{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7DI3UHSAISIVF7DAXIBNCI7DOP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b86083d5c0354f9348d956a26deea5105997666890fa7dd55a36766e7dbae94b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-21T14:48:01Z","title_canon_sha256":"3b14f0a9509550b53ed728a25ae1ffd325c48482f8351e8d4cfec018f51769c8"},"schema_version":"1.0","source":{"id":"1908.07898","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.07898","created_at":"2026-07-05T00:00:16Z"},{"alias_kind":"arxiv_version","alias_value":"1908.07898v2","created_at":"2026-07-05T00:00:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07898","created_at":"2026-07-05T00:00:16Z"},{"alias_kind":"pith_short_12","alias_value":"7DI3UHSAISIV","created_at":"2026-07-05T00:00:16Z"},{"alias_kind":"pith_short_16","alias_value":"7DI3UHSAISIVF7DA","created_at":"2026-07-05T00:00:16Z"},{"alias_kind":"pith_short_8","alias_value":"7DI3UHSA","created_at":"2026-07-05T00:00:16Z"}],"graph_snapshots":[{"event_id":"sha256:b537cd135a3aca24e00b22156d0e6a0c0cf725cc338611d01bb9b861c7e9bf3e","target":"graph","created_at":"2026-07-05T00:00:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.07898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Crowdsourcing has been the prevalent paradigm for creating natural language understanding datasets in recent years. A common crowdsourcing practice is to recruit a small number of high-quality workers, and have them massively generate examples. Having only a few workers generate the majority of examples raises concerns about data diversity, especially when workers freely generate sentences. In this paper, we perform a series of experiments showing these concerns are evident in three recent NLP datasets. We show that model performance improves when training with annotator identifiers as feature","authors_text":"Jonathan Berant, Mor Geva, Yoav Goldberg","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-21T14:48:01Z","title":"Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07898","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:13ed0306a0ecce80796b13eb6ac86df573cedbd1b602552f265341f81d9785bd","target":"record","created_at":"2026-07-05T00:00:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b86083d5c0354f9348d956a26deea5105997666890fa7dd55a36766e7dbae94b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-21T14:48:01Z","title_canon_sha256":"3b14f0a9509550b53ed728a25ae1ffd325c48482f8351e8d4cfec018f51769c8"},"schema_version":"1.0","source":{"id":"1908.07898","kind":"arxiv","version":2}},"canonical_sha256":"f8d1ba1e40449152fc60ba02d123e373d56ecd8503cda5e92a97955160d874c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8d1ba1e40449152fc60ba02d123e373d56ecd8503cda5e92a97955160d874c1","first_computed_at":"2026-07-05T00:00:16.216007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:00:16.216007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tHFd0MOsfNb1inxzURGy0E9A6ra+kinpLiahcxBLx8OF1gubqxnOYESoflb5OADwRyEgjR9jtoIyT5sTwUo1Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T00:00:16.216450Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.07898","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13ed0306a0ecce80796b13eb6ac86df573cedbd1b602552f265341f81d9785bd","sha256:b537cd135a3aca24e00b22156d0e6a0c0cf725cc338611d01bb9b861c7e9bf3e"],"state_sha256":"d326161cbecc4010800b55dafbb29e5ad5686d76abf92d34fa3175b83de66a63"}