{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SLKFH2D6SUTGVVWZZPXU4XFE66","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"00240617fe494538f45308d501d12fea0aab0b1c08ab80d074ebab070eebd918","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T23:03:08Z","title_canon_sha256":"0a52d1e074baaf9339f42c4bfce34467e681dbda73bca4f604ce4cbcb8be8bd1"},"schema_version":"1.0","source":{"id":"2505.24059","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24059","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24059v1","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24059","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"pith_short_12","alias_value":"SLKFH2D6SUTG","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"pith_short_16","alias_value":"SLKFH2D6SUTGVVWZ","created_at":"2026-07-05T11:12:40Z"},{"alias_kind":"pith_short_8","alias_value":"SLKFH2D6","created_at":"2026-07-05T11:12:40Z"}],"graph_snapshots":[{"event_id":"sha256:21653996723724e10319a3b491607996c27d0f8371ce162fb81ba8c4a8a87398","target":"graph","created_at":"2026-07-05T11:12:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.24059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although many previous studies have carried out multimodal learning with real-time MRI data that captures the audio-visual kinematics of the vocal tract during speech, these studies have been limited by their reliance on multi-speaker corpora. This prevents such models from learning a detailed relationship between acoustics and articulation due to considerable cross-speaker variability. In this study, we develop unimodal audio and video models as well as multimodal models for phoneme recognition using a long-form single-speaker MRI corpus, with the goal of disentangling and interpreting the co","authors_text":"Dani Byrd, Hong Nguyen, Jihwan Lee, Louis Goldstein, Sean Foley, Shrikanth Narayanan, Sudarsana Reddy Kadiri","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T23:03:08Z","title":"Towards disentangling the contributions of articulation and acoustics in multimodal phoneme recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24059","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4f338e50f1e2ae673acc86b773590ae6675fbd073ddf1e63c20ee89bd36e1c45","target":"record","created_at":"2026-07-05T11:12:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"00240617fe494538f45308d501d12fea0aab0b1c08ab80d074ebab070eebd918","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T23:03:08Z","title_canon_sha256":"0a52d1e074baaf9339f42c4bfce34467e681dbda73bca4f604ce4cbcb8be8bd1"},"schema_version":"1.0","source":{"id":"2505.24059","kind":"arxiv","version":1}},"canonical_sha256":"92d453e87e95266ad6d9cbef4e5ca4f7b4c1ab0b7ade87aa59dab977053ce4e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92d453e87e95266ad6d9cbef4e5ca4f7b4c1ab0b7ade87aa59dab977053ce4e3","first_computed_at":"2026-07-05T11:12:40.963719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:40.963719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wuYiRLvYiVGHaYf0IqfebY/I2dAFJUyYvDizEwZ8pEA0UW66OfZAQshkbz7l42VGY3i0/NA/9/TW9DgFJ3W8Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:40.964213Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24059","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f338e50f1e2ae673acc86b773590ae6675fbd073ddf1e63c20ee89bd36e1c45","sha256:21653996723724e10319a3b491607996c27d0f8371ce162fb81ba8c4a8a87398"],"state_sha256":"bb4b10816442fcdccfcb7a45a82f9b5b2ca3088df39352b787969608bb78cd38"}