{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GFIBYQ6WR34RXXJTSIBVJXMK6O","short_pith_number":"pith:GFIBYQ6W","schema_version":"1.0","canonical_sha256":"31501c43d68ef91bdd33920354dd8af3aa391262ea37e64cffeb1c12eff4a7a4","source":{"kind":"arxiv","id":"2009.10053","version":1},"attestation_state":"computed","paper":{"title":"Latin BERT: A Contextual Language Model for Classical Philology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Bamman, Patrick J. Burns","submitted_at":"2020-09-21T17:47:44Z","abstract_excerpt":"We present Latin BERT, a contextual language model for the Latin language, trained on 642.7 million words from a variety of sources spanning the Classical era to the 21st century. In a series of case studies, we illustrate the affordances of this language-specific model both for work in natural language processing for Latin and in using computational methods for traditional scholarship: we show that Latin BERT achieves a new state of the art for part-of-speech tagging on all three Universal Dependency datasets for Latin and can be used for predicting missing text (including critical emendation"},"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":"2009.10053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-21T17:47:44Z","cross_cats_sorted":[],"title_canon_sha256":"701230ac50d5d6828668ac4254effd710008475ec9c25b9bf7ab6bec428424da","abstract_canon_sha256":"82f671ab73201355b26b167ac513d6eafc569890e22033f2e6376bf40c2df887"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:36:55.795927Z","signature_b64":"n5iZ+9v4s3jhzkE/ydJuSPE/oSvowgeuwHbY/V/LeDB62xl2W4PwDuF28ZikMCwDAzCof/zwUZSJdgE6ueACCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31501c43d68ef91bdd33920354dd8af3aa391262ea37e64cffeb1c12eff4a7a4","last_reissued_at":"2026-07-05T01:36:55.795439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:36:55.795439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latin BERT: A Contextual Language Model for Classical Philology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Bamman, Patrick J. Burns","submitted_at":"2020-09-21T17:47:44Z","abstract_excerpt":"We present Latin BERT, a contextual language model for the Latin language, trained on 642.7 million words from a variety of sources spanning the Classical era to the 21st century. In a series of case studies, we illustrate the affordances of this language-specific model both for work in natural language processing for Latin and in using computational methods for traditional scholarship: we show that Latin BERT achieves a new state of the art for part-of-speech tagging on all three Universal Dependency datasets for Latin and can be used for predicting missing text (including critical emendation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.10053","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/2009.10053/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":"2009.10053","created_at":"2026-07-05T01:36:55.795497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.10053v1","created_at":"2026-07-05T01:36:55.795497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.10053","created_at":"2026-07-05T01:36:55.795497+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFIBYQ6WR34R","created_at":"2026-07-05T01:36:55.795497+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFIBYQ6WR34RXXJT","created_at":"2026-07-05T01:36:55.795497+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFIBYQ6W","created_at":"2026-07-05T01:36:55.795497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01136","citing_title":"From Outliers to Errors: Auditing Pali-to-English LLM Translations with Multi-Reference Adjudication","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20738","citing_title":"RespondeoQA: a Benchmark for Bilingual Latin-English Question Answering","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GFIBYQ6WR34RXXJTSIBVJXMK6O","json":"https://pith.science/pith/GFIBYQ6WR34RXXJTSIBVJXMK6O.json","graph_json":"https://pith.science/api/pith-number/GFIBYQ6WR34RXXJTSIBVJXMK6O/graph.json","events_json":"https://pith.science/api/pith-number/GFIBYQ6WR34RXXJTSIBVJXMK6O/events.json","paper":"https://pith.science/paper/GFIBYQ6W"},"agent_actions":{"view_html":"https://pith.science/pith/GFIBYQ6WR34RXXJTSIBVJXMK6O","download_json":"https://pith.science/pith/GFIBYQ6WR34RXXJTSIBVJXMK6O.json","view_paper":"https://pith.science/paper/GFIBYQ6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.10053&json=true","fetch_graph":"https://pith.science/api/pith-number/GFIBYQ6WR34RXXJTSIBVJXMK6O/graph.json","fetch_events":"https://pith.science/api/pith-number/GFIBYQ6WR34RXXJTSIBVJXMK6O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFIBYQ6WR34RXXJTSIBVJXMK6O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFIBYQ6WR34RXXJTSIBVJXMK6O/action/storage_attestation","attest_author":"https://pith.science/pith/GFIBYQ6WR34RXXJTSIBVJXMK6O/action/author_attestation","sign_citation":"https://pith.science/pith/GFIBYQ6WR34RXXJTSIBVJXMK6O/action/citation_signature","submit_replication":"https://pith.science/pith/GFIBYQ6WR34RXXJTSIBVJXMK6O/action/replication_record"}},"created_at":"2026-07-05T01:36:55.795497+00:00","updated_at":"2026-07-05T01:36:55.795497+00:00"}