{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AKXGKGVOEWJN3E24V7SWVEBPM4","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":"476c8614e1fab34bf9a7cee13dd77504f61cf14ba211985c0e73011e962e85c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T16:30:22Z","title_canon_sha256":"2dfef6b336eab3c0da7c879ec15a99163e9b23c904189750c228b5f1216a5f55"},"schema_version":"1.0","source":{"id":"2204.12421","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12421","created_at":"2026-07-05T11:06:06Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12421v1","created_at":"2026-07-05T11:06:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12421","created_at":"2026-07-05T11:06:06Z"},{"alias_kind":"pith_short_12","alias_value":"AKXGKGVOEWJN","created_at":"2026-07-05T11:06:06Z"},{"alias_kind":"pith_short_16","alias_value":"AKXGKGVOEWJN3E24","created_at":"2026-07-05T11:06:06Z"},{"alias_kind":"pith_short_8","alias_value":"AKXGKGVO","created_at":"2026-07-05T11:06:06Z"}],"graph_snapshots":[{"event_id":"sha256:8d09df84909ebc7c30287b0de05d5c9390d09fcb8e594b96083b2c757803ccb8","target":"graph","created_at":"2026-07-05T11:06:06Z","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/2204.12421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research has highlighted that natural language processing (NLP) systems exhibit a bias against African American speakers. The bias errors are often caused by poor representation of linguistic features unique to African American English (AAE), due to the relatively low probability of occurrence of many such features in training data. We present a workflow to overcome such bias in the case of habitual \"be\". Habitual \"be\" is isomorphic, and therefore ambiguous, with other forms of \"be\" found in both AAE and other varieties of English. This creates a clear challenge for bias in NLP technolo","authors_text":"Harrison Santiago, Joshua Martin, Kevin Tang, Sarah Moeller","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T16:30:22Z","title":"Disambiguation of morpho-syntactic features of African American English -- the case of habitual be"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12421","kind":"arxiv","version":1},"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:e05a51cacb53778a7cc77cbc5f8eeb6968f15a21b98bc646d9ca2ca20ae67bd9","target":"record","created_at":"2026-07-05T11:06:06Z","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":"476c8614e1fab34bf9a7cee13dd77504f61cf14ba211985c0e73011e962e85c2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T16:30:22Z","title_canon_sha256":"2dfef6b336eab3c0da7c879ec15a99163e9b23c904189750c228b5f1216a5f55"},"schema_version":"1.0","source":{"id":"2204.12421","kind":"arxiv","version":1}},"canonical_sha256":"02ae651aae2592dd935cafe56a902f67290ba62640515e170b094f8a94ec215f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02ae651aae2592dd935cafe56a902f67290ba62640515e170b094f8a94ec215f","first_computed_at":"2026-07-05T11:06:06.459421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:06.459421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JkPTHt16CNoGyYNC3Ka1tvQlO5jXh7fXWYg3fUUB1SQrywr5XW7pCXy+jEaF8uOUx7qj4MdUqb3LIzCkEr8BDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:06.459833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.12421","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e05a51cacb53778a7cc77cbc5f8eeb6968f15a21b98bc646d9ca2ca20ae67bd9","sha256:8d09df84909ebc7c30287b0de05d5c9390d09fcb8e594b96083b2c757803ccb8"],"state_sha256":"777b93f1e418cf89ef4041ccee56a7b2a5e8417a0a0a7e3624618b1bc166edb4"}