{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RJAVYRJBSTTEWXZPVE3KH6JQFW","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":"709674f9364bbdb837a5d91e477d894059a7a8e60ed63d318c903502473fee17","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-13T20:42:07Z","title_canon_sha256":"2cba7a54f887a8674d381f8f23af7cacda927ee198ee8ad345cdc27b1125bdf2"},"schema_version":"1.0","source":{"id":"2205.06885","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.06885","created_at":"2026-07-05T04:23:09Z"},{"alias_kind":"arxiv_version","alias_value":"2205.06885v1","created_at":"2026-07-05T04:23:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06885","created_at":"2026-07-05T04:23:09Z"},{"alias_kind":"pith_short_12","alias_value":"RJAVYRJBSTTE","created_at":"2026-07-05T04:23:09Z"},{"alias_kind":"pith_short_16","alias_value":"RJAVYRJBSTTEWXZP","created_at":"2026-07-05T04:23:09Z"},{"alias_kind":"pith_short_8","alias_value":"RJAVYRJB","created_at":"2026-07-05T04:23:09Z"}],"graph_snapshots":[{"event_id":"sha256:e0e1dee1a3d11f55277d8456d151223ba2cbc364cec34f35ad62f434f1edfec8","target":"graph","created_at":"2026-07-05T04:23:09Z","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/2205.06885/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Amara Tariq, Geoffrey H. Smith, Hari Trivedi, Imon Banerjee, Kavyasree Vayalpati, Susmita Das, Thiago Santos","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-13T20:42:07Z","title":"PathologyBERT -- Pre-trained Vs. A New Transformer Language Model for Pathology Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06885","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":"sha256:25dcf9048b0f65a13b93ae249bd125d083c5af78a79d35bbd961c80c7e752e49","target":"record","created_at":"2026-07-05T04:23:09Z","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":"709674f9364bbdb837a5d91e477d894059a7a8e60ed63d318c903502473fee17","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-13T20:42:07Z","title_canon_sha256":"2cba7a54f887a8674d381f8f23af7cacda927ee198ee8ad345cdc27b1125bdf2"},"schema_version":"1.0","source":{"id":"2205.06885","kind":"arxiv","version":1}},"canonical_sha256":"8a415c452194e64b5f2fa936a3f9302d8c44ed4c9d91eafa4ebbe40feb0b8f93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a415c452194e64b5f2fa936a3f9302d8c44ed4c9d91eafa4ebbe40feb0b8f93","first_computed_at":"2026-07-05T04:23:09.688400Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:23:09.688400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5I5eDhAq4uZXR5JRBGs4T1e/DX3s6b6N76bY0WezwBZJCQMAlP0DMtC4QICpOuf33E1zD3vY8d8r/NDR6pocAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:23:09.688873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.06885","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25dcf9048b0f65a13b93ae249bd125d083c5af78a79d35bbd961c80c7e752e49","sha256:e0e1dee1a3d11f55277d8456d151223ba2cbc364cec34f35ad62f434f1edfec8"],"state_sha256":"6038a945c7c65044cc1f5b5e73420ebee29fb26781ae97e3617eb8d7bde0bc4a"}