{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:POHXFJNMVUI2PG6OR7RBPG2MGJ","short_pith_number":"pith:POHXFJNM","canonical_record":{"source":{"id":"2402.01878","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T20:08:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"13c33650073478bedd8bea0d03f7832bf126fffa28e489e8359ef5f5b0ee89bc","abstract_canon_sha256":"3dfe823c1002c11b37db8183124c580d0a9f6b9993d977a05adb15376449ea53"},"schema_version":"1.0"},"canonical_sha256":"7b8f72a5acad11a79bce8fe2179b4c326892c296973bcee09699ed5635b74e48","source":{"kind":"arxiv","id":"2402.01878","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01878","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01878v3","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01878","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"POHXFJNMVUI2","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"POHXFJNMVUI2PG6O","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"POHXFJNM","created_at":"2026-07-05T10:05:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:POHXFJNMVUI2PG6OR7RBPG2MGJ","target":"record","payload":{"canonical_record":{"source":{"id":"2402.01878","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T20:08:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"13c33650073478bedd8bea0d03f7832bf126fffa28e489e8359ef5f5b0ee89bc","abstract_canon_sha256":"3dfe823c1002c11b37db8183124c580d0a9f6b9993d977a05adb15376449ea53"},"schema_version":"1.0"},"canonical_sha256":"7b8f72a5acad11a79bce8fe2179b4c326892c296973bcee09699ed5635b74e48","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:08.857410Z","signature_b64":"3NNSY8gZe/hc/QoQrSIGSrTNIFNDgzAamEeIkp7lbKe76Czt/XlGYQgPp6qQZsin4j6lKMYZ/3XX/22cBQUlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b8f72a5acad11a79bce8fe2179b4c326892c296973bcee09699ed5635b74e48","last_reissued_at":"2026-07-05T10:05:08.856883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:08.856883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.01878","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":"2026-07-05T10:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hiJTnnuCmkMkm+t8aZPJNLyJtbjMNIE77zzu5P7kLgS1pO9F/TQfUyvtbqQSwP8JWsTtiPbjsLlDU9yYyTiaDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:43:26.386732Z"},"content_sha256":"10bbf191000af7c579a61783a9a685b18ef187bd8a85316351a2b363be1ed705","schema_version":"1.0","event_id":"sha256:10bbf191000af7c579a61783a9a685b18ef187bd8a85316351a2b363be1ed705"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:POHXFJNMVUI2PG6OR7RBPG2MGJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LiPO: Listwise Preference Optimization through Learning-to-Rank","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jialu Liu, Jiaming Shen, Junru Wu, Misha Khalman, Mohammad Saleh, Peter J. Liu, Rishabh Joshi, Simon Baumgartner, Tianqi Liu, Xuanhui Wang, Yao Zhao, Zhen Qin","submitted_at":"2024-02-02T20:08:10Z","abstract_excerpt":"Aligning language models (LMs) with curated human feedback is critical to control their behaviors in real-world applications. Several recent policy optimization methods, such as DPO and SLiC, serve as promising alternatives to the traditional Reinforcement Learning from Human Feedback (RLHF) approach. In practice, human feedback often comes in a format of a ranked list over multiple responses to amortize the cost of reading prompt. Multiple responses can also be ranked by reward models or AI feedback. There lacks such a thorough study on directly fitting upon a list of responses. In this work,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01878","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/2402.01878/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":"2026-07-05T10:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ep0rnvgm2Jr3h6SJfGQKcY/yagg5NVWdz+hg9I+PzSs8evy3DJ0uFc+bPWj4YkmAEW0HiMTBkqWTAvEBoblCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:43:26.387225Z"},"content_sha256":"412b60ff0ec17028692d5bf234c76e4e2f171d1219bc1850e69037b614df2381","schema_version":"1.0","event_id":"sha256:412b60ff0ec17028692d5bf234c76e4e2f171d1219bc1850e69037b614df2381"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/POHXFJNMVUI2PG6OR7RBPG2MGJ/bundle.json","state_url":"https://pith.science/pith/POHXFJNMVUI2PG6OR7RBPG2MGJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/POHXFJNMVUI2PG6OR7RBPG2MGJ/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":"2026-08-06T07:43:26Z","links":{"resolver":"https://pith.science/pith/POHXFJNMVUI2PG6OR7RBPG2MGJ","bundle":"https://pith.science/pith/POHXFJNMVUI2PG6OR7RBPG2MGJ/bundle.json","state":"https://pith.science/pith/POHXFJNMVUI2PG6OR7RBPG2MGJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/POHXFJNMVUI2PG6OR7RBPG2MGJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:POHXFJNMVUI2PG6OR7RBPG2MGJ","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":"3dfe823c1002c11b37db8183124c580d0a9f6b9993d977a05adb15376449ea53","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T20:08:10Z","title_canon_sha256":"13c33650073478bedd8bea0d03f7832bf126fffa28e489e8359ef5f5b0ee89bc"},"schema_version":"1.0","source":{"id":"2402.01878","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01878","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01878v3","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01878","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"POHXFJNMVUI2","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"POHXFJNMVUI2PG6O","created_at":"2026-07-05T10:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"POHXFJNM","created_at":"2026-07-05T10:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:412b60ff0ec17028692d5bf234c76e4e2f171d1219bc1850e69037b614df2381","target":"graph","created_at":"2026-07-05T10:05:08Z","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/2402.01878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning language models (LMs) with curated human feedback is critical to control their behaviors in real-world applications. Several recent policy optimization methods, such as DPO and SLiC, serve as promising alternatives to the traditional Reinforcement Learning from Human Feedback (RLHF) approach. In practice, human feedback often comes in a format of a ranked list over multiple responses to amortize the cost of reading prompt. Multiple responses can also be ranked by reward models or AI feedback. There lacks such a thorough study on directly fitting upon a list of responses. In this work,","authors_text":"Jialu Liu, Jiaming Shen, Junru Wu, Misha Khalman, Mohammad Saleh, Peter J. Liu, Rishabh Joshi, Simon Baumgartner, Tianqi Liu, Xuanhui Wang, Yao Zhao, Zhen Qin","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T20:08:10Z","title":"LiPO: Listwise Preference Optimization through Learning-to-Rank"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01878","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":"sha256:10bbf191000af7c579a61783a9a685b18ef187bd8a85316351a2b363be1ed705","target":"record","created_at":"2026-07-05T10:05:08Z","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":"3dfe823c1002c11b37db8183124c580d0a9f6b9993d977a05adb15376449ea53","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T20:08:10Z","title_canon_sha256":"13c33650073478bedd8bea0d03f7832bf126fffa28e489e8359ef5f5b0ee89bc"},"schema_version":"1.0","source":{"id":"2402.01878","kind":"arxiv","version":3}},"canonical_sha256":"7b8f72a5acad11a79bce8fe2179b4c326892c296973bcee09699ed5635b74e48","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b8f72a5acad11a79bce8fe2179b4c326892c296973bcee09699ed5635b74e48","first_computed_at":"2026-07-05T10:05:08.856883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:08.856883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3NNSY8gZe/hc/QoQrSIGSrTNIFNDgzAamEeIkp7lbKe76Czt/XlGYQgPp6qQZsin4j6lKMYZ/3XX/22cBQUlCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:08.857410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01878","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10bbf191000af7c579a61783a9a685b18ef187bd8a85316351a2b363be1ed705","sha256:412b60ff0ec17028692d5bf234c76e4e2f171d1219bc1850e69037b614df2381"],"state_sha256":"92f559a4a7612a5125bb5f90ec0115c952a7f67f4360cc07377cd2c68090ab05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Iqrn5x+lES8/ZfbhzI49fWqzUIGO2amNe630iKNbBAnh9fo2LcQjCgTI8Oafxl7/7DRQMceie3t3/9uN2l8CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:43:26.390557Z","bundle_sha256":"fa01f80df3b9856e5681c5938ae414a62c2e9afe369c758bb317240538ddac6d"}}