{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5YAD7VBZVEWO7ZCH7HGBJE3UHF","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":"b9c250e7055c9502e674b1a4f98533ceb665650abb6db4bf7d18060dbb04f173","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T14:35:47Z","title_canon_sha256":"37775ff2318d152d3615a6372359d0cd398c31610c458e0dc6807506bba22b3a"},"schema_version":"1.0","source":{"id":"2606.00751","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00751","created_at":"2026-06-02T01:04:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00751v1","created_at":"2026-06-02T01:04:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00751","created_at":"2026-06-02T01:04:04Z"},{"alias_kind":"pith_short_12","alias_value":"5YAD7VBZVEWO","created_at":"2026-06-02T01:04:04Z"},{"alias_kind":"pith_short_16","alias_value":"5YAD7VBZVEWO7ZCH","created_at":"2026-06-02T01:04:04Z"},{"alias_kind":"pith_short_8","alias_value":"5YAD7VBZ","created_at":"2026-06-02T01:04:04Z"}],"graph_snapshots":[{"event_id":"sha256:638231d65d93a6cf24dc474c64c926407f19a19187336749f4326daa1aa638cc","target":"graph","created_at":"2026-06-02T01:04:04Z","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/2606.00751/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Speech Recognition (VSR) aims to recognize speech from visual cues such as lip movements, but its performance is fundamentally limited by viseme ambiguity and pose-induced variations that introduce geometric distortions and occlusions. Existing approaches mainly rely on linguistic context or implicit invariance, leaving visual representations insufficiently robust under non-frontal views. In this work, we propose a pose-aware phoneme-level framework, termed HP-VSR-ResFiLM, that explicitly incorporates head-pose information into visual feature extraction. The proposed framework adopts a ","authors_text":"Haibo Zhang, Matthew Kit Khinn Teng, Takeshi Saitoh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T14:35:47Z","title":"Head-Pose-Aware Visual Speech Recognition with FiLM Modulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00751","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":"sha256:8037ce1afcd25447dc17848df770c3324f6e8535b61182c83e537a1248d61ec6","target":"record","created_at":"2026-06-02T01:04:04Z","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":"b9c250e7055c9502e674b1a4f98533ceb665650abb6db4bf7d18060dbb04f173","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T14:35:47Z","title_canon_sha256":"37775ff2318d152d3615a6372359d0cd398c31610c458e0dc6807506bba22b3a"},"schema_version":"1.0","source":{"id":"2606.00751","kind":"arxiv","version":1}},"canonical_sha256":"ee003fd439a92cefe447f9cc1493743952dd232acdc5fc086ca3159f2c07f66a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee003fd439a92cefe447f9cc1493743952dd232acdc5fc086ca3159f2c07f66a","first_computed_at":"2026-06-02T01:04:04.776064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:04.776064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LZPm5t2QpUrCoKasTj1b1BD7YvakCfLj4/zSVtBHXLH4R4Jx/G6/60Uy6c1PdojjUV9C174DTcx4vkSAhsHKBQ==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:04.776422Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00751","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8037ce1afcd25447dc17848df770c3324f6e8535b61182c83e537a1248d61ec6","sha256:638231d65d93a6cf24dc474c64c926407f19a19187336749f4326daa1aa638cc"],"state_sha256":"42b0457b4193bb5856694e8f993dfa8c5fa165ae50a87777124230da4756fabf"}