{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CH2JSDHCQ6EYWJCFG7DLAGI23Q","short_pith_number":"pith:CH2JSDHC","canonical_record":{"source":{"id":"2505.14674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T17:58:03Z","cross_cats_sorted":[],"title_canon_sha256":"786b7b2a52651e19959c3fce673ad3352903eb57c351da9ee9d9a6fd814284e2","abstract_canon_sha256":"235c9ffdaeea6dd0ec8599439ad7994c1795b800f6d22b9c18bc49376591c63b"},"schema_version":"1.0"},"canonical_sha256":"11f4990ce287898b244537c6b0191adc3a84b5e437f38d90a218b424b42ca95a","source":{"kind":"arxiv","id":"2505.14674","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14674","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14674v1","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14674","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"pith_short_12","alias_value":"CH2JSDHCQ6EY","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"pith_short_16","alias_value":"CH2JSDHCQ6EYWJCF","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"pith_short_8","alias_value":"CH2JSDHC","created_at":"2026-07-05T11:06:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CH2JSDHCQ6EYWJCFG7DLAGI23Q","target":"record","payload":{"canonical_record":{"source":{"id":"2505.14674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T17:58:03Z","cross_cats_sorted":[],"title_canon_sha256":"786b7b2a52651e19959c3fce673ad3352903eb57c351da9ee9d9a6fd814284e2","abstract_canon_sha256":"235c9ffdaeea6dd0ec8599439ad7994c1795b800f6d22b9c18bc49376591c63b"},"schema_version":"1.0"},"canonical_sha256":"11f4990ce287898b244537c6b0191adc3a84b5e437f38d90a218b424b42ca95a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:17.454048Z","signature_b64":"BymEHtGK2C41Jd9d1DcL+AAp1ZWOpzeFylETEN0L/xsnT80n2GjraDi3VbP0h/WAGfbwOZW/DodeLhUG+g1iAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11f4990ce287898b244537c6b0191adc3a84b5e437f38d90a218b424b42ca95a","last_reissued_at":"2026-07-05T11:06:17.453526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:17.453526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.14674","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":"2026-07-05T11:06:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TVcGg5kwWWHyCAWQ1Kh3G5aJEqH5zLPzhcfzHmTzXvzBAC9NHzjuR9LQFfxTkuL/MKRLLC+I/d+atrZx/X6YAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:20:26.678387Z"},"content_sha256":"758a7688fa10f836499b65bb6916342070252290569862805707c83c8d7a579b","schema_version":"1.0","event_id":"sha256:758a7688fa10f836499b65bb6916342070252290569862805707c83c8d7a579b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CH2JSDHCQ6EYWJCFG7DLAGI23Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Reasoning Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Jiaxin Guo, Li Dong, Qingxiu Dong, Shaohan Huang, Xun Wu, Zewen Chi","submitted_at":"2025-05-20T17:58:03Z","abstract_excerpt":"Reward models play a critical role in guiding large language models toward outputs that align with human expectations. However, an open challenge remains in effectively utilizing test-time compute to enhance reward model performance. In this work, we introduce Reward Reasoning Models (RRMs), which are specifically designed to execute a deliberate reasoning process before generating final rewards. Through chain-of-thought reasoning, RRMs leverage additional test-time compute for complex queries where appropriate rewards are not immediately apparent. To develop RRMs, we implement a reinforcement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14674","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/2505.14674/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":"2026-07-05T11:06:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tkNFo6ZLE3gglG8P0t8TKD+CPzKXWoWsu6o6q8j5AV73i4/u6aQVLX4SzZcOu5R3ZZH7KYlXjiS8L7UyKrvsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:20:26.678959Z"},"content_sha256":"0fe187932c5498b3b9bb96a7b292543b1524c0be1f13c12ea2882b9f80e290db","schema_version":"1.0","event_id":"sha256:0fe187932c5498b3b9bb96a7b292543b1524c0be1f13c12ea2882b9f80e290db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CH2JSDHCQ6EYWJCFG7DLAGI23Q/bundle.json","state_url":"https://pith.science/pith/CH2JSDHCQ6EYWJCFG7DLAGI23Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CH2JSDHCQ6EYWJCFG7DLAGI23Q/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":"2026-08-06T07:20:26Z","links":{"resolver":"https://pith.science/pith/CH2JSDHCQ6EYWJCFG7DLAGI23Q","bundle":"https://pith.science/pith/CH2JSDHCQ6EYWJCFG7DLAGI23Q/bundle.json","state":"https://pith.science/pith/CH2JSDHCQ6EYWJCFG7DLAGI23Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CH2JSDHCQ6EYWJCFG7DLAGI23Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CH2JSDHCQ6EYWJCFG7DLAGI23Q","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":"235c9ffdaeea6dd0ec8599439ad7994c1795b800f6d22b9c18bc49376591c63b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T17:58:03Z","title_canon_sha256":"786b7b2a52651e19959c3fce673ad3352903eb57c351da9ee9d9a6fd814284e2"},"schema_version":"1.0","source":{"id":"2505.14674","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14674","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14674v1","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14674","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"pith_short_12","alias_value":"CH2JSDHCQ6EY","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"pith_short_16","alias_value":"CH2JSDHCQ6EYWJCF","created_at":"2026-07-05T11:06:17Z"},{"alias_kind":"pith_short_8","alias_value":"CH2JSDHC","created_at":"2026-07-05T11:06:17Z"}],"graph_snapshots":[{"event_id":"sha256:0fe187932c5498b3b9bb96a7b292543b1524c0be1f13c12ea2882b9f80e290db","target":"graph","created_at":"2026-07-05T11:06:17Z","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/2505.14674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward models play a critical role in guiding large language models toward outputs that align with human expectations. However, an open challenge remains in effectively utilizing test-time compute to enhance reward model performance. In this work, we introduce Reward Reasoning Models (RRMs), which are specifically designed to execute a deliberate reasoning process before generating final rewards. Through chain-of-thought reasoning, RRMs leverage additional test-time compute for complex queries where appropriate rewards are not immediately apparent. To develop RRMs, we implement a reinforcement","authors_text":"Furu Wei, Jiaxin Guo, Li Dong, Qingxiu Dong, Shaohan Huang, Xun Wu, Zewen Chi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T17:58:03Z","title":"Reward Reasoning Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14674","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":"sha256:758a7688fa10f836499b65bb6916342070252290569862805707c83c8d7a579b","target":"record","created_at":"2026-07-05T11:06:17Z","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":"235c9ffdaeea6dd0ec8599439ad7994c1795b800f6d22b9c18bc49376591c63b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T17:58:03Z","title_canon_sha256":"786b7b2a52651e19959c3fce673ad3352903eb57c351da9ee9d9a6fd814284e2"},"schema_version":"1.0","source":{"id":"2505.14674","kind":"arxiv","version":1}},"canonical_sha256":"11f4990ce287898b244537c6b0191adc3a84b5e437f38d90a218b424b42ca95a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11f4990ce287898b244537c6b0191adc3a84b5e437f38d90a218b424b42ca95a","first_computed_at":"2026-07-05T11:06:17.453526Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:17.453526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BymEHtGK2C41Jd9d1DcL+AAp1ZWOpzeFylETEN0L/xsnT80n2GjraDi3VbP0h/WAGfbwOZW/DodeLhUG+g1iAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:17.454048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14674","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:758a7688fa10f836499b65bb6916342070252290569862805707c83c8d7a579b","sha256:0fe187932c5498b3b9bb96a7b292543b1524c0be1f13c12ea2882b9f80e290db"],"state_sha256":"1b2dd20f95d1e1499fe43cec6cbba8622c531c9ffe347a00e73b25bfd6fad548"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tgm/rMiC3cfVvIdGmEmqoIbIJ4JpJChdg0WiDHe63XHsThIEeaO6u3uf+fnOtrGFYLBiKfh7iJOnBsnCKPv6BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:20:26.682530Z","bundle_sha256":"133706a0bfb66316f8f110be7ee2e8d9007b258ec3b43126ea8f7f590e733135"}}