{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GXJBDGRCVYDDGIGL5PFCKYRCSO","short_pith_number":"pith:GXJBDGRC","canonical_record":{"source":{"id":"2412.13746","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T11:28:05Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"c31efb8f6d88272e78f08fe603a94d80ff5b86f180528a9b3749af7d4ef6fb0e","abstract_canon_sha256":"3a12a6b7eb2c0b391911d68dc20633b47a7a4849ed669335425a5375f669564c"},"schema_version":"1.0"},"canonical_sha256":"35d2119a22ae063320cbebca25622293aa10f97d3dce32aaa60787cb2423a8c4","source":{"kind":"arxiv","id":"2412.13746","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13746","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13746v1","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13746","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"pith_short_12","alias_value":"GXJBDGRCVYDD","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"pith_short_16","alias_value":"GXJBDGRCVYDDGIGL","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"pith_short_8","alias_value":"GXJBDGRC","created_at":"2026-07-05T09:51:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GXJBDGRCVYDDGIGL5PFCKYRCSO","target":"record","payload":{"canonical_record":{"source":{"id":"2412.13746","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T11:28:05Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"c31efb8f6d88272e78f08fe603a94d80ff5b86f180528a9b3749af7d4ef6fb0e","abstract_canon_sha256":"3a12a6b7eb2c0b391911d68dc20633b47a7a4849ed669335425a5375f669564c"},"schema_version":"1.0"},"canonical_sha256":"35d2119a22ae063320cbebca25622293aa10f97d3dce32aaa60787cb2423a8c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:07.649123Z","signature_b64":"so16NaLunBDpGZYSdTHA957Rb6UhiKCODZ9+Z9xpQyHu+ogfM/q9ixDtIR8tGiPSJyhXBldgPC2LtwWAuC0HBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35d2119a22ae063320cbebca25622293aa10f97d3dce32aaa60787cb2423a8c4","last_reissued_at":"2026-07-05T09:51:07.648513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:07.648513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.13746","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":"2026-07-05T09:51:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CCevE6ggBx2v1xkr5CyvhaQ1G8/bKgSiLWzJ3WmpqUWSGZQsarlkx7TwNfgRzF4dy/pe8SNXu1f5/R17HYbRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:25:11.691301Z"},"content_sha256":"f48281e6acef590b2d11a65f6f3b1f7f40790bd2592b331c50178fd1600d98ab","schema_version":"1.0","event_id":"sha256:f48281e6acef590b2d11a65f6f3b1f7f40790bd2592b331c50178fd1600d98ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GXJBDGRCVYDDGIGL5PFCKYRCSO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Hongbang Yuan, Jun Zhao, Kang Liu, Pengfei Cao, Tianyi Men, Yubo Chen, Zhuoran Jin","submitted_at":"2024-12-18T11:28:05Z","abstract_excerpt":"Despite the significant progress made by existing retrieval augmented language models (RALMs) in providing trustworthy responses and grounding in reliable sources, they often overlook effective alignment with human preferences. In the alignment process, reward models (RMs) act as a crucial proxy for human values to guide optimization. However, it remains unclear how to evaluate and select a reliable RM for preference alignment in RALMs. To this end, we propose RAG-RewardBench, the first benchmark for evaluating RMs in RAG settings. First, we design four crucial and challenging RAG-specific sce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13746","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/2412.13746/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":"2026-07-05T09:51:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lasENF7JdULoZ5jYCUVeZaT3E84dfsdsXnTMofrUhcxjwWvBTFX9pVzs2z+7kDDeXS3wUSPBTVVDAE3Y/Fy1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:25:11.693004Z"},"content_sha256":"caa2df3f40f01648bc9ea8aefd409efb16b98e0a8b269f2408f22632f1c336c9","schema_version":"1.0","event_id":"sha256:caa2df3f40f01648bc9ea8aefd409efb16b98e0a8b269f2408f22632f1c336c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GXJBDGRCVYDDGIGL5PFCKYRCSO/bundle.json","state_url":"https://pith.science/pith/GXJBDGRCVYDDGIGL5PFCKYRCSO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GXJBDGRCVYDDGIGL5PFCKYRCSO/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":"2026-08-08T11:25:11Z","links":{"resolver":"https://pith.science/pith/GXJBDGRCVYDDGIGL5PFCKYRCSO","bundle":"https://pith.science/pith/GXJBDGRCVYDDGIGL5PFCKYRCSO/bundle.json","state":"https://pith.science/pith/GXJBDGRCVYDDGIGL5PFCKYRCSO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GXJBDGRCVYDDGIGL5PFCKYRCSO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GXJBDGRCVYDDGIGL5PFCKYRCSO","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":"3a12a6b7eb2c0b391911d68dc20633b47a7a4849ed669335425a5375f669564c","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T11:28:05Z","title_canon_sha256":"c31efb8f6d88272e78f08fe603a94d80ff5b86f180528a9b3749af7d4ef6fb0e"},"schema_version":"1.0","source":{"id":"2412.13746","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13746","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13746v1","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13746","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"pith_short_12","alias_value":"GXJBDGRCVYDD","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"pith_short_16","alias_value":"GXJBDGRCVYDDGIGL","created_at":"2026-07-05T09:51:07Z"},{"alias_kind":"pith_short_8","alias_value":"GXJBDGRC","created_at":"2026-07-05T09:51:07Z"}],"graph_snapshots":[{"event_id":"sha256:caa2df3f40f01648bc9ea8aefd409efb16b98e0a8b269f2408f22632f1c336c9","target":"graph","created_at":"2026-07-05T09:51:07Z","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/2412.13746/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the significant progress made by existing retrieval augmented language models (RALMs) in providing trustworthy responses and grounding in reliable sources, they often overlook effective alignment with human preferences. In the alignment process, reward models (RMs) act as a crucial proxy for human values to guide optimization. However, it remains unclear how to evaluate and select a reliable RM for preference alignment in RALMs. To this end, we propose RAG-RewardBench, the first benchmark for evaluating RMs in RAG settings. First, we design four crucial and challenging RAG-specific sce","authors_text":"Hongbang Yuan, Jun Zhao, Kang Liu, Pengfei Cao, Tianyi Men, Yubo Chen, Zhuoran Jin","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T11:28:05Z","title":"RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13746","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:f48281e6acef590b2d11a65f6f3b1f7f40790bd2592b331c50178fd1600d98ab","target":"record","created_at":"2026-07-05T09:51:07Z","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":"3a12a6b7eb2c0b391911d68dc20633b47a7a4849ed669335425a5375f669564c","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T11:28:05Z","title_canon_sha256":"c31efb8f6d88272e78f08fe603a94d80ff5b86f180528a9b3749af7d4ef6fb0e"},"schema_version":"1.0","source":{"id":"2412.13746","kind":"arxiv","version":1}},"canonical_sha256":"35d2119a22ae063320cbebca25622293aa10f97d3dce32aaa60787cb2423a8c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35d2119a22ae063320cbebca25622293aa10f97d3dce32aaa60787cb2423a8c4","first_computed_at":"2026-07-05T09:51:07.648513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:07.648513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"so16NaLunBDpGZYSdTHA957Rb6UhiKCODZ9+Z9xpQyHu+ogfM/q9ixDtIR8tGiPSJyhXBldgPC2LtwWAuC0HBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:07.649123Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13746","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f48281e6acef590b2d11a65f6f3b1f7f40790bd2592b331c50178fd1600d98ab","sha256:caa2df3f40f01648bc9ea8aefd409efb16b98e0a8b269f2408f22632f1c336c9"],"state_sha256":"1c5b2d0f1831650f300c52a6f8fa0d2eeb37871d9a022f04b3626a5c7fabbea3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z8r1hDVSj8lV6+h2qMTuXTSYDCRO9XxcEIsgGmipc8nBjDEgyxuUuVo/Hz3B5I3vM8GRAsrI9xJLbwyNhH6PDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:25:11.710542Z","bundle_sha256":"36a5493843a2733301a2d31ccd4401f17e34535a3591cf67d8e8e5679ebda2ca"}}