{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6DLH6IIJZ6RNI4RSJSINNXGU6C","short_pith_number":"pith:6DLH6IIJ","schema_version":"1.0","canonical_sha256":"f0d67f2109cfa2d472324c90d6dcd4f0b242f061c3be7e54b7f7320fdf88ae01","source":{"kind":"arxiv","id":"2607.01830","version":1},"attestation_state":"computed","paper":{"title":"Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dazhi Fu, Jicong Fan, Jiuding Yang, Yiwen Guo","submitted_at":"2026-07-02T07:50:38Z","abstract_excerpt":"Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompose such judgments into explicit evaluation criteria, but existing annotation-free rubric generators typically rely on a single generic evaluator. As a result, they may overlook important dimensions of human preference, a failure mode we term dimensional blind spots. To address this limitation, we propose Multi-Role Rubric Generation (MRRG), a training-free and reference-free framework that elicits evaluation criteria "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.01830","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T07:50:38Z","cross_cats_sorted":[],"title_canon_sha256":"2a4a9cbcde1cdeb137e976217c5d7cfa0fd54e194848c43c76324164180ed77d","abstract_canon_sha256":"501de11502ab16fd80bc7c3ffa1381260a9dded2af9417c47def01e0503e8817"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:31.057280Z","signature_b64":"6+EFVMQ2pvp8o6GKZX67/D/RVMcszQ4maBfchmsX3wfB93O44rbKoRW/1VKl04pIcQn4ZZtbc4RRW8ORbG5FCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0d67f2109cfa2d472324c90d6dcd4f0b242f061c3be7e54b7f7320fdf88ae01","last_reissued_at":"2026-07-03T01:17:31.056902Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:31.056902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dazhi Fu, Jicong Fan, Jiuding Yang, Yiwen Guo","submitted_at":"2026-07-02T07:50:38Z","abstract_excerpt":"Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompose such judgments into explicit evaluation criteria, but existing annotation-free rubric generators typically rely on a single generic evaluator. As a result, they may overlook important dimensions of human preference, a failure mode we term dimensional blind spots. To address this limitation, we propose Multi-Role Rubric Generation (MRRG), a training-free and reference-free framework that elicits evaluation criteria "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01830","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/2607.01830/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.01830","created_at":"2026-07-03T01:17:31.056961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01830v1","created_at":"2026-07-03T01:17:31.056961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01830","created_at":"2026-07-03T01:17:31.056961+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DLH6IIJZ6RN","created_at":"2026-07-03T01:17:31.056961+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DLH6IIJZ6RNI4RS","created_at":"2026-07-03T01:17:31.056961+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DLH6IIJ","created_at":"2026-07-03T01:17:31.056961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DLH6IIJZ6RNI4RSJSINNXGU6C","json":"https://pith.science/pith/6DLH6IIJZ6RNI4RSJSINNXGU6C.json","graph_json":"https://pith.science/api/pith-number/6DLH6IIJZ6RNI4RSJSINNXGU6C/graph.json","events_json":"https://pith.science/api/pith-number/6DLH6IIJZ6RNI4RSJSINNXGU6C/events.json","paper":"https://pith.science/paper/6DLH6IIJ"},"agent_actions":{"view_html":"https://pith.science/pith/6DLH6IIJZ6RNI4RSJSINNXGU6C","download_json":"https://pith.science/pith/6DLH6IIJZ6RNI4RSJSINNXGU6C.json","view_paper":"https://pith.science/paper/6DLH6IIJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01830&json=true","fetch_graph":"https://pith.science/api/pith-number/6DLH6IIJZ6RNI4RSJSINNXGU6C/graph.json","fetch_events":"https://pith.science/api/pith-number/6DLH6IIJZ6RNI4RSJSINNXGU6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DLH6IIJZ6RNI4RSJSINNXGU6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DLH6IIJZ6RNI4RSJSINNXGU6C/action/storage_attestation","attest_author":"https://pith.science/pith/6DLH6IIJZ6RNI4RSJSINNXGU6C/action/author_attestation","sign_citation":"https://pith.science/pith/6DLH6IIJZ6RNI4RSJSINNXGU6C/action/citation_signature","submit_replication":"https://pith.science/pith/6DLH6IIJZ6RNI4RSJSINNXGU6C/action/replication_record"}},"created_at":"2026-07-03T01:17:31.056961+00:00","updated_at":"2026-07-03T01:17:31.056961+00:00"}