{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GM5VSMTMU46KGLNOS6GQAX7LQA","short_pith_number":"pith:GM5VSMTM","schema_version":"1.0","canonical_sha256":"333b59326ca73ca32dae978d005feb8033a9348375ba0e11f600ceb49ddd1d6b","source":{"kind":"arxiv","id":"2202.03612","version":1},"attestation_state":"computed","paper":{"title":"HistBERT: A Pre-trained Language Model for Diachronic Lexical Semantic Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Wenjun Qiu, Yang Xu","submitted_at":"2022-02-08T02:53:48Z","abstract_excerpt":"Contextualized word embeddings have demonstrated state-of-the-art performance in various natural language processing tasks including those that concern historical semantic change. However, language models such as BERT was trained primarily on contemporary corpus data. To investigate whether training on historical corpus data improves diachronic semantic analysis, we present a pre-trained BERT-based language model, HistBERT, trained on the balanced Corpus of Historical American English. We examine the effectiveness of our approach by comparing the performance of the original BERT and that of Hi"},"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":"2202.03612","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-08T02:53:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7c11a81cd7b13c36b37e73ee7cb92f07d86ccbd25566eff74d628adf7d82dc09","abstract_canon_sha256":"a0b71d978957f6474fae7b99946e10ce60e18a0381cc86a106e979e04c73c898"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:55:32.876338Z","signature_b64":"dKhHx0dVWirB7B9MP/zo5diAlD2opkO7VONOU4roFGW67Spqy86aCqRsxxxgzIyTqC0RhuhRuX9VRe89dwxmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"333b59326ca73ca32dae978d005feb8033a9348375ba0e11f600ceb49ddd1d6b","last_reissued_at":"2026-07-05T03:55:32.875804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:55:32.875804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HistBERT: A Pre-trained Language Model for Diachronic Lexical Semantic Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Wenjun Qiu, Yang Xu","submitted_at":"2022-02-08T02:53:48Z","abstract_excerpt":"Contextualized word embeddings have demonstrated state-of-the-art performance in various natural language processing tasks including those that concern historical semantic change. However, language models such as BERT was trained primarily on contemporary corpus data. To investigate whether training on historical corpus data improves diachronic semantic analysis, we present a pre-trained BERT-based language model, HistBERT, trained on the balanced Corpus of Historical American English. We examine the effectiveness of our approach by comparing the performance of the original BERT and that of Hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03612","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/2202.03612/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":"2202.03612","created_at":"2026-07-05T03:55:32.875862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.03612v1","created_at":"2026-07-05T03:55:32.875862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03612","created_at":"2026-07-05T03:55:32.875862+00:00"},{"alias_kind":"pith_short_12","alias_value":"GM5VSMTMU46K","created_at":"2026-07-05T03:55:32.875862+00:00"},{"alias_kind":"pith_short_16","alias_value":"GM5VSMTMU46KGLNO","created_at":"2026-07-05T03:55:32.875862+00:00"},{"alias_kind":"pith_short_8","alias_value":"GM5VSMTM","created_at":"2026-07-05T03:55:32.875862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12148","citing_title":"Hatevolution: What Static Benchmarks Don't Tell Us","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GM5VSMTMU46KGLNOS6GQAX7LQA","json":"https://pith.science/pith/GM5VSMTMU46KGLNOS6GQAX7LQA.json","graph_json":"https://pith.science/api/pith-number/GM5VSMTMU46KGLNOS6GQAX7LQA/graph.json","events_json":"https://pith.science/api/pith-number/GM5VSMTMU46KGLNOS6GQAX7LQA/events.json","paper":"https://pith.science/paper/GM5VSMTM"},"agent_actions":{"view_html":"https://pith.science/pith/GM5VSMTMU46KGLNOS6GQAX7LQA","download_json":"https://pith.science/pith/GM5VSMTMU46KGLNOS6GQAX7LQA.json","view_paper":"https://pith.science/paper/GM5VSMTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.03612&json=true","fetch_graph":"https://pith.science/api/pith-number/GM5VSMTMU46KGLNOS6GQAX7LQA/graph.json","fetch_events":"https://pith.science/api/pith-number/GM5VSMTMU46KGLNOS6GQAX7LQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GM5VSMTMU46KGLNOS6GQAX7LQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GM5VSMTMU46KGLNOS6GQAX7LQA/action/storage_attestation","attest_author":"https://pith.science/pith/GM5VSMTMU46KGLNOS6GQAX7LQA/action/author_attestation","sign_citation":"https://pith.science/pith/GM5VSMTMU46KGLNOS6GQAX7LQA/action/citation_signature","submit_replication":"https://pith.science/pith/GM5VSMTMU46KGLNOS6GQAX7LQA/action/replication_record"}},"created_at":"2026-07-05T03:55:32.875862+00:00","updated_at":"2026-07-05T03:55:32.875862+00:00"}