{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2NMRTUGFI7HKPYNT2VORW67LSL","short_pith_number":"pith:2NMRTUGF","schema_version":"1.0","canonical_sha256":"d35919d0c547cea7e1b3d55d1b7beb92d2e36496ef0ef0417d75af2dfe8fda9a","source":{"kind":"arxiv","id":"2104.07613","version":1},"attestation_state":"computed","paper":{"title":"SINA-BERT: A pre-trained Language Model for Analysis of Medical Texts in Persian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ehsan Doostmohammadi, Elham Seifossadat, Hamid R. Rabiee, Maedeh S. Tahaei, Nasrin Taghizadeh","submitted_at":"2021-04-15T17:22:27Z","abstract_excerpt":"We have released Sina-BERT, a language model pre-trained on BERT (Devlin et al., 2018) to address the lack of a high-quality Persian language model in the medical domain. SINA-BERT utilizes pre-training on a large-scale corpus of medical contents including formal and informal texts collected from a variety of online resources in order to improve the performance on health-care related tasks. We employ SINA-BERT to complete following representative tasks: categorization of medical questions, medical sentiment analysis, and medical question retrieval. For each task, we have developed Persian anno"},"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":"2104.07613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-15T17:22:27Z","cross_cats_sorted":[],"title_canon_sha256":"13c3213b588d66b90e83441ddea6a7a7a82f1603ac1b0e5fcab04f59e3e6b755","abstract_canon_sha256":"07353947b7c995278c742256a59cb7ebdf18285b3eeb4aab6fec0f9ffdf5f5f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:30.030593Z","signature_b64":"vLz2e1P+KChTFqVh10ccn79Uog+0f+QLmutgpoKh4eEz54Ez/tXPNrGGruDZa5+W5pKdf/y7K03Z9d+KyLH6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d35919d0c547cea7e1b3d55d1b7beb92d2e36496ef0ef0417d75af2dfe8fda9a","last_reissued_at":"2026-07-05T02:32:30.030134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:30.030134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SINA-BERT: A pre-trained Language Model for Analysis of Medical Texts in Persian","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ehsan Doostmohammadi, Elham Seifossadat, Hamid R. Rabiee, Maedeh S. Tahaei, Nasrin Taghizadeh","submitted_at":"2021-04-15T17:22:27Z","abstract_excerpt":"We have released Sina-BERT, a language model pre-trained on BERT (Devlin et al., 2018) to address the lack of a high-quality Persian language model in the medical domain. SINA-BERT utilizes pre-training on a large-scale corpus of medical contents including formal and informal texts collected from a variety of online resources in order to improve the performance on health-care related tasks. We employ SINA-BERT to complete following representative tasks: categorization of medical questions, medical sentiment analysis, and medical question retrieval. For each task, we have developed Persian anno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.07613","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/2104.07613/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":"2104.07613","created_at":"2026-07-05T02:32:30.030191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.07613v1","created_at":"2026-07-05T02:32:30.030191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.07613","created_at":"2026-07-05T02:32:30.030191+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NMRTUGFI7HK","created_at":"2026-07-05T02:32:30.030191+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NMRTUGFI7HKPYNT","created_at":"2026-07-05T02:32:30.030191+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NMRTUGF","created_at":"2026-07-05T02:32:30.030191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.00932","citing_title":"Gaokerena: A Small Persian Medical Language Model Family","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2NMRTUGFI7HKPYNT2VORW67LSL","json":"https://pith.science/pith/2NMRTUGFI7HKPYNT2VORW67LSL.json","graph_json":"https://pith.science/api/pith-number/2NMRTUGFI7HKPYNT2VORW67LSL/graph.json","events_json":"https://pith.science/api/pith-number/2NMRTUGFI7HKPYNT2VORW67LSL/events.json","paper":"https://pith.science/paper/2NMRTUGF"},"agent_actions":{"view_html":"https://pith.science/pith/2NMRTUGFI7HKPYNT2VORW67LSL","download_json":"https://pith.science/pith/2NMRTUGFI7HKPYNT2VORW67LSL.json","view_paper":"https://pith.science/paper/2NMRTUGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.07613&json=true","fetch_graph":"https://pith.science/api/pith-number/2NMRTUGFI7HKPYNT2VORW67LSL/graph.json","fetch_events":"https://pith.science/api/pith-number/2NMRTUGFI7HKPYNT2VORW67LSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NMRTUGFI7HKPYNT2VORW67LSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NMRTUGFI7HKPYNT2VORW67LSL/action/storage_attestation","attest_author":"https://pith.science/pith/2NMRTUGFI7HKPYNT2VORW67LSL/action/author_attestation","sign_citation":"https://pith.science/pith/2NMRTUGFI7HKPYNT2VORW67LSL/action/citation_signature","submit_replication":"https://pith.science/pith/2NMRTUGFI7HKPYNT2VORW67LSL/action/replication_record"}},"created_at":"2026-07-05T02:32:30.030191+00:00","updated_at":"2026-07-05T02:32:30.030191+00:00"}