{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6WGIX24TTGEZYWKOUSURCDYBAF","short_pith_number":"pith:6WGIX24T","schema_version":"1.0","canonical_sha256":"f58c8beb9399899c594ea4a9110f01017b230339e96e00b7b686ba92f1ba8157","source":{"kind":"arxiv","id":"2104.03776","version":2},"attestation_state":"computed","paper":{"title":"Statistically significant detection of semantic shifts using contextual word embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Medlar, Dorota Glowacka, Yang Liu","submitted_at":"2021-04-08T13:58:54Z","abstract_excerpt":"Detecting lexical semantic change in smaller data sets, e.g. in historical linguistics and digital humanities, is challenging due to a lack of statistical power. This issue is exacerbated by non-contextual embedding models that produce one embedding per word and, therefore, mask the variability present in the data. In this article, we propose an approach to estimate semantic shift by combining contextual word embeddings with permutation-based statistical tests. We use the false discovery rate procedure to address the large number of hypothesis tests being conducted simultaneously. We demonstra"},"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":"2104.03776","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-08T13:58:54Z","cross_cats_sorted":[],"title_canon_sha256":"68d9377c36f7389f03c13edfce3fcca5814353ea00c933ee194828d7be1d7aa4","abstract_canon_sha256":"8ad9ca1851d4ed0a1b1a41a43e58c95723c7ecbb200d2aa3454e85ce71906bc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:47.972755Z","signature_b64":"p4LnLlgj655mBnEUJTQrzx9vFM1iyMExQgCIzIW/wMFxlRgUV+ibDmCDJQT74EGVLC1dKO3dh73+GJrRkgAbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f58c8beb9399899c594ea4a9110f01017b230339e96e00b7b686ba92f1ba8157","last_reissued_at":"2026-07-05T03:58:47.972263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:47.972263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistically significant detection of semantic shifts using contextual word embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Medlar, Dorota Glowacka, Yang Liu","submitted_at":"2021-04-08T13:58:54Z","abstract_excerpt":"Detecting lexical semantic change in smaller data sets, e.g. in historical linguistics and digital humanities, is challenging due to a lack of statistical power. This issue is exacerbated by non-contextual embedding models that produce one embedding per word and, therefore, mask the variability present in the data. In this article, we propose an approach to estimate semantic shift by combining contextual word embeddings with permutation-based statistical tests. We use the false discovery rate procedure to address the large number of hypothesis tests being conducted simultaneously. We demonstra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.03776","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/2104.03776/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":"2104.03776","created_at":"2026-07-05T03:58:47.972325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.03776v2","created_at":"2026-07-05T03:58:47.972325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.03776","created_at":"2026-07-05T03:58:47.972325+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WGIX24TTGEZ","created_at":"2026-07-05T03:58:47.972325+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WGIX24TTGEZYWKO","created_at":"2026-07-05T03:58:47.972325+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WGIX24T","created_at":"2026-07-05T03:58:47.972325+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.07522","citing_title":"Community-Specific Slang and Entity Detection via Semantic Shift in Fine-Tuned Language Models","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WGIX24TTGEZYWKOUSURCDYBAF","json":"https://pith.science/pith/6WGIX24TTGEZYWKOUSURCDYBAF.json","graph_json":"https://pith.science/api/pith-number/6WGIX24TTGEZYWKOUSURCDYBAF/graph.json","events_json":"https://pith.science/api/pith-number/6WGIX24TTGEZYWKOUSURCDYBAF/events.json","paper":"https://pith.science/paper/6WGIX24T"},"agent_actions":{"view_html":"https://pith.science/pith/6WGIX24TTGEZYWKOUSURCDYBAF","download_json":"https://pith.science/pith/6WGIX24TTGEZYWKOUSURCDYBAF.json","view_paper":"https://pith.science/paper/6WGIX24T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.03776&json=true","fetch_graph":"https://pith.science/api/pith-number/6WGIX24TTGEZYWKOUSURCDYBAF/graph.json","fetch_events":"https://pith.science/api/pith-number/6WGIX24TTGEZYWKOUSURCDYBAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WGIX24TTGEZYWKOUSURCDYBAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WGIX24TTGEZYWKOUSURCDYBAF/action/storage_attestation","attest_author":"https://pith.science/pith/6WGIX24TTGEZYWKOUSURCDYBAF/action/author_attestation","sign_citation":"https://pith.science/pith/6WGIX24TTGEZYWKOUSURCDYBAF/action/citation_signature","submit_replication":"https://pith.science/pith/6WGIX24TTGEZYWKOUSURCDYBAF/action/replication_record"}},"created_at":"2026-07-05T03:58:47.972325+00:00","updated_at":"2026-07-05T03:58:47.972325+00:00"}