{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CQWTLMTXVSOBY2L2YIXRQBR4I4","short_pith_number":"pith:CQWTLMTX","schema_version":"1.0","canonical_sha256":"142d35b277ac9c1c697ac22f18063c4711af5549f9f15ef34a059e62ad4eeb5c","source":{"kind":"arxiv","id":"2112.07475","version":2},"attestation_state":"computed","paper":{"title":"Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bertie Vidgen, Dirk Hovy, Janet B. Pierrehumbert, Paul R\\\"ottger","submitted_at":"2021-12-14T15:38:22Z","abstract_excerpt":"Labelled data is the foundation of most natural language processing tasks. However, labelling data is difficult and there often are diverse valid beliefs about what the correct data labels should be. So far, dataset creators have acknowledged annotator subjectivity, but rarely actively managed it in the annotation process. This has led to partly-subjective datasets that fail to serve a clear downstream use. To address this issue, we propose two contrasting paradigms for data annotation. The descriptive paradigm encourages annotator subjectivity, whereas the prescriptive paradigm discourages it"},"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":"2112.07475","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-14T15:38:22Z","cross_cats_sorted":[],"title_canon_sha256":"91e2908376082416b6e22bfca907a665a743f17d5980c9f930a43b32cc28afff","abstract_canon_sha256":"6571bf4998ce567421f2ff648949b0485305c21cdce408173184e13e2ec6358a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:18:50.034505Z","signature_b64":"FuzlupharnS+4a4aX/En7BnNdereOLJbfyeKAVGxJKjfODCkJnskZVWID+d00gC1g3+cShG3W9vCnBiMqAPmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"142d35b277ac9c1c697ac22f18063c4711af5549f9f15ef34a059e62ad4eeb5c","last_reissued_at":"2026-07-05T04:18:50.034026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:18:50.034026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bertie Vidgen, Dirk Hovy, Janet B. Pierrehumbert, Paul R\\\"ottger","submitted_at":"2021-12-14T15:38:22Z","abstract_excerpt":"Labelled data is the foundation of most natural language processing tasks. However, labelling data is difficult and there often are diverse valid beliefs about what the correct data labels should be. So far, dataset creators have acknowledged annotator subjectivity, but rarely actively managed it in the annotation process. This has led to partly-subjective datasets that fail to serve a clear downstream use. To address this issue, we propose two contrasting paradigms for data annotation. The descriptive paradigm encourages annotator subjectivity, whereas the prescriptive paradigm discourages it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07475","kind":"arxiv","version":2},"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/2112.07475/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":"2112.07475","created_at":"2026-07-05T04:18:50.034082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.07475v2","created_at":"2026-07-05T04:18:50.034082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07475","created_at":"2026-07-05T04:18:50.034082+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQWTLMTXVSOB","created_at":"2026-07-05T04:18:50.034082+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQWTLMTXVSOBY2L2","created_at":"2026-07-05T04:18:50.034082+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQWTLMTX","created_at":"2026-07-05T04:18:50.034082+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09408","citing_title":"Can Data Work be Reparative?","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQWTLMTXVSOBY2L2YIXRQBR4I4","json":"https://pith.science/pith/CQWTLMTXVSOBY2L2YIXRQBR4I4.json","graph_json":"https://pith.science/api/pith-number/CQWTLMTXVSOBY2L2YIXRQBR4I4/graph.json","events_json":"https://pith.science/api/pith-number/CQWTLMTXVSOBY2L2YIXRQBR4I4/events.json","paper":"https://pith.science/paper/CQWTLMTX"},"agent_actions":{"view_html":"https://pith.science/pith/CQWTLMTXVSOBY2L2YIXRQBR4I4","download_json":"https://pith.science/pith/CQWTLMTXVSOBY2L2YIXRQBR4I4.json","view_paper":"https://pith.science/paper/CQWTLMTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.07475&json=true","fetch_graph":"https://pith.science/api/pith-number/CQWTLMTXVSOBY2L2YIXRQBR4I4/graph.json","fetch_events":"https://pith.science/api/pith-number/CQWTLMTXVSOBY2L2YIXRQBR4I4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQWTLMTXVSOBY2L2YIXRQBR4I4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQWTLMTXVSOBY2L2YIXRQBR4I4/action/storage_attestation","attest_author":"https://pith.science/pith/CQWTLMTXVSOBY2L2YIXRQBR4I4/action/author_attestation","sign_citation":"https://pith.science/pith/CQWTLMTXVSOBY2L2YIXRQBR4I4/action/citation_signature","submit_replication":"https://pith.science/pith/CQWTLMTXVSOBY2L2YIXRQBR4I4/action/replication_record"}},"created_at":"2026-07-05T04:18:50.034082+00:00","updated_at":"2026-07-05T04:18:50.034082+00:00"}