{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BCMATCHMGSPH256ER6LXTCYSSP","short_pith_number":"pith:BCMATCHM","schema_version":"1.0","canonical_sha256":"08980988ec349e7d77c48f97798b1293c5b12b87b8a08963ebe86bcd3426d8be","source":{"kind":"arxiv","id":"2106.03851","version":1},"attestation_state":"computed","paper":{"title":"Impact of data-splits on generalization: Identifying COVID-19 from cough and context","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aman Dalmia, Amrita Mahale, Jigar Doshi, Makkunda Sharma, Neeraj Agrawal, Nikhil Shenoy, Parag Bhamare, Piyush Bagad, Rahul Panicker, Saurabh Rane","submitted_at":"2021-06-05T07:48:05Z","abstract_excerpt":"Rapidly scaling screening, testing and quarantine has shown to be an effective strategy to combat the COVID-19 pandemic. We consider the application of deep learning techniques to distinguish individuals with COVID from non-COVID by using data acquirable from a phone. Using cough and context (symptoms and meta-data) represent such a promising approach. Several independent works in this direction have shown promising results. However, none of them report performance across clinically relevant data splits. Specifically, the performance where the development and test sets are split in time (retro"},"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":"2106.03851","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-05T07:48:05Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"2ee2f4a7a5d489ad04ea080c32655dd5a229d78eb34eff276ddce22bf2fada73","abstract_canon_sha256":"afd3d2b9705c788718d94b94cbe6d6f551edd24e51e2825b8e410234b9044d3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:09.778337Z","signature_b64":"KdSCvejKyBXkgDDnTx1sTv051N4NtkD38BpAJPuFbf7DoVId2IxQmh4VH2mVl8NZkbQDNjDS4H6hhcX2os/jAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08980988ec349e7d77c48f97798b1293c5b12b87b8a08963ebe86bcd3426d8be","last_reissued_at":"2026-07-05T02:47:09.777906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:09.777906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Impact of data-splits on generalization: Identifying COVID-19 from cough and context","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aman Dalmia, Amrita Mahale, Jigar Doshi, Makkunda Sharma, Neeraj Agrawal, Nikhil Shenoy, Parag Bhamare, Piyush Bagad, Rahul Panicker, Saurabh Rane","submitted_at":"2021-06-05T07:48:05Z","abstract_excerpt":"Rapidly scaling screening, testing and quarantine has shown to be an effective strategy to combat the COVID-19 pandemic. We consider the application of deep learning techniques to distinguish individuals with COVID from non-COVID by using data acquirable from a phone. Using cough and context (symptoms and meta-data) represent such a promising approach. Several independent works in this direction have shown promising results. However, none of them report performance across clinically relevant data splits. Specifically, the performance where the development and test sets are split in time (retro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03851","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/2106.03851/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":"2106.03851","created_at":"2026-07-05T02:47:09.777960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03851v1","created_at":"2026-07-05T02:47:09.777960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03851","created_at":"2026-07-05T02:47:09.777960+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCMATCHMGSPH","created_at":"2026-07-05T02:47:09.777960+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCMATCHMGSPH256E","created_at":"2026-07-05T02:47:09.777960+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCMATCHM","created_at":"2026-07-05T02:47:09.777960+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/BCMATCHMGSPH256ER6LXTCYSSP","json":"https://pith.science/pith/BCMATCHMGSPH256ER6LXTCYSSP.json","graph_json":"https://pith.science/api/pith-number/BCMATCHMGSPH256ER6LXTCYSSP/graph.json","events_json":"https://pith.science/api/pith-number/BCMATCHMGSPH256ER6LXTCYSSP/events.json","paper":"https://pith.science/paper/BCMATCHM"},"agent_actions":{"view_html":"https://pith.science/pith/BCMATCHMGSPH256ER6LXTCYSSP","download_json":"https://pith.science/pith/BCMATCHMGSPH256ER6LXTCYSSP.json","view_paper":"https://pith.science/paper/BCMATCHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03851&json=true","fetch_graph":"https://pith.science/api/pith-number/BCMATCHMGSPH256ER6LXTCYSSP/graph.json","fetch_events":"https://pith.science/api/pith-number/BCMATCHMGSPH256ER6LXTCYSSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCMATCHMGSPH256ER6LXTCYSSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCMATCHMGSPH256ER6LXTCYSSP/action/storage_attestation","attest_author":"https://pith.science/pith/BCMATCHMGSPH256ER6LXTCYSSP/action/author_attestation","sign_citation":"https://pith.science/pith/BCMATCHMGSPH256ER6LXTCYSSP/action/citation_signature","submit_replication":"https://pith.science/pith/BCMATCHMGSPH256ER6LXTCYSSP/action/replication_record"}},"created_at":"2026-07-05T02:47:09.777960+00:00","updated_at":"2026-07-05T02:47:09.777960+00:00"}