{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IMLRA5ITNH6XERKMBFXSRJ24FP","short_pith_number":"pith:IMLRA5IT","schema_version":"1.0","canonical_sha256":"431710751369fd72454c096f28a75c2be7ca3141f91253fb67b7f77e156d8f12","source":{"kind":"arxiv","id":"2201.12888","version":1},"attestation_state":"computed","paper":{"title":"A Dataset for Medical Instructional Video Classification and Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Deepak Gupta, Dina Demner-Fushman, Kush Attal","submitted_at":"2022-01-30T18:06:31Z","abstract_excerpt":"This paper introduces a new challenge and datasets to foster research toward designing systems that can understand medical videos and provide visual answers to natural language questions. We believe medical videos may provide the best possible answers to many first aids, medical emergency, and medical education questions. Toward this, we created the MedVidCL and MedVidQA datasets and introduce the tasks of Medical Video Classification (MVC) and Medical Visual Answer Localization (MVAL), two tasks that focus on cross-modal (medical language and medical video) understanding. The proposed tasks a"},"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":"2201.12888","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-30T18:06:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a44c39a488476c2a71febd90b719b8911a84c023d5bebbe3d3a10c6ac150d20e","abstract_canon_sha256":"009e51a8522c53a68fdb4edd86ab311dcc62927d4b42f415828ab1027a442d78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:40.794916Z","signature_b64":"+YX+aRui+l2H5ypJhHrTW7bw08Vt2DahGpOdeujzYSpltxL7ufZJYd8OwBfxY2ZDxrvukpoGEKPai7avWD/dCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"431710751369fd72454c096f28a75c2be7ca3141f91253fb67b7f77e156d8f12","last_reissued_at":"2026-07-05T03:52:40.794351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:40.794351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Dataset for Medical Instructional Video Classification and Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Deepak Gupta, Dina Demner-Fushman, Kush Attal","submitted_at":"2022-01-30T18:06:31Z","abstract_excerpt":"This paper introduces a new challenge and datasets to foster research toward designing systems that can understand medical videos and provide visual answers to natural language questions. We believe medical videos may provide the best possible answers to many first aids, medical emergency, and medical education questions. Toward this, we created the MedVidCL and MedVidQA datasets and introduce the tasks of Medical Video Classification (MVC) and Medical Visual Answer Localization (MVAL), two tasks that focus on cross-modal (medical language and medical video) understanding. The proposed tasks a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12888","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/2201.12888/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":"2201.12888","created_at":"2026-07-05T03:52:40.794419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.12888v1","created_at":"2026-07-05T03:52:40.794419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12888","created_at":"2026-07-05T03:52:40.794419+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMLRA5ITNH6X","created_at":"2026-07-05T03:52:40.794419+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMLRA5ITNH6XERKM","created_at":"2026-07-05T03:52:40.794419+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMLRA5IT","created_at":"2026-07-05T03:52:40.794419+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19835","citing_title":"MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IMLRA5ITNH6XERKMBFXSRJ24FP","json":"https://pith.science/pith/IMLRA5ITNH6XERKMBFXSRJ24FP.json","graph_json":"https://pith.science/api/pith-number/IMLRA5ITNH6XERKMBFXSRJ24FP/graph.json","events_json":"https://pith.science/api/pith-number/IMLRA5ITNH6XERKMBFXSRJ24FP/events.json","paper":"https://pith.science/paper/IMLRA5IT"},"agent_actions":{"view_html":"https://pith.science/pith/IMLRA5ITNH6XERKMBFXSRJ24FP","download_json":"https://pith.science/pith/IMLRA5ITNH6XERKMBFXSRJ24FP.json","view_paper":"https://pith.science/paper/IMLRA5IT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.12888&json=true","fetch_graph":"https://pith.science/api/pith-number/IMLRA5ITNH6XERKMBFXSRJ24FP/graph.json","fetch_events":"https://pith.science/api/pith-number/IMLRA5ITNH6XERKMBFXSRJ24FP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMLRA5ITNH6XERKMBFXSRJ24FP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMLRA5ITNH6XERKMBFXSRJ24FP/action/storage_attestation","attest_author":"https://pith.science/pith/IMLRA5ITNH6XERKMBFXSRJ24FP/action/author_attestation","sign_citation":"https://pith.science/pith/IMLRA5ITNH6XERKMBFXSRJ24FP/action/citation_signature","submit_replication":"https://pith.science/pith/IMLRA5ITNH6XERKMBFXSRJ24FP/action/replication_record"}},"created_at":"2026-07-05T03:52:40.794419+00:00","updated_at":"2026-07-05T03:52:40.794419+00:00"}