{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MQFMZLIKE2YZBWOMRJT3LAOSA4","short_pith_number":"pith:MQFMZLIK","schema_version":"1.0","canonical_sha256":"640accad0a26b190d9cc8a67b581d207181bcba497c8607da67cd8e58fee847c","source":{"kind":"arxiv","id":"2507.17682","version":1},"attestation_state":"computed","paper":{"title":"Audio-Vision Contrastive Learning for Phonological Class Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andreas Maier, Daiqi Liu, Jana Hutter, Paula Andrea P\\'erez-Toro, Tom\\'as Arias-Vergara","submitted_at":"2025-07-23T16:44:22Z","abstract_excerpt":"Accurate classification of articulatory-phonological features plays a vital role in understanding human speech production and developing robust speech technologies, particularly in clinical contexts where targeted phonemic analysis and therapy can improve disease diagnosis accuracy and personalized rehabilitation. In this work, we propose a multimodal deep learning framework that combines real-time magnetic resonance imaging (rtMRI) and speech signals to classify three key articulatory dimensions: manner of articulation, place of articulation, and voicing. We perform classification on 15 phono"},"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":"2507.17682","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-23T16:44:22Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"6f280206e08d822e8cb1b37521b71df895f0953bb69f1c6801a9b31dd0a4fcdd","abstract_canon_sha256":"ca201cc58fd1afe1e090d697078872535cfd1dc55e7c1653c7cf5883ccad0849"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:16.892869Z","signature_b64":"9//9iSlgCwNxozimVKKnCY9wrnLck5Kjtpwm0ew3RG7dANCzHo13NVvh7DUoV/WhUn/dN6fAJzUwaAvtspscBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"640accad0a26b190d9cc8a67b581d207181bcba497c8607da67cd8e58fee847c","last_reissued_at":"2026-07-05T11:42:16.892467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:16.892467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Vision Contrastive Learning for Phonological Class Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andreas Maier, Daiqi Liu, Jana Hutter, Paula Andrea P\\'erez-Toro, Tom\\'as Arias-Vergara","submitted_at":"2025-07-23T16:44:22Z","abstract_excerpt":"Accurate classification of articulatory-phonological features plays a vital role in understanding human speech production and developing robust speech technologies, particularly in clinical contexts where targeted phonemic analysis and therapy can improve disease diagnosis accuracy and personalized rehabilitation. In this work, we propose a multimodal deep learning framework that combines real-time magnetic resonance imaging (rtMRI) and speech signals to classify three key articulatory dimensions: manner of articulation, place of articulation, and voicing. We perform classification on 15 phono"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17682","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/2507.17682/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":"2507.17682","created_at":"2026-07-05T11:42:16.892522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17682v1","created_at":"2026-07-05T11:42:16.892522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17682","created_at":"2026-07-05T11:42:16.892522+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQFMZLIKE2YZ","created_at":"2026-07-05T11:42:16.892522+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQFMZLIKE2YZBWOM","created_at":"2026-07-05T11:42:16.892522+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQFMZLIK","created_at":"2026-07-05T11:42:16.892522+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/MQFMZLIKE2YZBWOMRJT3LAOSA4","json":"https://pith.science/pith/MQFMZLIKE2YZBWOMRJT3LAOSA4.json","graph_json":"https://pith.science/api/pith-number/MQFMZLIKE2YZBWOMRJT3LAOSA4/graph.json","events_json":"https://pith.science/api/pith-number/MQFMZLIKE2YZBWOMRJT3LAOSA4/events.json","paper":"https://pith.science/paper/MQFMZLIK"},"agent_actions":{"view_html":"https://pith.science/pith/MQFMZLIKE2YZBWOMRJT3LAOSA4","download_json":"https://pith.science/pith/MQFMZLIKE2YZBWOMRJT3LAOSA4.json","view_paper":"https://pith.science/paper/MQFMZLIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17682&json=true","fetch_graph":"https://pith.science/api/pith-number/MQFMZLIKE2YZBWOMRJT3LAOSA4/graph.json","fetch_events":"https://pith.science/api/pith-number/MQFMZLIKE2YZBWOMRJT3LAOSA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQFMZLIKE2YZBWOMRJT3LAOSA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQFMZLIKE2YZBWOMRJT3LAOSA4/action/storage_attestation","attest_author":"https://pith.science/pith/MQFMZLIKE2YZBWOMRJT3LAOSA4/action/author_attestation","sign_citation":"https://pith.science/pith/MQFMZLIKE2YZBWOMRJT3LAOSA4/action/citation_signature","submit_replication":"https://pith.science/pith/MQFMZLIKE2YZBWOMRJT3LAOSA4/action/replication_record"}},"created_at":"2026-07-05T11:42:16.892522+00:00","updated_at":"2026-07-05T11:42:16.892522+00:00"}