{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FUTCSY4G7NVHHLSX765QHQDBTS","short_pith_number":"pith:FUTCSY4G","schema_version":"1.0","canonical_sha256":"2d26296386fb6a73ae57ffbb03c0619c90d585b16fc4bb9d3cc55142e694ccae","source":{"kind":"arxiv","id":"2509.05440","version":1},"attestation_state":"computed","paper":{"title":"Direct-Scoring NLG Evaluators Can Use Pairwise Comparisons Too","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander Shelton, Ashton Williamson, Logan Lawrence","submitted_at":"2025-09-05T18:48:34Z","abstract_excerpt":"As large-language models have been increasingly used as automatic raters for evaluating free-form content, including document summarization, dialog, and story generation, work has been dedicated to evaluating such models by measuring their correlations with human judgment. For \\textit{sample-level} performance, methods which operate by using pairwise comparisons between machine-generated text perform well but often lack the ability to assign absolute scores to individual summaries, an ability crucial for use cases that require thresholding. In this work, we propose a direct-scoring method whic"},"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":"2509.05440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-05T18:48:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ee65bc5467095b1744dcb18431de2a15706ac2cb3dddbb5bb9360d89530f5dd3","abstract_canon_sha256":"70d12c511d8111326c0f2ef2b0cf57b37a633b18aae213ed2a7a0158c46c1bb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:47.649188Z","signature_b64":"5wNTuReiDsnpZoBwVPXw3qb/QoH81es1ldLga5l1KwnY+zbVxiFgUQRqjOb478Y24VLdcMrmZz9RHakkbl7aDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d26296386fb6a73ae57ffbb03c0619c90d585b16fc4bb9d3cc55142e694ccae","last_reissued_at":"2026-07-05T12:05:47.648591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:47.648591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Direct-Scoring NLG Evaluators Can Use Pairwise Comparisons Too","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander Shelton, Ashton Williamson, Logan Lawrence","submitted_at":"2025-09-05T18:48:34Z","abstract_excerpt":"As large-language models have been increasingly used as automatic raters for evaluating free-form content, including document summarization, dialog, and story generation, work has been dedicated to evaluating such models by measuring their correlations with human judgment. For \\textit{sample-level} performance, methods which operate by using pairwise comparisons between machine-generated text perform well but often lack the ability to assign absolute scores to individual summaries, an ability crucial for use cases that require thresholding. In this work, we propose a direct-scoring method whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05440","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/2509.05440/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":"2509.05440","created_at":"2026-07-05T12:05:47.648702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05440v1","created_at":"2026-07-05T12:05:47.648702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05440","created_at":"2026-07-05T12:05:47.648702+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUTCSY4G7NVH","created_at":"2026-07-05T12:05:47.648702+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUTCSY4G7NVHHLSX","created_at":"2026-07-05T12:05:47.648702+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUTCSY4G","created_at":"2026-07-05T12:05:47.648702+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/FUTCSY4G7NVHHLSX765QHQDBTS","json":"https://pith.science/pith/FUTCSY4G7NVHHLSX765QHQDBTS.json","graph_json":"https://pith.science/api/pith-number/FUTCSY4G7NVHHLSX765QHQDBTS/graph.json","events_json":"https://pith.science/api/pith-number/FUTCSY4G7NVHHLSX765QHQDBTS/events.json","paper":"https://pith.science/paper/FUTCSY4G"},"agent_actions":{"view_html":"https://pith.science/pith/FUTCSY4G7NVHHLSX765QHQDBTS","download_json":"https://pith.science/pith/FUTCSY4G7NVHHLSX765QHQDBTS.json","view_paper":"https://pith.science/paper/FUTCSY4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05440&json=true","fetch_graph":"https://pith.science/api/pith-number/FUTCSY4G7NVHHLSX765QHQDBTS/graph.json","fetch_events":"https://pith.science/api/pith-number/FUTCSY4G7NVHHLSX765QHQDBTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUTCSY4G7NVHHLSX765QHQDBTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUTCSY4G7NVHHLSX765QHQDBTS/action/storage_attestation","attest_author":"https://pith.science/pith/FUTCSY4G7NVHHLSX765QHQDBTS/action/author_attestation","sign_citation":"https://pith.science/pith/FUTCSY4G7NVHHLSX765QHQDBTS/action/citation_signature","submit_replication":"https://pith.science/pith/FUTCSY4G7NVHHLSX765QHQDBTS/action/replication_record"}},"created_at":"2026-07-05T12:05:47.648702+00:00","updated_at":"2026-07-05T12:05:47.648702+00:00"}