{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:A23355QAJAKKWWQMVF6ZOUPJZF","short_pith_number":"pith:A23355QA","canonical_record":{"source":{"id":"2411.04991","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-07T18:57:03Z","cross_cats_sorted":[],"title_canon_sha256":"021113b57f0b1de1337f37653ff593761ee33d0b12f2f72607d90daa075e2f2f","abstract_canon_sha256":"ab736feba68367f1fc6f5930c2e4b8dc52ffb7b329eea64a7d1acfbe0c35feed"},"schema_version":"1.0"},"canonical_sha256":"06b7bef6004814ab5a0ca97d9751e9c959d8825173e573fe1f210cb358f780d7","source":{"kind":"arxiv","id":"2411.04991","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04991","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04991v2","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04991","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"A23355QAJAKK","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"A23355QAJAKKWWQM","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"A23355QA","created_at":"2026-07-05T10:05:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:A23355QAJAKKWWQMVF6ZOUPJZF","target":"record","payload":{"canonical_record":{"source":{"id":"2411.04991","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-07T18:57:03Z","cross_cats_sorted":[],"title_canon_sha256":"021113b57f0b1de1337f37653ff593761ee33d0b12f2f72607d90daa075e2f2f","abstract_canon_sha256":"ab736feba68367f1fc6f5930c2e4b8dc52ffb7b329eea64a7d1acfbe0c35feed"},"schema_version":"1.0"},"canonical_sha256":"06b7bef6004814ab5a0ca97d9751e9c959d8825173e573fe1f210cb358f780d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:14.477160Z","signature_b64":"b0sAyK26rTvwdsfNVL1J1oQv7TFbwMal1+XSo4uqkd8esHlKqgLDHXcIJCB7Pgau/fhW3lr1jiYne1qKRpy2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06b7bef6004814ab5a0ca97d9751e9c959d8825173e573fe1f210cb358f780d7","last_reissued_at":"2026-07-05T10:05:14.476650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:14.476650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.04991","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":"2026-07-05T10:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s6xNYrJ7Y6JYXjXSFRG+Spi2Mof354F+JFGr/Xxo/kv062otY6f+zNrfOmR5RvSxVHiUmQoW5rdiNJoXb2zOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:08:23.616830Z"},"content_sha256":"02379d59624ad5860b25633b118e2749f52cb2d1916fce9040a7f8782ee1eb78","schema_version":"1.0","event_id":"sha256:02379d59624ad5860b25633b118e2749f52cb2d1916fce9040a7f8782ee1eb78"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:A23355QAJAKKWWQMVF6ZOUPJZF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hao Sun, Jean-Francois Ton, Yunyi Shen","submitted_at":"2024-11-07T18:57:03Z","abstract_excerpt":"The Bradley-Terry (BT) model is a common and successful practice in reward modeling for Large Language Model (LLM) alignment. However, it remains unclear why this model -- originally developed for multi-player stochastic game matching -- can be adopted to convert pairwise response comparisons to reward values and make predictions. Especially given the fact that only a limited number of prompt-response pairs are sparsely compared with others. In this paper, we first revisit the foundations of using BT models in reward modeling, and establish the convergence rate of BT reward models based on dee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04991","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/2411.04991/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":"2026-07-05T10:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C0GFMEibnUJKlCBnpUdLUolQswysuPIxx3y7+fydpdpcUDEHEJNGx7R7cUMmUctDTDF7SWHqxFzuaCANoETlCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:08:23.617496Z"},"content_sha256":"be517dae1ce8630b638fe9bed971f31786024b5dc35783c57b3f30823eacf44d","schema_version":"1.0","event_id":"sha256:be517dae1ce8630b638fe9bed971f31786024b5dc35783c57b3f30823eacf44d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A23355QAJAKKWWQMVF6ZOUPJZF/bundle.json","state_url":"https://pith.science/pith/A23355QAJAKKWWQMVF6ZOUPJZF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A23355QAJAKKWWQMVF6ZOUPJZF/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":"2026-07-07T05:08:23Z","links":{"resolver":"https://pith.science/pith/A23355QAJAKKWWQMVF6ZOUPJZF","bundle":"https://pith.science/pith/A23355QAJAKKWWQMVF6ZOUPJZF/bundle.json","state":"https://pith.science/pith/A23355QAJAKKWWQMVF6ZOUPJZF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A23355QAJAKKWWQMVF6ZOUPJZF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A23355QAJAKKWWQMVF6ZOUPJZF","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":"ab736feba68367f1fc6f5930c2e4b8dc52ffb7b329eea64a7d1acfbe0c35feed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-07T18:57:03Z","title_canon_sha256":"021113b57f0b1de1337f37653ff593761ee33d0b12f2f72607d90daa075e2f2f"},"schema_version":"1.0","source":{"id":"2411.04991","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04991","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04991v2","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04991","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"A23355QAJAKK","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"A23355QAJAKKWWQM","created_at":"2026-07-05T10:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"A23355QA","created_at":"2026-07-05T10:05:14Z"}],"graph_snapshots":[{"event_id":"sha256:be517dae1ce8630b638fe9bed971f31786024b5dc35783c57b3f30823eacf44d","target":"graph","created_at":"2026-07-05T10:05:14Z","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/2411.04991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Bradley-Terry (BT) model is a common and successful practice in reward modeling for Large Language Model (LLM) alignment. However, it remains unclear why this model -- originally developed for multi-player stochastic game matching -- can be adopted to convert pairwise response comparisons to reward values and make predictions. Especially given the fact that only a limited number of prompt-response pairs are sparsely compared with others. In this paper, we first revisit the foundations of using BT models in reward modeling, and establish the convergence rate of BT reward models based on dee","authors_text":"Hao Sun, Jean-Francois Ton, Yunyi Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-07T18:57:03Z","title":"Rethinking Bradley-Terry Models in Preference-Based Reward Modeling: Foundations, Theory, and Alternatives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04991","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":"sha256:02379d59624ad5860b25633b118e2749f52cb2d1916fce9040a7f8782ee1eb78","target":"record","created_at":"2026-07-05T10:05:14Z","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":"ab736feba68367f1fc6f5930c2e4b8dc52ffb7b329eea64a7d1acfbe0c35feed","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-07T18:57:03Z","title_canon_sha256":"021113b57f0b1de1337f37653ff593761ee33d0b12f2f72607d90daa075e2f2f"},"schema_version":"1.0","source":{"id":"2411.04991","kind":"arxiv","version":2}},"canonical_sha256":"06b7bef6004814ab5a0ca97d9751e9c959d8825173e573fe1f210cb358f780d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06b7bef6004814ab5a0ca97d9751e9c959d8825173e573fe1f210cb358f780d7","first_computed_at":"2026-07-05T10:05:14.476650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:14.476650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b0sAyK26rTvwdsfNVL1J1oQv7TFbwMal1+XSo4uqkd8esHlKqgLDHXcIJCB7Pgau/fhW3lr1jiYne1qKRpy2AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:14.477160Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04991","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02379d59624ad5860b25633b118e2749f52cb2d1916fce9040a7f8782ee1eb78","sha256:be517dae1ce8630b638fe9bed971f31786024b5dc35783c57b3f30823eacf44d"],"state_sha256":"d588015d9e5488b85089f0bf962706571429724595ee974c0f5d7898297a2938"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9jW1ub69FPLrUgolDYevE/sNw09oWtWa/Z4BTa64g2pj8U/MvRt77qdeTH1jPNBjuttQC8CDjDxJtHMm6HMWDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:08:23.621083Z","bundle_sha256":"be128d49f50d63819b4430f0ef7a8a36234f77e89fd52d89638cb17b722e4343"}}