{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7Z4ULJSYCS55MJF6NMBTCWGF44","short_pith_number":"pith:7Z4ULJSY","schema_version":"1.0","canonical_sha256":"fe7945a65814bbd624be6b033158c5e71658f757da45ca935a4999a9942faf03","source":{"kind":"arxiv","id":"2305.14663","version":2},"attestation_state":"computed","paper":{"title":"You Are What You Annotate: Towards Better Models through Annotator Representations","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lu Wang, Naihao Deng, Rada Mihalcea, Siyang Liu, Winston Wu, Xinliang Frederick Zhang","submitted_at":"2023-05-24T03:06:13Z","abstract_excerpt":"Annotator disagreement is ubiquitous in natural language processing (NLP) tasks. There are multiple reasons for such disagreements, including the subjectivity of the task, difficult cases, unclear guidelines, and so on. Rather than simply aggregating labels to obtain data annotations, we instead try to directly model the diverse perspectives of the annotators, and explicitly account for annotators' idiosyncrasies in the modeling process by creating representations for each annotator (annotator embeddings) and also their annotations (annotation embeddings). In addition, we propose TID-8, The In"},"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":"2305.14663","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T03:06:13Z","cross_cats_sorted":[],"title_canon_sha256":"b9075785576d4b590a1a0b5a7f9d3b001bdc51a2ac9784ba39286e91c03ee686","abstract_canon_sha256":"64febebfb35e3128891ac7a8070391718fa562e3ab45ad3d3cd787ba1b109058"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:25.584740Z","signature_b64":"ckQomV4KSpR9eddInd1sRefqVVblgXaZthmErOGStEx3HkXQyLSMND/Ojg+RdCrS+W/J+Evw0nIm2obm+OLLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe7945a65814bbd624be6b033158c5e71658f757da45ca935a4999a9942faf03","last_reissued_at":"2026-07-05T07:03:25.584271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:25.584271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"You Are What You Annotate: Towards Better Models through Annotator Representations","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lu Wang, Naihao Deng, Rada Mihalcea, Siyang Liu, Winston Wu, Xinliang Frederick Zhang","submitted_at":"2023-05-24T03:06:13Z","abstract_excerpt":"Annotator disagreement is ubiquitous in natural language processing (NLP) tasks. There are multiple reasons for such disagreements, including the subjectivity of the task, difficult cases, unclear guidelines, and so on. Rather than simply aggregating labels to obtain data annotations, we instead try to directly model the diverse perspectives of the annotators, and explicitly account for annotators' idiosyncrasies in the modeling process by creating representations for each annotator (annotator embeddings) and also their annotations (annotation embeddings). In addition, we propose TID-8, The In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14663","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/2305.14663/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":"2305.14663","created_at":"2026-07-05T07:03:25.584332+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14663v2","created_at":"2026-07-05T07:03:25.584332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14663","created_at":"2026-07-05T07:03:25.584332+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Z4ULJSYCS55","created_at":"2026-07-05T07:03:25.584332+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Z4ULJSYCS55MJF6","created_at":"2026-07-05T07:03:25.584332+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Z4ULJSY","created_at":"2026-07-05T07:03:25.584332+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07591","citing_title":"From Ground Truth to Measurement: A Statistical Framework for Human Labeling","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7Z4ULJSYCS55MJF6NMBTCWGF44","json":"https://pith.science/pith/7Z4ULJSYCS55MJF6NMBTCWGF44.json","graph_json":"https://pith.science/api/pith-number/7Z4ULJSYCS55MJF6NMBTCWGF44/graph.json","events_json":"https://pith.science/api/pith-number/7Z4ULJSYCS55MJF6NMBTCWGF44/events.json","paper":"https://pith.science/paper/7Z4ULJSY"},"agent_actions":{"view_html":"https://pith.science/pith/7Z4ULJSYCS55MJF6NMBTCWGF44","download_json":"https://pith.science/pith/7Z4ULJSYCS55MJF6NMBTCWGF44.json","view_paper":"https://pith.science/paper/7Z4ULJSY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14663&json=true","fetch_graph":"https://pith.science/api/pith-number/7Z4ULJSYCS55MJF6NMBTCWGF44/graph.json","fetch_events":"https://pith.science/api/pith-number/7Z4ULJSYCS55MJF6NMBTCWGF44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Z4ULJSYCS55MJF6NMBTCWGF44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Z4ULJSYCS55MJF6NMBTCWGF44/action/storage_attestation","attest_author":"https://pith.science/pith/7Z4ULJSYCS55MJF6NMBTCWGF44/action/author_attestation","sign_citation":"https://pith.science/pith/7Z4ULJSYCS55MJF6NMBTCWGF44/action/citation_signature","submit_replication":"https://pith.science/pith/7Z4ULJSYCS55MJF6NMBTCWGF44/action/replication_record"}},"created_at":"2026-07-05T07:03:25.584332+00:00","updated_at":"2026-07-05T07:03:25.584332+00:00"}