{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RJAVYRJBSTTEWXZPVE3KH6JQFW","short_pith_number":"pith:RJAVYRJB","schema_version":"1.0","canonical_sha256":"8a415c452194e64b5f2fa936a3f9302d8c44ed4c9d91eafa4ebbe40feb0b8f93","source":{"kind":"arxiv","id":"2205.06885","version":1},"attestation_state":"computed","paper":{"title":"PathologyBERT -- Pre-trained Vs. A New Transformer Language Model for Pathology Domain","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amara Tariq, Geoffrey H. Smith, Hari Trivedi, Imon Banerjee, Kavyasree Vayalpati, Susmita Das, Thiago Santos","submitted_at":"2022-05-13T20:42:07Z","abstract_excerpt":"Pathology text mining is a challenging task given the reporting variability and constant new findings in cancer sub-type definitions. However, successful text mining of a large pathology database can play a critical role to advance 'big data' cancer research like similarity-based treatment selection, case identification, prognostication, surveillance, clinical trial screening, risk stratification, and many others. While there is a growing interest in developing language models for more specific clinical domains, no pathology-specific language space exist to support the rapid data-mining develo"},"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":"2205.06885","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-13T20:42:07Z","cross_cats_sorted":[],"title_canon_sha256":"2cba7a54f887a8674d381f8f23af7cacda927ee198ee8ad345cdc27b1125bdf2","abstract_canon_sha256":"709674f9364bbdb837a5d91e477d894059a7a8e60ed63d318c903502473fee17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:23:09.688873Z","signature_b64":"5I5eDhAq4uZXR5JRBGs4T1e/DX3s6b6N76bY0WezwBZJCQMAlP0DMtC4QICpOuf33E1zD3vY8d8r/NDR6pocAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a415c452194e64b5f2fa936a3f9302d8c44ed4c9d91eafa4ebbe40feb0b8f93","last_reissued_at":"2026-07-05T04:23:09.688400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:23:09.688400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PathologyBERT -- Pre-trained Vs. A New Transformer Language Model for Pathology Domain","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amara Tariq, Geoffrey H. Smith, Hari Trivedi, Imon Banerjee, Kavyasree Vayalpati, Susmita Das, Thiago Santos","submitted_at":"2022-05-13T20:42:07Z","abstract_excerpt":"Pathology text mining is a challenging task given the reporting variability and constant new findings in cancer sub-type definitions. However, successful text mining of a large pathology database can play a critical role to advance 'big data' cancer research like similarity-based treatment selection, case identification, prognostication, surveillance, clinical trial screening, risk stratification, and many others. While there is a growing interest in developing language models for more specific clinical domains, no pathology-specific language space exist to support the rapid data-mining develo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06885","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/2205.06885/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":"2205.06885","created_at":"2026-07-05T04:23:09.688457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.06885v1","created_at":"2026-07-05T04:23:09.688457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06885","created_at":"2026-07-05T04:23:09.688457+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJAVYRJBSTTE","created_at":"2026-07-05T04:23:09.688457+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJAVYRJBSTTEWXZP","created_at":"2026-07-05T04:23:09.688457+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJAVYRJB","created_at":"2026-07-05T04:23:09.688457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RJAVYRJBSTTEWXZPVE3KH6JQFW","json":"https://pith.science/pith/RJAVYRJBSTTEWXZPVE3KH6JQFW.json","graph_json":"https://pith.science/api/pith-number/RJAVYRJBSTTEWXZPVE3KH6JQFW/graph.json","events_json":"https://pith.science/api/pith-number/RJAVYRJBSTTEWXZPVE3KH6JQFW/events.json","paper":"https://pith.science/paper/RJAVYRJB"},"agent_actions":{"view_html":"https://pith.science/pith/RJAVYRJBSTTEWXZPVE3KH6JQFW","download_json":"https://pith.science/pith/RJAVYRJBSTTEWXZPVE3KH6JQFW.json","view_paper":"https://pith.science/paper/RJAVYRJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.06885&json=true","fetch_graph":"https://pith.science/api/pith-number/RJAVYRJBSTTEWXZPVE3KH6JQFW/graph.json","fetch_events":"https://pith.science/api/pith-number/RJAVYRJBSTTEWXZPVE3KH6JQFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJAVYRJBSTTEWXZPVE3KH6JQFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJAVYRJBSTTEWXZPVE3KH6JQFW/action/storage_attestation","attest_author":"https://pith.science/pith/RJAVYRJBSTTEWXZPVE3KH6JQFW/action/author_attestation","sign_citation":"https://pith.science/pith/RJAVYRJBSTTEWXZPVE3KH6JQFW/action/citation_signature","submit_replication":"https://pith.science/pith/RJAVYRJBSTTEWXZPVE3KH6JQFW/action/replication_record"}},"created_at":"2026-07-05T04:23:09.688457+00:00","updated_at":"2026-07-05T04:23:09.688457+00:00"}