{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ERS47LQEHTJGYREGMIYHWY2XBB","short_pith_number":"pith:ERS47LQE","schema_version":"1.0","canonical_sha256":"2465cfae043cd26c448662307b635708752a1ea8c325b7ef827cb09d5a002208","source":{"kind":"arxiv","id":"2504.06088","version":1},"attestation_state":"computed","paper":{"title":"MCAT: Visual Query-Based Localization of Standard Anatomical Clips in Fetal Ultrasound Videos Using Multi-Tier Class-Aware Token Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aris Papageorghiou, Divyanshu Mishra, He Zhao, J. Alison Noble, Netzahualcoyotl Hernandez-Cruz, Olga Patey, Pramit Saha","submitted_at":"2025-04-08T14:29:15Z","abstract_excerpt":"Accurate standard plane acquisition in fetal ultrasound (US) videos is crucial for fetal growth assessment, anomaly detection, and adherence to clinical guidelines. However, manually selecting standard frames is time-consuming and prone to intra- and inter-sonographer variability. Existing methods primarily rely on image-based approaches that capture standard frames and then classify the input frames across different anatomies. This ignores the dynamic nature of video acquisition and its interpretation. To address these challenges, we introduce Multi-Tier Class-Aware Token Transformer (MCAT), "},"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":"2504.06088","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-08T14:29:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1b66cf4fc678d21a907cfc5d13910cf44a0015d3f2b53639cb1b9176d4447028","abstract_canon_sha256":"a277e3bf7d1877fe9d6e8b2871ec0783ffe14d7f960005749233fbae4a0c61e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:15.266154Z","signature_b64":"ipGaPbZr0aKYjvewJqpWicgUs5BbCovezqrRNE7O3/PibfPw7aichJG/YrUM2kbBXhss3Umx93pfxVfQo88uAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2465cfae043cd26c448662307b635708752a1ea8c325b7ef827cb09d5a002208","last_reissued_at":"2026-07-05T10:46:15.265681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:15.265681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MCAT: Visual Query-Based Localization of Standard Anatomical Clips in Fetal Ultrasound Videos Using Multi-Tier Class-Aware Token Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Aris Papageorghiou, Divyanshu Mishra, He Zhao, J. Alison Noble, Netzahualcoyotl Hernandez-Cruz, Olga Patey, Pramit Saha","submitted_at":"2025-04-08T14:29:15Z","abstract_excerpt":"Accurate standard plane acquisition in fetal ultrasound (US) videos is crucial for fetal growth assessment, anomaly detection, and adherence to clinical guidelines. However, manually selecting standard frames is time-consuming and prone to intra- and inter-sonographer variability. Existing methods primarily rely on image-based approaches that capture standard frames and then classify the input frames across different anatomies. This ignores the dynamic nature of video acquisition and its interpretation. To address these challenges, we introduce Multi-Tier Class-Aware Token Transformer (MCAT), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06088","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/2504.06088/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":"2504.06088","created_at":"2026-07-05T10:46:15.265735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.06088v1","created_at":"2026-07-05T10:46:15.265735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06088","created_at":"2026-07-05T10:46:15.265735+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERS47LQEHTJG","created_at":"2026-07-05T10:46:15.265735+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERS47LQEHTJGYREG","created_at":"2026-07-05T10:46:15.265735+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERS47LQE","created_at":"2026-07-05T10:46:15.265735+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/ERS47LQEHTJGYREGMIYHWY2XBB","json":"https://pith.science/pith/ERS47LQEHTJGYREGMIYHWY2XBB.json","graph_json":"https://pith.science/api/pith-number/ERS47LQEHTJGYREGMIYHWY2XBB/graph.json","events_json":"https://pith.science/api/pith-number/ERS47LQEHTJGYREGMIYHWY2XBB/events.json","paper":"https://pith.science/paper/ERS47LQE"},"agent_actions":{"view_html":"https://pith.science/pith/ERS47LQEHTJGYREGMIYHWY2XBB","download_json":"https://pith.science/pith/ERS47LQEHTJGYREGMIYHWY2XBB.json","view_paper":"https://pith.science/paper/ERS47LQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.06088&json=true","fetch_graph":"https://pith.science/api/pith-number/ERS47LQEHTJGYREGMIYHWY2XBB/graph.json","fetch_events":"https://pith.science/api/pith-number/ERS47LQEHTJGYREGMIYHWY2XBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERS47LQEHTJGYREGMIYHWY2XBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERS47LQEHTJGYREGMIYHWY2XBB/action/storage_attestation","attest_author":"https://pith.science/pith/ERS47LQEHTJGYREGMIYHWY2XBB/action/author_attestation","sign_citation":"https://pith.science/pith/ERS47LQEHTJGYREGMIYHWY2XBB/action/citation_signature","submit_replication":"https://pith.science/pith/ERS47LQEHTJGYREGMIYHWY2XBB/action/replication_record"}},"created_at":"2026-07-05T10:46:15.265735+00:00","updated_at":"2026-07-05T10:46:15.265735+00:00"}