1qo3T8z3b7DrcgI1Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:29.548633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04190","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce2275d8a52a0cb98bc7c915e95ae2d08fe92970ad6cc8754052a9ac884377c0","sha256:5b3477fc86af3f7299960f795a95bff2a584a3e294bc5e95eefd343860350406"],"state_sha256":"e5069c3dac89bcb08b3345f571c5a542f8fe15829760b8e095606ab564bcd16f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VlzxypTv9RWXhECSCsUXQmsxy9hUC623fKjjKAQzVyBZzCAEV26Heep5UiA4Ac8tf/OJxuaofTJ2idQNMFDaBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:30:51.722797Z","bundle_sha256":"1eb2c06b28d733a3ee0c67bd5250ebd3f55342248c3c9b0edc5087e5b9abbeda"}}