{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:27BENKZVZY4KSG43V2BSNWOECJ","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":"a8ed605126c22cf33fe37eb2553aa3bae0362051493e727f26d19c94fa57d318","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-04T06:44:54Z","title_canon_sha256":"cbf1c615785b2c226decaae3c2b3791d0aca9a9bf5f818922e1d7f31c285a9c5"},"schema_version":"1.0","source":{"id":"2606.05763","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05763","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05763v1","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05763","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"pith_short_12","alias_value":"27BENKZVZY4K","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"pith_short_16","alias_value":"27BENKZVZY4KSG43","created_at":"2026-06-05T01:15:02Z"},{"alias_kind":"pith_short_8","alias_value":"27BENKZV","created_at":"2026-06-05T01:15:02Z"}],"graph_snapshots":[{"event_id":"sha256:a9843649b47bcf5fcd2f693bee0cc9925c1c687cbcb83311f896ce9506223078","target":"graph","created_at":"2026-06-05T01:15:02Z","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/2606.05763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Speech Recognition (AVSR) enhances speech recognition robustness by leveraging visual cues, while real-world scenarios remain challenging due to viewpoint variation, audio distortion, and visual occlusion, which degrade modality quality and increase audio-visual asynchrony. In this paper, we propose a novel Modality-aware Multi-view Self-supervised representation framework for robust Audio-Visual Speech Recognition (M2S-AVSR). First, we introduce a multi-view representation learning encoder to learn view-invariant visual speech representations. Next, we employ a modality-aware mod","authors_text":"Cancan Li, Fei Su, Juan Liu, Ming Li","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-04T06:44:54Z","title":"M2S-AVSR: Modality-aware Multi-view Self-supervised Representation for Robust Audio-Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05763","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:dba0f0f27e26d8aa0cffdc9f7d94686c47be0c89d9deb3b94a0b8c9a74d8fd2c","target":"record","created_at":"2026-06-05T01:15:02Z","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":"a8ed605126c22cf33fe37eb2553aa3bae0362051493e727f26d19c94fa57d318","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-04T06:44:54Z","title_canon_sha256":"cbf1c615785b2c226decaae3c2b3791d0aca9a9bf5f818922e1d7f31c285a9c5"},"schema_version":"1.0","source":{"id":"2606.05763","kind":"arxiv","version":1}},"canonical_sha256":"d7c246ab35ce38a91b9bae8326d9c412427ee6ac27d048d5b167c0e230d31e0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7c246ab35ce38a91b9bae8326d9c412427ee6ac27d048d5b167c0e230d31e0b","first_computed_at":"2026-06-05T01:15:02.312570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:02.312570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kThwvt2zRmv+ssjlvteiDC1SXQNBrRrB2yXxjVZ6dLkVAG5ZoPt87bYic9xc3XBhSIndX3owGiw+xtfnIvbWDw==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:02.313074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05763","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dba0f0f27e26d8aa0cffdc9f7d94686c47be0c89d9deb3b94a0b8c9a74d8fd2c","sha256:a9843649b47bcf5fcd2f693bee0cc9925c1c687cbcb83311f896ce9506223078"],"state_sha256":"47750e6292b3cecc0bbae4997c443467ace64364fd27ccffa8417bc75b5cfb71"}