{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QNFHGMTMNEZWXSP4FAYKA43WX2","short_pith_number":"pith:QNFHGMTM","schema_version":"1.0","canonical_sha256":"834a73326c69336bc9fc2830a07376beae80a36d67bfe7752de2b7e7cbe838e9","source":{"kind":"arxiv","id":"2112.04554","version":1},"attestation_state":"computed","paper":{"title":"Whose Ground Truth? Accounting for Individual and Collective Identities Underlying Dataset Annotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ian Kivlichan, Mark D\\'iaz, Rachel Rosen, Remi Denton, Vinodkumar Prabhakaran","submitted_at":"2021-12-08T19:56:56Z","abstract_excerpt":"Human annotations play a crucial role in machine learning (ML) research and development. However, the ethical considerations around the processes and decisions that go into building ML datasets has not received nearly enough attention. In this paper, we survey an array of literature that provides insights into ethical considerations around crowdsourced dataset annotation. We synthesize these insights, and lay out the challenges in this space along two layers: (1) who the annotator is, and how the annotators' lived experiences can impact their annotations, and (2) the relationship between the a"},"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":"2112.04554","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-08T19:56:56Z","cross_cats_sorted":[],"title_canon_sha256":"06cd933196de00114e5d88ceae5e3372d56b3743c3d1cb02b7f55e684cc11dd0","abstract_canon_sha256":"0f8de534d880459e3a1361d93dcf8cd1598bc1f36ee8686a2cd2edfae5120827"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:18.111650Z","signature_b64":"qF95CtINuG/6eapsIgh/cWr4dC2w+w93PuWD+XRLhLZvG9QKTIn0SFjuqeSRQmxv7240q3j9SyhLZa24MumFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"834a73326c69336bc9fc2830a07376beae80a36d67bfe7752de2b7e7cbe838e9","last_reissued_at":"2026-07-05T07:55:18.111214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:18.111214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Whose Ground Truth? Accounting for Individual and Collective Identities Underlying Dataset Annotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ian Kivlichan, Mark D\\'iaz, Rachel Rosen, Remi Denton, Vinodkumar Prabhakaran","submitted_at":"2021-12-08T19:56:56Z","abstract_excerpt":"Human annotations play a crucial role in machine learning (ML) research and development. However, the ethical considerations around the processes and decisions that go into building ML datasets has not received nearly enough attention. In this paper, we survey an array of literature that provides insights into ethical considerations around crowdsourced dataset annotation. We synthesize these insights, and lay out the challenges in this space along two layers: (1) who the annotator is, and how the annotators' lived experiences can impact their annotations, and (2) the relationship between the a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04554","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/2112.04554/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":"2112.04554","created_at":"2026-07-05T07:55:18.111271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.04554v1","created_at":"2026-07-05T07:55:18.111271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04554","created_at":"2026-07-05T07:55:18.111271+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNFHGMTMNEZW","created_at":"2026-07-05T07:55:18.111271+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNFHGMTMNEZWXSP4","created_at":"2026-07-05T07:55:18.111271+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNFHGMTM","created_at":"2026-07-05T07:55:18.111271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19151","citing_title":"The Market in the Model: Latent Diffusion as Neural Economy","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2402.02249","citing_title":"Don't Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11318","citing_title":"The Consensus Trap: Dissecting Subjectivity and the \"Ground Truth\" Illusion in Data Annotation","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09955","citing_title":"Beyond Majority Voting: Agreement-Based Clustering to Model Annotator Perspectives in Subjective NLP Tasks","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07084","citing_title":"Beyond Single Ground Truth: Reference Monism as Epistemic Injustice in ASR Evaluation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16654","citing_title":"IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QNFHGMTMNEZWXSP4FAYKA43WX2","json":"https://pith.science/pith/QNFHGMTMNEZWXSP4FAYKA43WX2.json","graph_json":"https://pith.science/api/pith-number/QNFHGMTMNEZWXSP4FAYKA43WX2/graph.json","events_json":"https://pith.science/api/pith-number/QNFHGMTMNEZWXSP4FAYKA43WX2/events.json","paper":"https://pith.science/paper/QNFHGMTM"},"agent_actions":{"view_html":"https://pith.science/pith/QNFHGMTMNEZWXSP4FAYKA43WX2","download_json":"https://pith.science/pith/QNFHGMTMNEZWXSP4FAYKA43WX2.json","view_paper":"https://pith.science/paper/QNFHGMTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.04554&json=true","fetch_graph":"https://pith.science/api/pith-number/QNFHGMTMNEZWXSP4FAYKA43WX2/graph.json","fetch_events":"https://pith.science/api/pith-number/QNFHGMTMNEZWXSP4FAYKA43WX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNFHGMTMNEZWXSP4FAYKA43WX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNFHGMTMNEZWXSP4FAYKA43WX2/action/storage_attestation","attest_author":"https://pith.science/pith/QNFHGMTMNEZWXSP4FAYKA43WX2/action/author_attestation","sign_citation":"https://pith.science/pith/QNFHGMTMNEZWXSP4FAYKA43WX2/action/citation_signature","submit_replication":"https://pith.science/pith/QNFHGMTMNEZWXSP4FAYKA43WX2/action/replication_record"}},"created_at":"2026-07-05T07:55:18.111271+00:00","updated_at":"2026-07-05T07:55:18.111271+00:00"}