{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VGPNUICV2AGLHZN5QS5V7PTEPP","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":"5a9181f55cc9976fedb59ee0e82410e08fc6e03ea8bd9743b416f3c26fd3ac24","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-04-18T15:45:27Z","title_canon_sha256":"e4fc2096b96caf6d138268db8a7748a11b7c1bad00b34470936e7c5b0b1159c1"},"schema_version":"1.0","source":{"id":"2404.12272","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12272","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12272v1","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12272","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"VGPNUICV2AGL","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"VGPNUICV2AGLHZN5","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"VGPNUICV","created_at":"2026-07-05T08:09:37Z"}],"graph_snapshots":[{"event_id":"sha256:a2bd6c475a03779682a89d24e9f235dd5bd7ab4a1d4e9511f110cc8bae9b9146","target":"graph","created_at":"2026-07-05T08:09:37Z","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/2404.12272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Due to the cumbersome nature of human evaluation and limitations of code-based evaluation, Large Language Models (LLMs) are increasingly being used to assist humans in evaluating LLM outputs. Yet LLM-generated evaluators simply inherit all the problems of the LLMs they evaluate, requiring further human validation. We present a mixed-initiative approach to ``validate the validators'' -- aligning LLM-generated evaluation functions (be it prompts or code) with human requirements. Our interface, EvalGen, provides automated assistance to users in generating evaluation criteria and implementing asse","authors_text":"Aditya G. Parameswaran, Bj\\\"orn Hartmann, Ian Arawjo, J.D. Zamfirescu-Pereira, Shreya Shankar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-04-18T15:45:27Z","title":"Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12272","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:f039d3d99cad90384343d2a354f4f25a1cb0f509b2fdd0c44967d79968edc428","target":"record","created_at":"2026-07-05T08:09:37Z","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":"5a9181f55cc9976fedb59ee0e82410e08fc6e03ea8bd9743b416f3c26fd3ac24","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-04-18T15:45:27Z","title_canon_sha256":"e4fc2096b96caf6d138268db8a7748a11b7c1bad00b34470936e7c5b0b1159c1"},"schema_version":"1.0","source":{"id":"2404.12272","kind":"arxiv","version":1}},"canonical_sha256":"a99eda2055d00cb3e5bd84bb5fbe647bd02e534ab599d5b6bedbc838a0bff16a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a99eda2055d00cb3e5bd84bb5fbe647bd02e534ab599d5b6bedbc838a0bff16a","first_computed_at":"2026-07-05T08:09:37.811541Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:37.811541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XLVbykWXONCA6rY0DeBADck5SyT6CVB36FPWmokDQf5dDkdLC7ZtsiTpaFJRmGClMwRbgolT9Z6PCGM9zD9kAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:37.812016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.12272","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f039d3d99cad90384343d2a354f4f25a1cb0f509b2fdd0c44967d79968edc428","sha256:a2bd6c475a03779682a89d24e9f235dd5bd7ab4a1d4e9511f110cc8bae9b9146"],"state_sha256":"cbdac3b12f7260d8d7acd6e5bc0805029b22304c319bfe484d1c8b069963fcd4"}