{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XKA3IIEJMIFAYPV64DFA4DFWPM","short_pith_number":"pith:XKA3IIEJ","schema_version":"1.0","canonical_sha256":"ba81b42089620a0c3ebee0ca0e0cb67b29789ed164cd9c94e35edfa1e14d04d6","source":{"kind":"arxiv","id":"2008.06607","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised Contrastive Video-Speech Representation Learning for Ultrasound","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aris T.Papageorghiou, J. Alison Noble, Jianbo Jiao, Lior Drukker, Mohammad Alsharid, Yifan Cai","submitted_at":"2020-08-14T23:58:23Z","abstract_excerpt":"In medical imaging, manual annotations can be expensive to acquire and sometimes infeasible to access, making conventional deep learning-based models difficult to scale. As a result, it would be beneficial if useful representations could be derived from raw data without the need for manual annotations. In this paper, we propose to address the problem of self-supervised representation learning with multi-modal ultrasound video-speech raw data. For this case, we assume that there is a high correlation between the ultrasound video and the corresponding narrative speech audio of the sonographer. I"},"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":"2008.06607","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-14T23:58:23Z","cross_cats_sorted":[],"title_canon_sha256":"8b5683ee407e168abbc24bd7399a42241b624067203d26166beab8b40c7f94d8","abstract_canon_sha256":"08fb93779f507c4a0cbb975193bd8439be8164800c06c54561470bd19e8a8dbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:30.162060Z","signature_b64":"Jt+QHJYWk9Odt63MgX46O5iWjZdAK04IglXNj9fD9Ep2jWFkDX4M/IF9nT5XOCTlxRSlTuYqe/ZJ9cmF8OLdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba81b42089620a0c3ebee0ca0e0cb67b29789ed164cd9c94e35edfa1e14d04d6","last_reissued_at":"2026-07-05T01:27:30.161655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:30.161655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Contrastive Video-Speech Representation Learning for Ultrasound","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aris T.Papageorghiou, J. Alison Noble, Jianbo Jiao, Lior Drukker, Mohammad Alsharid, Yifan Cai","submitted_at":"2020-08-14T23:58:23Z","abstract_excerpt":"In medical imaging, manual annotations can be expensive to acquire and sometimes infeasible to access, making conventional deep learning-based models difficult to scale. As a result, it would be beneficial if useful representations could be derived from raw data without the need for manual annotations. In this paper, we propose to address the problem of self-supervised representation learning with multi-modal ultrasound video-speech raw data. For this case, we assume that there is a high correlation between the ultrasound video and the corresponding narrative speech audio of the sonographer. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06607","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/2008.06607/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":"2008.06607","created_at":"2026-07-05T01:27:30.161714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.06607v1","created_at":"2026-07-05T01:27:30.161714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06607","created_at":"2026-07-05T01:27:30.161714+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKA3IIEJMIFA","created_at":"2026-07-05T01:27:30.161714+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKA3IIEJMIFAYPV6","created_at":"2026-07-05T01:27:30.161714+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKA3IIEJ","created_at":"2026-07-05T01:27:30.161714+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/XKA3IIEJMIFAYPV64DFA4DFWPM","json":"https://pith.science/pith/XKA3IIEJMIFAYPV64DFA4DFWPM.json","graph_json":"https://pith.science/api/pith-number/XKA3IIEJMIFAYPV64DFA4DFWPM/graph.json","events_json":"https://pith.science/api/pith-number/XKA3IIEJMIFAYPV64DFA4DFWPM/events.json","paper":"https://pith.science/paper/XKA3IIEJ"},"agent_actions":{"view_html":"https://pith.science/pith/XKA3IIEJMIFAYPV64DFA4DFWPM","download_json":"https://pith.science/pith/XKA3IIEJMIFAYPV64DFA4DFWPM.json","view_paper":"https://pith.science/paper/XKA3IIEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.06607&json=true","fetch_graph":"https://pith.science/api/pith-number/XKA3IIEJMIFAYPV64DFA4DFWPM/graph.json","fetch_events":"https://pith.science/api/pith-number/XKA3IIEJMIFAYPV64DFA4DFWPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKA3IIEJMIFAYPV64DFA4DFWPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKA3IIEJMIFAYPV64DFA4DFWPM/action/storage_attestation","attest_author":"https://pith.science/pith/XKA3IIEJMIFAYPV64DFA4DFWPM/action/author_attestation","sign_citation":"https://pith.science/pith/XKA3IIEJMIFAYPV64DFA4DFWPM/action/citation_signature","submit_replication":"https://pith.science/pith/XKA3IIEJMIFAYPV64DFA4DFWPM/action/replication_record"}},"created_at":"2026-07-05T01:27:30.161714+00:00","updated_at":"2026-07-05T01:27:30.161714+00:00"}