{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OBZTFJPM6AHB7JO6C4273KH2II","short_pith_number":"pith:OBZTFJPM","schema_version":"1.0","canonical_sha256":"707332a5ecf00e1fa5de1735fda8fa42360042c4e13a337b33dff4dddb3de05a","source":{"kind":"arxiv","id":"2204.00333","version":1},"attestation_state":"computed","paper":{"title":"PriMock57: A Dataset Of Primary Care Mock Consultations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aleksandar Savkov, Alex Papadopoulos Korfiatis, Francesco Moramarco, Radmila Sarac","submitted_at":"2022-04-01T10:18:28Z","abstract_excerpt":"Recent advances in Automatic Speech Recognition (ASR) have made it possible to reliably produce automatic transcripts of clinician-patient conversations. However, access to clinical datasets is heavily restricted due to patient privacy, thus slowing down normal research practices. We detail the development of a public access, high quality dataset comprising of57 mocked primary care consultations, including audio recordings, their manual utterance-level transcriptions, and the associated consultation notes. Our work illustrates how the dataset can be used as a benchmark for conversational medic"},"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":"2204.00333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-01T10:18:28Z","cross_cats_sorted":[],"title_canon_sha256":"6b9ae152a0a1bab8be133da892207a81ad58a71ec65a31ceea23ea1c88183b33","abstract_canon_sha256":"91ac57b71464f777dd574e96b75cfefe9085c6f2e84ff8a9908e6d87d45fe5d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:45.932821Z","signature_b64":"FU6UmtVqpFit4cv6IV2Wjm9vkCjKlhU8SVLdMK2Yt5NTGSFokoaPh3cLqksAlOjNDh1+Ka8WHPHlkwMYGlZDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"707332a5ecf00e1fa5de1735fda8fa42360042c4e13a337b33dff4dddb3de05a","last_reissued_at":"2026-07-05T04:10:45.932350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:45.932350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PriMock57: A Dataset Of Primary Care Mock Consultations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aleksandar Savkov, Alex Papadopoulos Korfiatis, Francesco Moramarco, Radmila Sarac","submitted_at":"2022-04-01T10:18:28Z","abstract_excerpt":"Recent advances in Automatic Speech Recognition (ASR) have made it possible to reliably produce automatic transcripts of clinician-patient conversations. However, access to clinical datasets is heavily restricted due to patient privacy, thus slowing down normal research practices. We detail the development of a public access, high quality dataset comprising of57 mocked primary care consultations, including audio recordings, their manual utterance-level transcriptions, and the associated consultation notes. Our work illustrates how the dataset can be used as a benchmark for conversational medic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00333","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/2204.00333/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":"2204.00333","created_at":"2026-07-05T04:10:45.932407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.00333v1","created_at":"2026-07-05T04:10:45.932407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00333","created_at":"2026-07-05T04:10:45.932407+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBZTFJPM6AHB","created_at":"2026-07-05T04:10:45.932407+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBZTFJPM6AHB7JO6","created_at":"2026-07-05T04:10:45.932407+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBZTFJPM","created_at":"2026-07-05T04:10:45.932407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10896","citing_title":"BioClinical ModernBERT: A State-of-the-Art Long-Context Encoder for Biomedical and Clinical NLP","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBZTFJPM6AHB7JO6C4273KH2II","json":"https://pith.science/pith/OBZTFJPM6AHB7JO6C4273KH2II.json","graph_json":"https://pith.science/api/pith-number/OBZTFJPM6AHB7JO6C4273KH2II/graph.json","events_json":"https://pith.science/api/pith-number/OBZTFJPM6AHB7JO6C4273KH2II/events.json","paper":"https://pith.science/paper/OBZTFJPM"},"agent_actions":{"view_html":"https://pith.science/pith/OBZTFJPM6AHB7JO6C4273KH2II","download_json":"https://pith.science/pith/OBZTFJPM6AHB7JO6C4273KH2II.json","view_paper":"https://pith.science/paper/OBZTFJPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.00333&json=true","fetch_graph":"https://pith.science/api/pith-number/OBZTFJPM6AHB7JO6C4273KH2II/graph.json","fetch_events":"https://pith.science/api/pith-number/OBZTFJPM6AHB7JO6C4273KH2II/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBZTFJPM6AHB7JO6C4273KH2II/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBZTFJPM6AHB7JO6C4273KH2II/action/storage_attestation","attest_author":"https://pith.science/pith/OBZTFJPM6AHB7JO6C4273KH2II/action/author_attestation","sign_citation":"https://pith.science/pith/OBZTFJPM6AHB7JO6C4273KH2II/action/citation_signature","submit_replication":"https://pith.science/pith/OBZTFJPM6AHB7JO6C4273KH2II/action/replication_record"}},"created_at":"2026-07-05T04:10:45.932407+00:00","updated_at":"2026-07-05T04:10:45.932407+00:00"}