{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2RJ47KJE7O2CQU7JXZXFDSIDYY","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":"5b44aacb6422fffed03c4faad2b552cc1c22a8ebb80229a6902c703ad867b3ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T15:01:33Z","title_canon_sha256":"47c9949f6050b3a15a6900b5c6e3cad4770030b1829819f52f44740ec4c15cb6"},"schema_version":"1.0","source":{"id":"2607.15092","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15092","created_at":"2026-07-17T01:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15092v1","created_at":"2026-07-17T01:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15092","created_at":"2026-07-17T01:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"2RJ47KJE7O2C","created_at":"2026-07-17T01:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"2RJ47KJE7O2CQU7J","created_at":"2026-07-17T01:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"2RJ47KJE","created_at":"2026-07-17T01:22:09Z"}],"graph_snapshots":[{"event_id":"sha256:1d529b23fcc3b113edd37a23b249c2e7d5ec3aa9697bba99342fcdeeb7cabdbb","target":"graph","created_at":"2026-07-17T01:22:09Z","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/2607.15092/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rubrics provide structured, fine-grained signals for training and evaluating large language models (LLMs). Yet reliable query-specific rubrics are difficult to construct. Existing approaches often derive supervision from human-written rubrics, preference data, or sampled responses. Direct query-to-rubric generation avoids these resources, but provides no explicit check that a plausible rubric is useful. Such a rubric may fail to distinguish answer quality, reward an optional style, or penalize a valid alternative strategy. We introduce Rubrics on Trial, a query-only framework that evolves a ru","authors_text":"Haocheng Yang, Hao Wang, Haoxuan Li, Licheng Pan, Xiaoxi Li, Yuan Lu, Zhichao Chen, Zhiheng Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T15:01:33Z","title":"Rubrics on Trial: Evolving Rubrics from a Single Query via Synthetic Pairwise Evidence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15092","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:f4a0e9a00b618538831f67aadb2a05b9df5f1fcfbe373f7662e64ef71a5c29b2","target":"record","created_at":"2026-07-17T01:22:09Z","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":"5b44aacb6422fffed03c4faad2b552cc1c22a8ebb80229a6902c703ad867b3ac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T15:01:33Z","title_canon_sha256":"47c9949f6050b3a15a6900b5c6e3cad4770030b1829819f52f44740ec4c15cb6"},"schema_version":"1.0","source":{"id":"2607.15092","kind":"arxiv","version":1}},"canonical_sha256":"d453cfa924fbb42853e9be6e51c903c608a3045ad082bee9fa3f635a5289ab34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d453cfa924fbb42853e9be6e51c903c608a3045ad082bee9fa3f635a5289ab34","first_computed_at":"2026-07-17T01:22:09.065395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:22:09.065395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JyUm1J5BjjzBy2JibYmm5GB5xQKrfe38j8zHXbmXHWP45TQSwlu+YjF4DhOIrrpmuMfop9TkaPMM4zmR09JZAQ==","signature_status":"signed_v1","signed_at":"2026-07-17T01:22:09.066243Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15092","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4a0e9a00b618538831f67aadb2a05b9df5f1fcfbe373f7662e64ef71a5c29b2","sha256:1d529b23fcc3b113edd37a23b249c2e7d5ec3aa9697bba99342fcdeeb7cabdbb"],"state_sha256":"58a9005cb48ecffb67d57f7053d950c3636c784d9322c85bba1e105d1f5cb55e"}