{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QN3ABX2IIPHFIXAKK2GJAU6ZUP","short_pith_number":"pith:QN3ABX2I","canonical_record":{"source":{"id":"2410.01257","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T06:05:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ba40e4fca8e5350dba90f36b358698ac3efe2ce8ef2396a0df24c82cd3fa7d6a","abstract_canon_sha256":"152fc2265e177d7adb23f1934dd9d9848fe3ea18996c17361b711a4314edc27a"},"schema_version":"1.0"},"canonical_sha256":"837600df4843ce545c0a568c9053d9a3d34155a5cc1dbb01d58780b4b3ed737b","source":{"kind":"arxiv","id":"2410.01257","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01257","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01257v2","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01257","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"QN3ABX2IIPHF","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"pith_short_16","alias_value":"QN3ABX2IIPHFIXAK","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"pith_short_8","alias_value":"QN3ABX2I","created_at":"2026-07-05T10:25:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QN3ABX2IIPHFIXAKK2GJAU6ZUP","target":"record","payload":{"canonical_record":{"source":{"id":"2410.01257","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T06:05:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ba40e4fca8e5350dba90f36b358698ac3efe2ce8ef2396a0df24c82cd3fa7d6a","abstract_canon_sha256":"152fc2265e177d7adb23f1934dd9d9848fe3ea18996c17361b711a4314edc27a"},"schema_version":"1.0"},"canonical_sha256":"837600df4843ce545c0a568c9053d9a3d34155a5cc1dbb01d58780b4b3ed737b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:10.900345Z","signature_b64":"7z+N6RMoankn0GOdF5oHKsGCo8fitU6GOHMnqFW1bXbfufnteyCY7SQc/vuBDKZYzjvwWXtptoD8RJtMDJtvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"837600df4843ce545c0a568c9053d9a3d34155a5cc1dbb01d58780b4b3ed737b","last_reissued_at":"2026-07-05T10:25:10.899736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:10.899736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.01257","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":"2026-07-05T10:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5X3IPeWLAxd9iak+dDWGqfw7F+slVvnb7o1dMAYjKjqD4wg/Rrv30udTkIzpONUNx8otEvlMeZUaUOxcN4y8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:32:56.517559Z"},"content_sha256":"c3f3c80c3df4cd84806859b445ab7856434ed6388a1500f631e7c4325bdb7382","schema_version":"1.0","event_id":"sha256:c3f3c80c3df4cd84806859b445ab7856434ed6388a1500f631e7c4325bdb7382"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QN3ABX2IIPHFIXAKK2GJAU6ZUP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HelpSteer2-Preference: Complementing Ratings with Preferences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexander Bukharin, Daniel Egert, Gerald Shen, Jiaqi Zeng, Oleksii Kuchaiev, Olivier Delalleau, Yi Dong, Zhilin Wang","submitted_at":"2024-10-02T06:05:52Z","abstract_excerpt":"Reward models are critical for aligning models to follow instructions, and are typically trained following one of two popular paradigms: Bradley-Terry style or Regression style. However, there is a lack of evidence that either approach is better than the other, when adequately matched for data. This is primarily because these approaches require data collected in different (but incompatible) formats, meaning that adequately matched data is not available in existing public datasets. To tackle this problem, we release preference annotations (designed for Bradley-Terry training) to complement exis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01257","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/2410.01257/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":"2026-07-05T10:25:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7dGgSyU6XZUOk/Ym3RwqPMkdVaJ2l4iKMIkbNacL8SlkG1brORtmNeEUMiianXABRwhguh6CxKCISMQ6ZhYVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:32:56.518083Z"},"content_sha256":"04dbff95f4c1795a9f70313ec817f00310ed39f7472de63cff036f976cadb282","schema_version":"1.0","event_id":"sha256:04dbff95f4c1795a9f70313ec817f00310ed39f7472de63cff036f976cadb282"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QN3ABX2IIPHFIXAKK2GJAU6ZUP/bundle.json","state_url":"https://pith.science/pith/QN3ABX2IIPHFIXAKK2GJAU6ZUP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QN3ABX2IIPHFIXAKK2GJAU6ZUP/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":"2026-08-07T18:32:56Z","links":{"resolver":"https://pith.science/pith/QN3ABX2IIPHFIXAKK2GJAU6ZUP","bundle":"https://pith.science/pith/QN3ABX2IIPHFIXAKK2GJAU6ZUP/bundle.json","state":"https://pith.science/pith/QN3ABX2IIPHFIXAKK2GJAU6ZUP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QN3ABX2IIPHFIXAKK2GJAU6ZUP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QN3ABX2IIPHFIXAKK2GJAU6ZUP","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":"152fc2265e177d7adb23f1934dd9d9848fe3ea18996c17361b711a4314edc27a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T06:05:52Z","title_canon_sha256":"ba40e4fca8e5350dba90f36b358698ac3efe2ce8ef2396a0df24c82cd3fa7d6a"},"schema_version":"1.0","source":{"id":"2410.01257","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01257","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01257v2","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01257","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"QN3ABX2IIPHF","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"pith_short_16","alias_value":"QN3ABX2IIPHFIXAK","created_at":"2026-07-05T10:25:10Z"},{"alias_kind":"pith_short_8","alias_value":"QN3ABX2I","created_at":"2026-07-05T10:25:10Z"}],"graph_snapshots":[{"event_id":"sha256:04dbff95f4c1795a9f70313ec817f00310ed39f7472de63cff036f976cadb282","target":"graph","created_at":"2026-07-05T10:25:10Z","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/2410.01257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward models are critical for aligning models to follow instructions, and are typically trained following one of two popular paradigms: Bradley-Terry style or Regression style. However, there is a lack of evidence that either approach is better than the other, when adequately matched for data. This is primarily because these approaches require data collected in different (but incompatible) formats, meaning that adequately matched data is not available in existing public datasets. To tackle this problem, we release preference annotations (designed for Bradley-Terry training) to complement exis","authors_text":"Alexander Bukharin, Daniel Egert, Gerald Shen, Jiaqi Zeng, Oleksii Kuchaiev, Olivier Delalleau, Yi Dong, Zhilin Wang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T06:05:52Z","title":"HelpSteer2-Preference: Complementing Ratings with Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01257","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:c3f3c80c3df4cd84806859b445ab7856434ed6388a1500f631e7c4325bdb7382","target":"record","created_at":"2026-07-05T10:25:10Z","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":"152fc2265e177d7adb23f1934dd9d9848fe3ea18996c17361b711a4314edc27a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T06:05:52Z","title_canon_sha256":"ba40e4fca8e5350dba90f36b358698ac3efe2ce8ef2396a0df24c82cd3fa7d6a"},"schema_version":"1.0","source":{"id":"2410.01257","kind":"arxiv","version":2}},"canonical_sha256":"837600df4843ce545c0a568c9053d9a3d34155a5cc1dbb01d58780b4b3ed737b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"837600df4843ce545c0a568c9053d9a3d34155a5cc1dbb01d58780b4b3ed737b","first_computed_at":"2026-07-05T10:25:10.899736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:10.899736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7z+N6RMoankn0GOdF5oHKsGCo8fitU6GOHMnqFW1bXbfufnteyCY7SQc/vuBDKZYzjvwWXtptoD8RJtMDJtvDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:10.900345Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01257","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3f3c80c3df4cd84806859b445ab7856434ed6388a1500f631e7c4325bdb7382","sha256:04dbff95f4c1795a9f70313ec817f00310ed39f7472de63cff036f976cadb282"],"state_sha256":"5a1d0d5b5182a931a62c3a75fb5d015d8b8bb6be0b438027a671eb160f5970b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vwtrd3QcfdqRGrNEL9Sa00BYmUGDwV4Gr4RMFbE2+fSrGqmvBwog/sRoqMAI6OIYbB0xd78Gn8qIjDXuAnApCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:32:56.522592Z","bundle_sha256":"e3efa7b06da9e492bda27d5471138ecd5d75e65686af37d3c5e04045cb6d3cdb"}}