{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WWUAC3TY4EAKE423745K3RGNWY","short_pith_number":"pith:WWUAC3TY","schema_version":"1.0","canonical_sha256":"b5a8016e78e100a2735bff3aadc4cdb60adeebc9e37557dc8b7cc62d8f941957","source":{"kind":"arxiv","id":"2608.00932","version":1},"attestation_state":"computed","paper":{"title":"Gaokerena: A Small Persian Medical Language Model Family","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Audrina Ebrahimi, Hamidreza Baradaran Kashani, Mehrdad Ghassabi, Pedram Rostami, Sadra Hakim, Zahra Kazemi","submitted_at":"2026-08-02T02:17:10Z","abstract_excerpt":"The integration of artificial intelligence into medical question-answering systems has advanced rapidly; however, research remains predominantly focused on English, leaving low resource languages like Persian significantly underserved. To address this gap, this paper introduces Gaokerena, a novel family of compact Persian medical language models optimized for deployment on consumer grade hardware. As a foundational step toward localized digital healthcare, we first present Gaokerena-V, developed by training a baseline model on a newly curated 90-million-token Persian medical corpus and 20,000 "},"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":"2608.00932","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T02:17:10Z","cross_cats_sorted":[],"title_canon_sha256":"5046d0ae0ab457de44041abaec806b39051af6d51ab926da19d3a07c1623abd6","abstract_canon_sha256":"0f4e656a31f1dc2b345055cf8928c7e8fc87b3a2603afe6e499db758edfea0eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:55:52.236513Z","signature_b64":"03hHXrXItN3uFoL5EYJ5QgjijFU68TzcqcWF9iqY7WXToULiy0IcZmbpZww6Jro/rka9h5GaXmItsQ5pQq9ODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5a8016e78e100a2735bff3aadc4cdb60adeebc9e37557dc8b7cc62d8f941957","last_reissued_at":"2026-08-04T01:55:52.234828Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:55:52.234828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaokerena: A Small Persian Medical Language Model Family","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Audrina Ebrahimi, Hamidreza Baradaran Kashani, Mehrdad Ghassabi, Pedram Rostami, Sadra Hakim, Zahra Kazemi","submitted_at":"2026-08-02T02:17:10Z","abstract_excerpt":"The integration of artificial intelligence into medical question-answering systems has advanced rapidly; however, research remains predominantly focused on English, leaving low resource languages like Persian significantly underserved. To address this gap, this paper introduces Gaokerena, a novel family of compact Persian medical language models optimized for deployment on consumer grade hardware. As a foundational step toward localized digital healthcare, we first present Gaokerena-V, developed by training a baseline model on a newly curated 90-million-token Persian medical corpus and 20,000 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00932","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/2608.00932/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":"2608.00932","created_at":"2026-08-04T01:55:52.236294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00932v1","created_at":"2026-08-04T01:55:52.236294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00932","created_at":"2026-08-04T01:55:52.236294+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWUAC3TY4EAK","created_at":"2026-08-04T01:55:52.236294+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWUAC3TY4EAKE423","created_at":"2026-08-04T01:55:52.236294+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWUAC3TY","created_at":"2026-08-04T01:55:52.236294+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/WWUAC3TY4EAKE423745K3RGNWY","json":"https://pith.science/pith/WWUAC3TY4EAKE423745K3RGNWY.json","graph_json":"https://pith.science/api/pith-number/WWUAC3TY4EAKE423745K3RGNWY/graph.json","events_json":"https://pith.science/api/pith-number/WWUAC3TY4EAKE423745K3RGNWY/events.json","paper":"https://pith.science/paper/WWUAC3TY"},"agent_actions":{"view_html":"https://pith.science/pith/WWUAC3TY4EAKE423745K3RGNWY","download_json":"https://pith.science/pith/WWUAC3TY4EAKE423745K3RGNWY.json","view_paper":"https://pith.science/paper/WWUAC3TY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00932&json=true","fetch_graph":"https://pith.science/api/pith-number/WWUAC3TY4EAKE423745K3RGNWY/graph.json","fetch_events":"https://pith.science/api/pith-number/WWUAC3TY4EAKE423745K3RGNWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWUAC3TY4EAKE423745K3RGNWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWUAC3TY4EAKE423745K3RGNWY/action/storage_attestation","attest_author":"https://pith.science/pith/WWUAC3TY4EAKE423745K3RGNWY/action/author_attestation","sign_citation":"https://pith.science/pith/WWUAC3TY4EAKE423745K3RGNWY/action/citation_signature","submit_replication":"https://pith.science/pith/WWUAC3TY4EAKE423745K3RGNWY/action/replication_record"}},"created_at":"2026-08-04T01:55:52.236294+00:00","updated_at":"2026-08-04T01:55:52.236294+00:00"}