{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ATQW7QKSHOCGU4F2VNW5OX6P3P","short_pith_number":"pith:ATQW7QKS","schema_version":"1.0","canonical_sha256":"04e16fc1523b846a70baab6dd75fcfdbc7f53f704e5ee5df1dd824cc2501430b","source":{"kind":"arxiv","id":"2406.14576","version":1},"attestation_state":"computed","paper":{"title":"Towards Intelligent Speech Assistants in Operating Rooms: A Multimodal Model for Surgical Workflow Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Andreas Maier, Belen Lojo Rodriguez, Kubilay Can Demir, Seung Hee Yang, Tobias Weise","submitted_at":"2024-06-17T12:47:04Z","abstract_excerpt":"To develop intelligent speech assistants and integrate them seamlessly with intra-operative decision-support frameworks, accurate and efficient surgical phase recognition is a prerequisite. In this study, we propose a multimodal framework based on Gated Multimodal Units (GMU) and Multi-Stage Temporal Convolutional Networks (MS-TCN) to recognize surgical phases of port-catheter placement operations. Our method merges speech and image models and uses them separately in different surgical phases. Based on the evaluation of 28 operations, we report a frame-wise accuracy of 92.65 $\\pm$ 3.52% and an"},"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":"2406.14576","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-17T12:47:04Z","cross_cats_sorted":[],"title_canon_sha256":"ea491a0f92dd6255ee42726097d561573427532b235a8cb030f12f256b2b7510","abstract_canon_sha256":"1d17b426738177def56d9c78bb0d00ebb53ca40510934efc5abcc9b48a761165"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:05.366111Z","signature_b64":"x6edONkbVKZzhH6Ydzxo0KXfCQ1aETb0xUL6J9+3bjFwAawGA0oXM2upnPDsVokavnSSJWFmlEvjmSBHmoLmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04e16fc1523b846a70baab6dd75fcfdbc7f53f704e5ee5df1dd824cc2501430b","last_reissued_at":"2026-07-05T08:35:05.365642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:05.365642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Intelligent Speech Assistants in Operating Rooms: A Multimodal Model for Surgical Workflow Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Andreas Maier, Belen Lojo Rodriguez, Kubilay Can Demir, Seung Hee Yang, Tobias Weise","submitted_at":"2024-06-17T12:47:04Z","abstract_excerpt":"To develop intelligent speech assistants and integrate them seamlessly with intra-operative decision-support frameworks, accurate and efficient surgical phase recognition is a prerequisite. In this study, we propose a multimodal framework based on Gated Multimodal Units (GMU) and Multi-Stage Temporal Convolutional Networks (MS-TCN) to recognize surgical phases of port-catheter placement operations. Our method merges speech and image models and uses them separately in different surgical phases. Based on the evaluation of 28 operations, we report a frame-wise accuracy of 92.65 $\\pm$ 3.52% and an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14576","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/2406.14576/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":"2406.14576","created_at":"2026-07-05T08:35:05.365699+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14576v1","created_at":"2026-07-05T08:35:05.365699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14576","created_at":"2026-07-05T08:35:05.365699+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATQW7QKSHOCG","created_at":"2026-07-05T08:35:05.365699+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATQW7QKSHOCGU4F2","created_at":"2026-07-05T08:35:05.365699+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATQW7QKS","created_at":"2026-07-05T08:35:05.365699+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.22500","citing_title":"OR-VSKC: Resolving Visual-Semantic Knowledge Conflicts in Operating Rooms with Synthetic Data-Guided Alignment","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ATQW7QKSHOCGU4F2VNW5OX6P3P","json":"https://pith.science/pith/ATQW7QKSHOCGU4F2VNW5OX6P3P.json","graph_json":"https://pith.science/api/pith-number/ATQW7QKSHOCGU4F2VNW5OX6P3P/graph.json","events_json":"https://pith.science/api/pith-number/ATQW7QKSHOCGU4F2VNW5OX6P3P/events.json","paper":"https://pith.science/paper/ATQW7QKS"},"agent_actions":{"view_html":"https://pith.science/pith/ATQW7QKSHOCGU4F2VNW5OX6P3P","download_json":"https://pith.science/pith/ATQW7QKSHOCGU4F2VNW5OX6P3P.json","view_paper":"https://pith.science/paper/ATQW7QKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14576&json=true","fetch_graph":"https://pith.science/api/pith-number/ATQW7QKSHOCGU4F2VNW5OX6P3P/graph.json","fetch_events":"https://pith.science/api/pith-number/ATQW7QKSHOCGU4F2VNW5OX6P3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATQW7QKSHOCGU4F2VNW5OX6P3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATQW7QKSHOCGU4F2VNW5OX6P3P/action/storage_attestation","attest_author":"https://pith.science/pith/ATQW7QKSHOCGU4F2VNW5OX6P3P/action/author_attestation","sign_citation":"https://pith.science/pith/ATQW7QKSHOCGU4F2VNW5OX6P3P/action/citation_signature","submit_replication":"https://pith.science/pith/ATQW7QKSHOCGU4F2VNW5OX6P3P/action/replication_record"}},"created_at":"2026-07-05T08:35:05.365699+00:00","updated_at":"2026-07-05T08:35:05.365699+00:00"}