{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NFBBO4TL7SYOS7KMX4PRZ2RYU7","short_pith_number":"pith:NFBBO4TL","schema_version":"1.0","canonical_sha256":"694217726bfcb0e97d4cbf1f1cea38a7f16936ed10ec9c13149bc781c0bfa058","source":{"kind":"arxiv","id":"2606.00093","version":1},"attestation_state":"computed","paper":{"title":"Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.HC","physics.data-an"],"primary_cat":"cs.CL","authors_text":"Chris Callison-Burch, Delip Rao","submitted_at":"2026-05-25T07:31:44Z","abstract_excerpt":"Validating an LLM judge against human annotations usually means reporting several agreement statistics: accuracy, precision, recall, $F_1$, Cohen's $\\kappa$, and one or more rank correlations. A survey of 24 recent LLM-as-judge papers finds metric choice entangled with the judgment scale, tie handling, invalid outputs, and abstention handling, and those choices rarely stated. For binary criteria -- the common case in rubric-based evaluation, where each criterion is graded MET or UNMET -- most of the reported numbers are redundant: Pearson's $r$, Spearman's $\\rho$, Kendall's $\\tau_b$, the phi c"},"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":"2606.00093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T07:31:44Z","cross_cats_sorted":["cs.HC","physics.data-an"],"title_canon_sha256":"78e1cae135e4185ba867359a42d4e2e863d2184fd6bfe9e18c49eebba86d9ea1","abstract_canon_sha256":"706fa7fd9d3a60be08ece1f9d00b9c0e2fa2350e433e1c69eeb9e7895fb3b74a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T00:03:14.787695Z","signature_b64":"PymqJeajwk46c0h54wtJ+UIJPVfL8RXsncqZPA1rbS2XoIFJyQFwQbBoWNCBdW59CILo2qQqfXecvl89DlbYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"694217726bfcb0e97d4cbf1f1cea38a7f16936ed10ec9c13149bc781c0bfa058","last_reissued_at":"2026-06-02T00:03:14.787278Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T00:03:14.787278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.HC","physics.data-an"],"primary_cat":"cs.CL","authors_text":"Chris Callison-Burch, Delip Rao","submitted_at":"2026-05-25T07:31:44Z","abstract_excerpt":"Validating an LLM judge against human annotations usually means reporting several agreement statistics: accuracy, precision, recall, $F_1$, Cohen's $\\kappa$, and one or more rank correlations. A survey of 24 recent LLM-as-judge papers finds metric choice entangled with the judgment scale, tie handling, invalid outputs, and abstention handling, and those choices rarely stated. For binary criteria -- the common case in rubric-based evaluation, where each criterion is graded MET or UNMET -- most of the reported numbers are redundant: Pearson's $r$, Spearman's $\\rho$, Kendall's $\\tau_b$, the phi c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00093","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/2606.00093/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":"2606.00093","created_at":"2026-06-02T00:03:14.787341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00093v1","created_at":"2026-06-02T00:03:14.787341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00093","created_at":"2026-06-02T00:03:14.787341+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFBBO4TL7SYO","created_at":"2026-06-02T00:03:14.787341+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFBBO4TL7SYOS7KM","created_at":"2026-06-02T00:03:14.787341+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFBBO4TL","created_at":"2026-06-02T00:03:14.787341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFBBO4TL7SYOS7KMX4PRZ2RYU7","json":"https://pith.science/pith/NFBBO4TL7SYOS7KMX4PRZ2RYU7.json","graph_json":"https://pith.science/api/pith-number/NFBBO4TL7SYOS7KMX4PRZ2RYU7/graph.json","events_json":"https://pith.science/api/pith-number/NFBBO4TL7SYOS7KMX4PRZ2RYU7/events.json","paper":"https://pith.science/paper/NFBBO4TL"},"agent_actions":{"view_html":"https://pith.science/pith/NFBBO4TL7SYOS7KMX4PRZ2RYU7","download_json":"https://pith.science/pith/NFBBO4TL7SYOS7KMX4PRZ2RYU7.json","view_paper":"https://pith.science/paper/NFBBO4TL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00093&json=true","fetch_graph":"https://pith.science/api/pith-number/NFBBO4TL7SYOS7KMX4PRZ2RYU7/graph.json","fetch_events":"https://pith.science/api/pith-number/NFBBO4TL7SYOS7KMX4PRZ2RYU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFBBO4TL7SYOS7KMX4PRZ2RYU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFBBO4TL7SYOS7KMX4PRZ2RYU7/action/storage_attestation","attest_author":"https://pith.science/pith/NFBBO4TL7SYOS7KMX4PRZ2RYU7/action/author_attestation","sign_citation":"https://pith.science/pith/NFBBO4TL7SYOS7KMX4PRZ2RYU7/action/citation_signature","submit_replication":"https://pith.science/pith/NFBBO4TL7SYOS7KMX4PRZ2RYU7/action/replication_record"}},"created_at":"2026-06-02T00:03:14.787341+00:00","updated_at":"2026-06-02T00:03:14.787341+00:00"}