{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ONM3W2MH2FZO2JWGI4BM2KVYHH","short_pith_number":"pith:ONM3W2MH","canonical_record":{"source":{"id":"2403.13787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-20T17:49:54Z","cross_cats_sorted":[],"title_canon_sha256":"1bbf49fa9ac42d7fd478b8f6cb538064aa8ec7952d34e3da5bf7fe943e3f3d4f","abstract_canon_sha256":"1c0024b059f8647810fd6c17e064e7b5baa2a8c4e417075655203c1cbbcfed67"},"schema_version":"1.0"},"canonical_sha256":"7359bb6987d172ed26c64702cd2ab839dbe328bb74e4f56c07f667c2fa13910d","source":{"kind":"arxiv","id":"2403.13787","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13787","created_at":"2026-07-05T08:29:24Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13787v2","created_at":"2026-07-05T08:29:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13787","created_at":"2026-07-05T08:29:24Z"},{"alias_kind":"pith_short_12","alias_value":"ONM3W2MH2FZO","created_at":"2026-07-05T08:29:24Z"},{"alias_kind":"pith_short_16","alias_value":"ONM3W2MH2FZO2JWG","created_at":"2026-07-05T08:29:24Z"},{"alias_kind":"pith_short_8","alias_value":"ONM3W2MH","created_at":"2026-07-05T08:29:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ONM3W2MH2FZO2JWGI4BM2KVYHH","target":"record","payload":{"canonical_record":{"source":{"id":"2403.13787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-20T17:49:54Z","cross_cats_sorted":[],"title_canon_sha256":"1bbf49fa9ac42d7fd478b8f6cb538064aa8ec7952d34e3da5bf7fe943e3f3d4f","abstract_canon_sha256":"1c0024b059f8647810fd6c17e064e7b5baa2a8c4e417075655203c1cbbcfed67"},"schema_version":"1.0"},"canonical_sha256":"7359bb6987d172ed26c64702cd2ab839dbe328bb74e4f56c07f667c2fa13910d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:24.623485Z","signature_b64":"oIEXGv9jf71yxUrWzgPcLssK4M0g0BjYrvSoGRhNVIgYAFCgVwt5DeRtMebCCyHHY7OaToC+CgO+hKNclByfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7359bb6987d172ed26c64702cd2ab839dbe328bb74e4f56c07f667c2fa13910d","last_reissued_at":"2026-07-05T08:29:24.622998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:24.622998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.13787","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":"2026-07-05T08:29:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iZYcaIQuBV6Ggd7ONO02x7lLoAIH+KwOmilPuGGB7RGihbNoBnYZVEvKu2wEhCNCbpcRhsj6aXp2ZF83PZwcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:19:18.971417Z"},"content_sha256":"8e7978b46fcd51d9976186e7bb5916e882e4a646b7cd07b92a904c61916f9e75","schema_version":"1.0","event_id":"sha256:8e7978b46fcd51d9976186e7bb5916e882e4a646b7cd07b92a904c61916f9e75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ONM3W2MH2FZO2JWGI4BM2KVYHH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RewardBench: Evaluating Reward Models for Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bill Yuchen Lin, Hannaneh Hajishirzi, Jacob Morrison, Khyathi Chandu, LJ Miranda, Nathan Lambert, Noah A. Smith, Nouha Dziri, Sachin Kumar, Tom Zick, Valentina Pyatkin, Yejin Choi","submitted_at":"2024-03-20T17:49:54Z","abstract_excerpt":"Reward models (RMs) are at the crux of successfully using RLHF to align pretrained models to human preferences, yet there has been relatively little study that focuses on evaluation of those models. Evaluating reward models presents an opportunity to understand the opaque technologies used for alignment of language models and which values are embedded in them. Resources for reward model training and understanding are sparse in the nascent open-source community around them. To enhance scientific understanding of reward models, we present RewardBench, a benchmark dataset and code-base for evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13787","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/2403.13787/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":"2026-07-05T08:29:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ns7VWxrx1AImHEs9NO4o2RYtGdnEd2iOakTu79MI3hU0UoWumNJ2SHL2MUQOxgu11IgMJ/AXKpAU1MWFYjhQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T23:19:18.971800Z"},"content_sha256":"1da395f2dd7dd8c278418e5d3ede18ce40a606f1239ec45cf7003fce64a7bbc5","schema_version":"1.0","event_id":"sha256:1da395f2dd7dd8c278418e5d3ede18ce40a606f1239ec45cf7003fce64a7bbc5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ONM3W2MH2FZO2JWGI4BM2KVYHH/bundle.json","state_url":"https://pith.science/pith/ONM3W2MH2FZO2JWGI4BM2KVYHH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ONM3W2MH2FZO2JWGI4BM2KVYHH/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":"2026-07-08T23:19:18Z","links":{"resolver":"https://pith.science/pith/ONM3W2MH2FZO2JWGI4BM2KVYHH","bundle":"https://pith.science/pith/ONM3W2MH2FZO2JWGI4BM2KVYHH/bundle.json","state":"https://pith.science/pith/ONM3W2MH2FZO2JWGI4BM2KVYHH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ONM3W2MH2FZO2JWGI4BM2KVYHH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ONM3W2MH2FZO2JWGI4BM2KVYHH","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":"1c0024b059f8647810fd6c17e064e7b5baa2a8c4e417075655203c1cbbcfed67","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-20T17:49:54Z","title_canon_sha256":"1bbf49fa9ac42d7fd478b8f6cb538064aa8ec7952d34e3da5bf7fe943e3f3d4f"},"schema_version":"1.0","source":{"id":"2403.13787","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13787","created_at":"2026-07-05T08:29:24Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13787v2","created_at":"2026-07-05T08:29:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13787","created_at":"2026-07-05T08:29:24Z"},{"alias_kind":"pith_short_12","alias_value":"ONM3W2MH2FZO","created_at":"2026-07-05T08:29:24Z"},{"alias_kind":"pith_short_16","alias_value":"ONM3W2MH2FZO2JWG","created_at":"2026-07-05T08:29:24Z"},{"alias_kind":"pith_short_8","alias_value":"ONM3W2MH","created_at":"2026-07-05T08:29:24Z"}],"graph_snapshots":[{"event_id":"sha256:1da395f2dd7dd8c278418e5d3ede18ce40a606f1239ec45cf7003fce64a7bbc5","target":"graph","created_at":"2026-07-05T08:29:24Z","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/2403.13787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward models (RMs) are at the crux of successfully using RLHF to align pretrained models to human preferences, yet there has been relatively little study that focuses on evaluation of those models. Evaluating reward models presents an opportunity to understand the opaque technologies used for alignment of language models and which values are embedded in them. Resources for reward model training and understanding are sparse in the nascent open-source community around them. To enhance scientific understanding of reward models, we present RewardBench, a benchmark dataset and code-base for evalua","authors_text":"Bill Yuchen Lin, Hannaneh Hajishirzi, Jacob Morrison, Khyathi Chandu, LJ Miranda, Nathan Lambert, Noah A. Smith, Nouha Dziri, Sachin Kumar, Tom Zick, Valentina Pyatkin, Yejin Choi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-20T17:49:54Z","title":"RewardBench: Evaluating Reward Models for Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13787","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":"sha256:8e7978b46fcd51d9976186e7bb5916e882e4a646b7cd07b92a904c61916f9e75","target":"record","created_at":"2026-07-05T08:29:24Z","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":"1c0024b059f8647810fd6c17e064e7b5baa2a8c4e417075655203c1cbbcfed67","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-20T17:49:54Z","title_canon_sha256":"1bbf49fa9ac42d7fd478b8f6cb538064aa8ec7952d34e3da5bf7fe943e3f3d4f"},"schema_version":"1.0","source":{"id":"2403.13787","kind":"arxiv","version":2}},"canonical_sha256":"7359bb6987d172ed26c64702cd2ab839dbe328bb74e4f56c07f667c2fa13910d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7359bb6987d172ed26c64702cd2ab839dbe328bb74e4f56c07f667c2fa13910d","first_computed_at":"2026-07-05T08:29:24.622998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:24.622998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oIEXGv9jf71yxUrWzgPcLssK4M0g0BjYrvSoGRhNVIgYAFCgVwt5DeRtMebCCyHHY7OaToC+CgO+hKNclByfAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:24.623485Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.13787","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e7978b46fcd51d9976186e7bb5916e882e4a646b7cd07b92a904c61916f9e75","sha256:1da395f2dd7dd8c278418e5d3ede18ce40a606f1239ec45cf7003fce64a7bbc5"],"state_sha256":"2d98ddecb7ce54ff0eeddc262ce2127b582f2d311b016d4c077407f10200c749"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ndfe9R9/Iz1ZyMr5l7dIeFqeCg0KXV6cn5cK0xLb6l0v1AK2MZgPHHmK0BbR/Ac6ei34RVBYP3+GJ7FShQZRAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T23:19:18.973853Z","bundle_sha256":"8279c2093bcd4a36d5cc6391e1251eade170888907c3e1040e1c85bdce3b9596"}}