{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SGVLNUREZPXARMN2R24ONEETDT","short_pith_number":"pith:SGVLNURE","schema_version":"1.0","canonical_sha256":"91aab6d224cbee08b1ba8eb8e690931ce3eead9ae92553fccda7c866f64f4d73","source":{"kind":"arxiv","id":"2306.01943","version":1},"attestation_state":"computed","paper":{"title":"NLPositionality: Characterizing Design Biases of Datasets and Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.HC"],"primary_cat":"cs.CL","authors_text":"Jenny T. Liang, Katharina Reinecke, Maarten Sap, Ronan Le Bras, Sebastin Santy","submitted_at":"2023-06-02T23:02:09Z","abstract_excerpt":"Design biases in NLP systems, such as performance differences for different populations, often stem from their creator's positionality, i.e., views and lived experiences shaped by identity and background. Despite the prevalence and risks of design biases, they are hard to quantify because researcher, system, and dataset positionality is often unobserved. We introduce NLPositionality, a framework for characterizing design biases and quantifying the positionality of NLP datasets and models. Our framework continuously collects annotations from a diverse pool of volunteer participants on LabintheW"},"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":"2306.01943","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T23:02:09Z","cross_cats_sorted":["cs.CY","cs.HC"],"title_canon_sha256":"04ba29808083f06bda3e529ffbcd5df8e77588571582d188de92b8b9df92b28e","abstract_canon_sha256":"d1c3e63dcd696272d6e7e27af6ad8a6f9f6b57fec78567905190aaeea13ba595"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:11.292124Z","signature_b64":"u/yBGxmhlCDGoqjizCU5AorufNK2forNejgNh92UgFWMNaWGW66Tj0XUTE8qwr7RAvIorCAMOqFWU2gc0d1sCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91aab6d224cbee08b1ba8eb8e690931ce3eead9ae92553fccda7c866f64f4d73","last_reissued_at":"2026-07-05T06:17:11.291734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:11.291734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NLPositionality: Characterizing Design Biases of Datasets and Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.HC"],"primary_cat":"cs.CL","authors_text":"Jenny T. Liang, Katharina Reinecke, Maarten Sap, Ronan Le Bras, Sebastin Santy","submitted_at":"2023-06-02T23:02:09Z","abstract_excerpt":"Design biases in NLP systems, such as performance differences for different populations, often stem from their creator's positionality, i.e., views and lived experiences shaped by identity and background. Despite the prevalence and risks of design biases, they are hard to quantify because researcher, system, and dataset positionality is often unobserved. We introduce NLPositionality, a framework for characterizing design biases and quantifying the positionality of NLP datasets and models. Our framework continuously collects annotations from a diverse pool of volunteer participants on LabintheW"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01943","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/2306.01943/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":"2306.01943","created_at":"2026-07-05T06:17:11.291792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01943v1","created_at":"2026-07-05T06:17:11.291792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01943","created_at":"2026-07-05T06:17:11.291792+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGVLNUREZPXA","created_at":"2026-07-05T06:17:11.291792+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGVLNUREZPXARMN2","created_at":"2026-07-05T06:17:11.291792+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGVLNURE","created_at":"2026-07-05T06:17:11.291792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09408","citing_title":"Can Data Work be Reparative?","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2408.09049","citing_title":"Inertia in Moral and Value Judgments of Large Language Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20512","citing_title":"Framing an AI with Values Reduces AI Reliance in AI-supported Writing Tasks","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2402.05070","citing_title":"A Roadmap to Pluralistic Alignment","ref_index":284,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGVLNUREZPXARMN2R24ONEETDT","json":"https://pith.science/pith/SGVLNUREZPXARMN2R24ONEETDT.json","graph_json":"https://pith.science/api/pith-number/SGVLNUREZPXARMN2R24ONEETDT/graph.json","events_json":"https://pith.science/api/pith-number/SGVLNUREZPXARMN2R24ONEETDT/events.json","paper":"https://pith.science/paper/SGVLNURE"},"agent_actions":{"view_html":"https://pith.science/pith/SGVLNUREZPXARMN2R24ONEETDT","download_json":"https://pith.science/pith/SGVLNUREZPXARMN2R24ONEETDT.json","view_paper":"https://pith.science/paper/SGVLNURE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01943&json=true","fetch_graph":"https://pith.science/api/pith-number/SGVLNUREZPXARMN2R24ONEETDT/graph.json","fetch_events":"https://pith.science/api/pith-number/SGVLNUREZPXARMN2R24ONEETDT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGVLNUREZPXARMN2R24ONEETDT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGVLNUREZPXARMN2R24ONEETDT/action/storage_attestation","attest_author":"https://pith.science/pith/SGVLNUREZPXARMN2R24ONEETDT/action/author_attestation","sign_citation":"https://pith.science/pith/SGVLNUREZPXARMN2R24ONEETDT/action/citation_signature","submit_replication":"https://pith.science/pith/SGVLNUREZPXARMN2R24ONEETDT/action/replication_record"}},"created_at":"2026-07-05T06:17:11.291792+00:00","updated_at":"2026-07-05T06:17:11.291792+00:00"}