{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VGPNUICV2AGLHZN5QS5V7PTEPP","short_pith_number":"pith:VGPNUICV","schema_version":"1.0","canonical_sha256":"a99eda2055d00cb3e5bd84bb5fbe647bd02e534ab599d5b6bedbc838a0bff16a","source":{"kind":"arxiv","id":"2404.12272","version":1},"attestation_state":"computed","paper":{"title":"Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Aditya G. Parameswaran, Bj\\\"orn Hartmann, Ian Arawjo, J.D. Zamfirescu-Pereira, Shreya Shankar","submitted_at":"2024-04-18T15:45:27Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.12272","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2024-04-18T15:45:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e4fc2096b96caf6d138268db8a7748a11b7c1bad00b34470936e7c5b0b1159c1","abstract_canon_sha256":"5a9181f55cc9976fedb59ee0e82410e08fc6e03ea8bd9743b416f3c26fd3ac24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:37.812016Z","signature_b64":"XLVbykWXONCA6rY0DeBADck5SyT6CVB36FPWmokDQf5dDkdLC7ZtsiTpaFJRmGClMwRbgolT9Z6PCGM9zD9kAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a99eda2055d00cb3e5bd84bb5fbe647bd02e534ab599d5b6bedbc838a0bff16a","last_reissued_at":"2026-07-05T08:09:37.811541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:37.811541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Aditya G. Parameswaran, Bj\\\"orn Hartmann, Ian Arawjo, J.D. Zamfirescu-Pereira, Shreya Shankar","submitted_at":"2024-04-18T15:45:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12272","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.12272/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.12272","created_at":"2026-07-05T08:09:37.811619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.12272v1","created_at":"2026-07-05T08:09:37.811619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12272","created_at":"2026-07-05T08:09:37.811619+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGPNUICV2AGL","created_at":"2026-07-05T08:09:37.811619+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGPNUICV2AGLHZN5","created_at":"2026-07-05T08:09:37.811619+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGPNUICV","created_at":"2026-07-05T08:09:37.811619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26185","citing_title":"Necessary but Not Sufficient: Temperature Control and Reproducibility in LLM-as-Judge Safety Evaluations","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04037","citing_title":"Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certification","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02080","citing_title":"Agentic-J: An AI Agent for Biological Microscopy Image Analysis","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16304","citing_title":"Results-Actionability Gap: Understanding How Practitioners Evaluate LLM Products in the Wild","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23178","citing_title":"Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipelines","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10545","citing_title":"Enhanced Self-Learning with Epistemologically-Informed LLM Dialogue","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGPNUICV2AGLHZN5QS5V7PTEPP","json":"https://pith.science/pith/VGPNUICV2AGLHZN5QS5V7PTEPP.json","graph_json":"https://pith.science/api/pith-number/VGPNUICV2AGLHZN5QS5V7PTEPP/graph.json","events_json":"https://pith.science/api/pith-number/VGPNUICV2AGLHZN5QS5V7PTEPP/events.json","paper":"https://pith.science/paper/VGPNUICV"},"agent_actions":{"view_html":"https://pith.science/pith/VGPNUICV2AGLHZN5QS5V7PTEPP","download_json":"https://pith.science/pith/VGPNUICV2AGLHZN5QS5V7PTEPP.json","view_paper":"https://pith.science/paper/VGPNUICV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.12272&json=true","fetch_graph":"https://pith.science/api/pith-number/VGPNUICV2AGLHZN5QS5V7PTEPP/graph.json","fetch_events":"https://pith.science/api/pith-number/VGPNUICV2AGLHZN5QS5V7PTEPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGPNUICV2AGLHZN5QS5V7PTEPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGPNUICV2AGLHZN5QS5V7PTEPP/action/storage_attestation","attest_author":"https://pith.science/pith/VGPNUICV2AGLHZN5QS5V7PTEPP/action/author_attestation","sign_citation":"https://pith.science/pith/VGPNUICV2AGLHZN5QS5V7PTEPP/action/citation_signature","submit_replication":"https://pith.science/pith/VGPNUICV2AGLHZN5QS5V7PTEPP/action/replication_record"}},"created_at":"2026-07-05T08:09:37.811619+00:00","updated_at":"2026-07-05T08:09:37.811619+00:00"}