{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LQJIKFIBAABI5MW4EPXG35EBE6","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":"b973b0370e81eaba5945dba11167593162a51412868e0f17340b5e8f78697813","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-13T15:31:42Z","title_canon_sha256":"da23c475d7d3238b95daef93fc96d3b004dbb18a01703d86fa44d07fe32f3719"},"schema_version":"1.0","source":{"id":"2601.08654","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.08654","created_at":"2026-05-29T00:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2601.08654v2","created_at":"2026-05-29T00:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.08654","created_at":"2026-05-29T00:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"LQJIKFIBAABI","created_at":"2026-05-29T00:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"LQJIKFIBAABI5MW4","created_at":"2026-05-29T00:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"LQJIKFIB","created_at":"2026-05-29T00:04:12Z"}],"graph_snapshots":[{"event_id":"sha256:40be9217825945e496275c9c91b193db808236e730f3ea102fd408474cc3b646","target":"graph","created_at":"2026-05-29T00:04:12Z","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/2601.08654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rubric-based text evaluation increasingly uses large language models (LLMs) as scalable judges, but aligning frozen black-box models with human scoring standards remains challenging. We formulate this challenge as a criteria-transfer problem: the goal is not merely to prompt an LLM to assign a score, but to transfer human rubric intent into a stable, auditable, and human-aligned scoring protocol. We identify three recurring failure modes in LLM-based rubric scoring: rubric execution drift, unverifiable score attribution, and human-scale misalignment. To address these failure modes, we introduc","authors_text":"Bolin Shen, Huaiyuan Yao, Hua Wei, Wanpeng Xu, Yihan Hong, Yushun Dong","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-13T15:31:42Z","title":"From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.08654","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:e4e7fa34b7799719231d6d80789cb384fad867312f59923852fd113f3393234b","target":"record","created_at":"2026-05-29T00:04:12Z","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":"b973b0370e81eaba5945dba11167593162a51412868e0f17340b5e8f78697813","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-13T15:31:42Z","title_canon_sha256":"da23c475d7d3238b95daef93fc96d3b004dbb18a01703d86fa44d07fe32f3719"},"schema_version":"1.0","source":{"id":"2601.08654","kind":"arxiv","version":2}},"canonical_sha256":"5c1285150100028eb2dc23ee6df48127b4e4088ba1d03a4809913fa9d0c1c514","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c1285150100028eb2dc23ee6df48127b4e4088ba1d03a4809913fa9d0c1c514","first_computed_at":"2026-05-29T00:04:12.738007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T00:04:12.738007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HmX522MdV5lW54ByUepLDWxImXmQSDTKVBJ1rtJBRCcH9kbk2EmzbEkcRTpntaR4PstFkX3wUcIl5qBXE7T1Ag==","signature_status":"signed_v1","signed_at":"2026-05-29T00:04:12.738726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.08654","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4e7fa34b7799719231d6d80789cb384fad867312f59923852fd113f3393234b","sha256:40be9217825945e496275c9c91b193db808236e730f3ea102fd408474cc3b646"],"state_sha256":"8702c7b601290db2b0f3741d099be735b61db75729241a2b68fce88719a42441"}