{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BFRQCMAX3ZYD3DQVLCE27YH5GZ","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":"2e960dc5563e04e08da591143b0ccbb51eb296920831ff3398043b20b7a56e0a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T00:38:39Z","title_canon_sha256":"9d8995e4800a4027838fc5f86b97875d875c8b881a651b134ea20a47f725f5bf"},"schema_version":"1.0","source":{"id":"2507.18863","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18863","created_at":"2026-06-02T01:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18863v2","created_at":"2026-06-02T01:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18863","created_at":"2026-06-02T01:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"BFRQCMAX3ZYD","created_at":"2026-06-02T01:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"BFRQCMAX3ZYD3DQV","created_at":"2026-06-02T01:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"BFRQCMAX","created_at":"2026-06-02T01:03:32Z"}],"graph_snapshots":[{"event_id":"sha256:68b75f2c442913c9712f72289de3f0fad6c41d0aae2503da03c09e7b013417b8","target":"graph","created_at":"2026-06-02T01:03:32Z","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/2507.18863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Automatic Speech Recognition (V-ASR) is a challenging task that involves interpreting spoken language solely from visual information, such as lip movements and facial expressions. This task is notably challenging due to the absence of auditory cues and the visual ambiguity of phonemes that exhibit similar visemes-distinct sounds that appear identical in lip motions. Existing methods often aim to predict words or characters directly from visual cues, but they commonly suffer from high error rates due to viseme ambiguity and require large amounts of pre-training data. We propose a novel p","authors_text":"Haibo Zhang, Matthew Kit Khinn Teng, Takeshi Saitoh","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T00:38:39Z","title":"Phoneme-Level Visual Speech Recognition via Point-Visual Fusion and Language Model Reconstruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18863","kind":"arxiv","version":2},"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":"sha256:3235cdbf95bcaad10111ca03853cc15cc716a555174002fdc38bae6df932adb9","target":"record","created_at":"2026-06-02T01:03:32Z","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":"2e960dc5563e04e08da591143b0ccbb51eb296920831ff3398043b20b7a56e0a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T00:38:39Z","title_canon_sha256":"9d8995e4800a4027838fc5f86b97875d875c8b881a651b134ea20a47f725f5bf"},"schema_version":"1.0","source":{"id":"2507.18863","kind":"arxiv","version":2}},"canonical_sha256":"0963013017de703d8e155889afe0fd364886d1b15fd2837eccd6be38113d66a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0963013017de703d8e155889afe0fd364886d1b15fd2837eccd6be38113d66a7","first_computed_at":"2026-06-02T01:03:32.806731Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:32.806731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C+hulqzkSP39xPTBi0DOQNcDNNyqx2vHitStihXSWbVMvsVR6QGRxn/1OAci6LIUDiXpm2MGfcK3yzuTD08WAQ==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:32.807228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18863","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3235cdbf95bcaad10111ca03853cc15cc716a555174002fdc38bae6df932adb9","sha256:68b75f2c442913c9712f72289de3f0fad6c41d0aae2503da03c09e7b013417b8"],"state_sha256":"b028972c8221e068ce2ab7ad5fdd9ade72c52ef929678d9fe90765b1020208d3"}