{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TZOR2QROB5IO6H5QCG7G54YKCE","short_pith_number":"pith:TZOR2QRO","schema_version":"1.0","canonical_sha256":"9e5d1d422e0f50ef1fb011be6ef30a113dbd351f63a082d23904a79f822dd9d7","source":{"kind":"arxiv","id":"2407.03479","version":1},"attestation_state":"computed","paper":{"title":"Human-Centered Design Recommendations for LLM-as-a-Judge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Elizabeth Daly, James Johnson, Martin Santillan Cooper, Michael Desmond, Qian Pan, Rahul Nair, Werner Geyer, Zahra Ashktorab","submitted_at":"2024-07-03T19:53:47Z","abstract_excerpt":"Traditional reference-based metrics, such as BLEU and ROUGE, are less effective for assessing outputs from Large Language Models (LLMs) that produce highly creative or superior-quality text, or in situations where reference outputs are unavailable. While human evaluation remains an option, it is costly and difficult to scale. Recent work using LLMs as evaluators (LLM-as-a-judge) is promising, but trust and reliability remain a significant concern. Integrating human input is crucial to ensure criteria used to evaluate are aligned with the human's intent, and evaluations are robust and consisten"},"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":"2407.03479","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2024-07-03T19:53:47Z","cross_cats_sorted":[],"title_canon_sha256":"f2007470bec7da9175592e876b3b5caae76bdb6cab81ce24f6a32e34acce1177","abstract_canon_sha256":"aac65acd1bd82f55693bb6d7019b91b474c626e7cc0922bd25d5e38a18a9684e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:55.633141Z","signature_b64":"jQgKYWvtVh/4cOPYDUXZ49DskSBQDq50k/xNOxrvb80AomFkHI9bWc3+BBEjq0wH9Q7y+8gXW49GUfHPq+ItBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e5d1d422e0f50ef1fb011be6ef30a113dbd351f63a082d23904a79f822dd9d7","last_reissued_at":"2026-07-05T08:39:55.632619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:55.632619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-Centered Design Recommendations for LLM-as-a-Judge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Elizabeth Daly, James Johnson, Martin Santillan Cooper, Michael Desmond, Qian Pan, Rahul Nair, Werner Geyer, Zahra Ashktorab","submitted_at":"2024-07-03T19:53:47Z","abstract_excerpt":"Traditional reference-based metrics, such as BLEU and ROUGE, are less effective for assessing outputs from Large Language Models (LLMs) that produce highly creative or superior-quality text, or in situations where reference outputs are unavailable. While human evaluation remains an option, it is costly and difficult to scale. Recent work using LLMs as evaluators (LLM-as-a-judge) is promising, but trust and reliability remain a significant concern. Integrating human input is crucial to ensure criteria used to evaluate are aligned with the human's intent, and evaluations are robust and consisten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03479","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/2407.03479/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":"2407.03479","created_at":"2026-07-05T08:39:55.632697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03479v1","created_at":"2026-07-05T08:39:55.632697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03479","created_at":"2026-07-05T08:39:55.632697+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZOR2QROB5IO","created_at":"2026-07-05T08:39:55.632697+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZOR2QROB5IO6H5Q","created_at":"2026-07-05T08:39:55.632697+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZOR2QRO","created_at":"2026-07-05T08:39:55.632697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10142","citing_title":"DB-3DME: From Dataset to Benchmark for Human-aligned Automatic 3D Mesh Evaluation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15503","citing_title":"Guidelines for Empirical Studies in Software Engineering involving Large Language Models","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15503","citing_title":"Guidelines for Empirical Studies in Software Engineering involving Large Language Models","ref_index":99,"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":47,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":175,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05371","citing_title":"LLM-as-Judge for Semantic Judging of Powerline Segmentation in UAV Inspection","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZOR2QROB5IO6H5QCG7G54YKCE","json":"https://pith.science/pith/TZOR2QROB5IO6H5QCG7G54YKCE.json","graph_json":"https://pith.science/api/pith-number/TZOR2QROB5IO6H5QCG7G54YKCE/graph.json","events_json":"https://pith.science/api/pith-number/TZOR2QROB5IO6H5QCG7G54YKCE/events.json","paper":"https://pith.science/paper/TZOR2QRO"},"agent_actions":{"view_html":"https://pith.science/pith/TZOR2QROB5IO6H5QCG7G54YKCE","download_json":"https://pith.science/pith/TZOR2QROB5IO6H5QCG7G54YKCE.json","view_paper":"https://pith.science/paper/TZOR2QRO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03479&json=true","fetch_graph":"https://pith.science/api/pith-number/TZOR2QROB5IO6H5QCG7G54YKCE/graph.json","fetch_events":"https://pith.science/api/pith-number/TZOR2QROB5IO6H5QCG7G54YKCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZOR2QROB5IO6H5QCG7G54YKCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZOR2QROB5IO6H5QCG7G54YKCE/action/storage_attestation","attest_author":"https://pith.science/pith/TZOR2QROB5IO6H5QCG7G54YKCE/action/author_attestation","sign_citation":"https://pith.science/pith/TZOR2QROB5IO6H5QCG7G54YKCE/action/citation_signature","submit_replication":"https://pith.science/pith/TZOR2QROB5IO6H5QCG7G54YKCE/action/replication_record"}},"created_at":"2026-07-05T08:39:55.632697+00:00","updated_at":"2026-07-05T08:39:55.632697+00:00"}