{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R7Q7FDIE4HGADGUYMZIIBEF2BN","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":"879fec9d6b33d1f78ef24de28a3372fbee92e7c60c6f18dd5f7ac894cd185ab8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T04:57:01Z","title_canon_sha256":"f0629a056389b308dcdcf7131be8fc4df7312c7249680b8d4f0774cd9891ed5c"},"schema_version":"1.0","source":{"id":"2501.00274","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00274","created_at":"2026-07-05T09:55:42Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00274v1","created_at":"2026-07-05T09:55:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00274","created_at":"2026-07-05T09:55:42Z"},{"alias_kind":"pith_short_12","alias_value":"R7Q7FDIE4HGA","created_at":"2026-07-05T09:55:42Z"},{"alias_kind":"pith_short_16","alias_value":"R7Q7FDIE4HGADGUY","created_at":"2026-07-05T09:55:42Z"},{"alias_kind":"pith_short_8","alias_value":"R7Q7FDIE","created_at":"2026-07-05T09:55:42Z"}],"graph_snapshots":[{"event_id":"sha256:e2d7cd0fe614418dbe18cba89897897f8d969b9ac6bb813bcd6732ecb15ca667","target":"graph","created_at":"2026-07-05T09:55:42Z","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/2501.00274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces a framework for the automated evaluation of natural language texts. A manually constructed rubric describes how to assess multiple dimensions of interest. To evaluate a text, a large language model (LLM) is prompted with each rubric question and produces a distribution over potential responses. The LLM predictions often fail to agree well with human judges -- indeed, the humans do not fully agree with one another. However, the multiple LLM distributions can be $\\textit{combined}$ to $\\textit{predict}$ each human judge's annotations on all questions, including a summary qu","authors_text":"Benjamin Van Durme, Chris Kedzie, Corby Rosset, Helia Hashemi, Jason Eisner","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T04:57:01Z","title":"LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00274","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":"sha256:8fbd2eaa0f8b2302dd5ebad1793e8c7b7e230002263164cf9a5f1d2c3702acad","target":"record","created_at":"2026-07-05T09:55:42Z","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":"879fec9d6b33d1f78ef24de28a3372fbee92e7c60c6f18dd5f7ac894cd185ab8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-31T04:57:01Z","title_canon_sha256":"f0629a056389b308dcdcf7131be8fc4df7312c7249680b8d4f0774cd9891ed5c"},"schema_version":"1.0","source":{"id":"2501.00274","kind":"arxiv","version":1}},"canonical_sha256":"8fe1f28d04e1cc019a9866508090ba0b48f3cf1607590cdd49cce74315cda63e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fe1f28d04e1cc019a9866508090ba0b48f3cf1607590cdd49cce74315cda63e","first_computed_at":"2026-07-05T09:55:42.083267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:42.083267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L+TwB7D4Osh7g3Rb4bKmBfuve67hUfolWQVOzr6+aEowo3E/EucT21FqMYUTclaoCFQsdWtSOcctacGL3u+IBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:42.083878Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00274","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fbd2eaa0f8b2302dd5ebad1793e8c7b7e230002263164cf9a5f1d2c3702acad","sha256:e2d7cd0fe614418dbe18cba89897897f8d969b9ac6bb813bcd6732ecb15ca667"],"state_sha256":"89527f013189ba89baf36cebe3508f8e005c6c7a5e912f00843cafaa0399a08e"}