{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TKDZMPM5FMDA2JXSVXPARFAHM4","short_pith_number":"pith:TKDZMPM5","schema_version":"1.0","canonical_sha256":"9a87963d9d2b060d26f2adde0894076726b76fff27187c753b8d08570c6f24a9","source":{"kind":"arxiv","id":"2305.14770","version":6},"attestation_state":"computed","paper":{"title":"Using Natural Language Explanations to Rescale Human Judgments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Greg Durrett, Jifan Chen, Junyi Jessy Li, Manya Wadhwa","submitted_at":"2023-05-24T06:19:14Z","abstract_excerpt":"The rise of large language models (LLMs) has brought a critical need for high-quality human-labeled data, particularly for processes like human feedback and evaluation. A common practice is to label data via consensus annotation over human judgments. However, annotators' judgments for subjective tasks can differ in many ways: they may reflect different qualitative judgments about an example, and they may be mapped to a labeling scheme in different ways. We show that these nuances can be captured by natural language explanations, and propose a method to rescale ordinal annotations and explanati"},"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":"2305.14770","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T06:19:14Z","cross_cats_sorted":[],"title_canon_sha256":"7a6acbf47846d672fe381489e688c31a887f59d97a655da897b9935ddca30303","abstract_canon_sha256":"b6eef9a84afeb11119d5151bf9401362a833e30f65d61e8df1b952792508e7bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:00.508517Z","signature_b64":"u1LGxfjABi6mnkiQfEubdC6eCuG4uqW8aeDiw/11N23jb8hMp8IB/hUpestawnHUWNRu26da6guDgMkL4oIcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a87963d9d2b060d26f2adde0894076726b76fff27187c753b8d08570c6f24a9","last_reissued_at":"2026-07-05T11:24:00.507993Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:00.507993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Natural Language Explanations to Rescale Human Judgments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Greg Durrett, Jifan Chen, Junyi Jessy Li, Manya Wadhwa","submitted_at":"2023-05-24T06:19:14Z","abstract_excerpt":"The rise of large language models (LLMs) has brought a critical need for high-quality human-labeled data, particularly for processes like human feedback and evaluation. A common practice is to label data via consensus annotation over human judgments. However, annotators' judgments for subjective tasks can differ in many ways: they may reflect different qualitative judgments about an example, and they may be mapped to a labeling scheme in different ways. We show that these nuances can be captured by natural language explanations, and propose a method to rescale ordinal annotations and explanati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14770","kind":"arxiv","version":6},"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/2305.14770/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":"2305.14770","created_at":"2026-07-05T11:24:00.508062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14770v6","created_at":"2026-07-05T11:24:00.508062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14770","created_at":"2026-07-05T11:24:00.508062+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKDZMPM5FMDA","created_at":"2026-07-05T11:24:00.508062+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKDZMPM5FMDA2JXS","created_at":"2026-07-05T11:24:00.508062+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKDZMPM5","created_at":"2026-07-05T11:24:00.508062+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/TKDZMPM5FMDA2JXSVXPARFAHM4","json":"https://pith.science/pith/TKDZMPM5FMDA2JXSVXPARFAHM4.json","graph_json":"https://pith.science/api/pith-number/TKDZMPM5FMDA2JXSVXPARFAHM4/graph.json","events_json":"https://pith.science/api/pith-number/TKDZMPM5FMDA2JXSVXPARFAHM4/events.json","paper":"https://pith.science/paper/TKDZMPM5"},"agent_actions":{"view_html":"https://pith.science/pith/TKDZMPM5FMDA2JXSVXPARFAHM4","download_json":"https://pith.science/pith/TKDZMPM5FMDA2JXSVXPARFAHM4.json","view_paper":"https://pith.science/paper/TKDZMPM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14770&json=true","fetch_graph":"https://pith.science/api/pith-number/TKDZMPM5FMDA2JXSVXPARFAHM4/graph.json","fetch_events":"https://pith.science/api/pith-number/TKDZMPM5FMDA2JXSVXPARFAHM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKDZMPM5FMDA2JXSVXPARFAHM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKDZMPM5FMDA2JXSVXPARFAHM4/action/storage_attestation","attest_author":"https://pith.science/pith/TKDZMPM5FMDA2JXSVXPARFAHM4/action/author_attestation","sign_citation":"https://pith.science/pith/TKDZMPM5FMDA2JXSVXPARFAHM4/action/citation_signature","submit_replication":"https://pith.science/pith/TKDZMPM5FMDA2JXSVXPARFAHM4/action/replication_record"}},"created_at":"2026-07-05T11:24:00.508062+00:00","updated_at":"2026-07-05T11:24:00.508062+00:00"}