{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4TR6JJARK2RBIOZOHSNT7VBIZ2","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":"33d76f133bfbf492b2da063b035a1e84a5d33e8eb2b2c816cb37ca8cf18747c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-23T08:46:11Z","title_canon_sha256":"1e41e3ea3459fcc779208f7888612d6b1c8f637677689fa60ce4b2b10f1c6ce1"},"schema_version":"1.0","source":{"id":"2309.13308","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.13308","created_at":"2026-07-05T06:53:50Z"},{"alias_kind":"arxiv_version","alias_value":"2309.13308v1","created_at":"2026-07-05T06:53:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13308","created_at":"2026-07-05T06:53:50Z"},{"alias_kind":"pith_short_12","alias_value":"4TR6JJARK2RB","created_at":"2026-07-05T06:53:50Z"},{"alias_kind":"pith_short_16","alias_value":"4TR6JJARK2RBIOZO","created_at":"2026-07-05T06:53:50Z"},{"alias_kind":"pith_short_8","alias_value":"4TR6JJAR","created_at":"2026-07-05T06:53:50Z"}],"graph_snapshots":[{"event_id":"sha256:fabbfcb999097a9b23a5794a27b2c7bf42b2d8340af11b6cb957a449df0214cc","target":"graph","created_at":"2026-07-05T06:53:50Z","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/2309.13308/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) on language modeling and emergent capabilities make them a promising reference-free evaluator of natural language generation quality, and a competent alternative to human evaluation. However, hindered by the closed-source or high computational demand to host and tune, there is a lack of practice to further calibrate an off-the-shelf LLM-based evaluator towards better human alignment. In this work, we propose AutoCalibrate, a multi-stage, gradient-free approach to automatically calibrate and align an LLM-based evaluator toward human preference","authors_text":"Feng Sun, Furu Wei, Haizhen Huang, Qi Zhang, Shaohan Huang, Tianchi Yang, Weiwei Deng, Yuxuan Liu, Zihan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-23T08:46:11Z","title":"Calibrating LLM-Based Evaluator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13308","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:bfdd54cf5ab64f8cfa1ebd08ebcad0a350f5531ff7b59ddaad6f71069314dc65","target":"record","created_at":"2026-07-05T06:53:50Z","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":"33d76f133bfbf492b2da063b035a1e84a5d33e8eb2b2c816cb37ca8cf18747c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-23T08:46:11Z","title_canon_sha256":"1e41e3ea3459fcc779208f7888612d6b1c8f637677689fa60ce4b2b10f1c6ce1"},"schema_version":"1.0","source":{"id":"2309.13308","kind":"arxiv","version":1}},"canonical_sha256":"e4e3e4a41156a2143b2e3c9b3fd428cea3c0e5ff4983b14878e936988085db7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4e3e4a41156a2143b2e3c9b3fd428cea3c0e5ff4983b14878e936988085db7b","first_computed_at":"2026-07-05T06:53:50.083645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:50.083645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2sm+NP3iv/B4TJy7u7B9TUXukpXIYxE0KpepIKMRI8OuF+37Ld4qTEIE0zAGnsiZhQ8gedgM4sKbQtPxuWB+Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:50.084156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.13308","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfdd54cf5ab64f8cfa1ebd08ebcad0a350f5531ff7b59ddaad6f71069314dc65","sha256:fabbfcb999097a9b23a5794a27b2c7bf42b2d8340af11b6cb957a449df0214cc"],"state_sha256":"d8719c9b09b506acd5ef68228a0ff6a9d6945f563c7c54c6cc66fdeac9c9b023"}