{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RDD4AZXZQSROS63EE5R3YSQWQD","short_pith_number":"pith:RDD4AZXZ","canonical_record":{"source":{"id":"2410.16438","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-21T19:02:13Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"e7f4b95ed4f03f938e06e6d5dbba3d2dfdcecb207b42c0de17c40feac51555e6","abstract_canon_sha256":"60db55c2c77733f27ac54e50d1532535a013f0983c6978808bc1ca6c5ca79007"},"schema_version":"1.0"},"canonical_sha256":"88c7c066f984a2e97b642763bc4a1680ff8f1234c390fa9ee8d00e3b1524a4a6","source":{"kind":"arxiv","id":"2410.16438","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16438","created_at":"2026-07-05T09:24:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16438v1","created_at":"2026-07-05T09:24:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16438","created_at":"2026-07-05T09:24:02Z"},{"alias_kind":"pith_short_12","alias_value":"RDD4AZXZQSRO","created_at":"2026-07-05T09:24:02Z"},{"alias_kind":"pith_short_16","alias_value":"RDD4AZXZQSROS63E","created_at":"2026-07-05T09:24:02Z"},{"alias_kind":"pith_short_8","alias_value":"RDD4AZXZ","created_at":"2026-07-05T09:24:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RDD4AZXZQSROS63EE5R3YSQWQD","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16438","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-21T19:02:13Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"e7f4b95ed4f03f938e06e6d5dbba3d2dfdcecb207b42c0de17c40feac51555e6","abstract_canon_sha256":"60db55c2c77733f27ac54e50d1532535a013f0983c6978808bc1ca6c5ca79007"},"schema_version":"1.0"},"canonical_sha256":"88c7c066f984a2e97b642763bc4a1680ff8f1234c390fa9ee8d00e3b1524a4a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:02.171795Z","signature_b64":"eiXp8paDYJ4lYrBPDhDK3hauoDUU1p5ET7FAKbtWEkovbXNSsMYNfbdvusyRFc6JnuFWvB5vFRV5YZcUc59nCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88c7c066f984a2e97b642763bc4a1680ff8f1234c390fa9ee8d00e3b1524a4a6","last_reissued_at":"2026-07-05T09:24:02.171250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:02.171250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16438","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:24:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k2hRmCIKFUTac5Gn6w9ZBNjnmrwu+9Uq9ODvaFxubzmJ8XFzGLEkNqP+yMlbwibKxnub/bv0PNFGow4+JGHrBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:56:56.900182Z"},"content_sha256":"96fc634d75e90f94e975cf5eccc8b8e045bf9431afcb4b938b55f250f0182504","schema_version":"1.0","event_id":"sha256:96fc634d75e90f94e975cf5eccc8b8e045bf9431afcb4b938b55f250f0182504"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RDD4AZXZQSROS63EE5R3YSQWQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech 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":"Chen Chen, Dong Wang, Lantian Li, Li Guo, Xiaolou Li, Zehua Liu","submitted_at":"2024-10-21T19:02:13Z","abstract_excerpt":"Visual Speech Recognition (VSR) aims to recognize corresponding text by analyzing visual information from lip movements. Due to the high variability and weak information of lip movements, VSR tasks require effectively utilizing any information from any source and at any level. In this paper, we propose a VSR method based on audio-visual cross-modal alignment, named AlignVSR. The method leverages the audio modality as an auxiliary information source and utilizes the global and local correspondence between the audio and visual modalities to improve visual-to-text inference. Specifically, the met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16438","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/2410.16438/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:24:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4/CJQeDXobSQ/w7FcV4N2gA4jKtkX6SrArKxuhBoWJCIPxL1S4rlbuXT9A6PNiDHBssQDM4H0HUF2WtPbdgCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:56:56.900697Z"},"content_sha256":"c20b2b783043b2d4151536fbc91cf58126e01de2bf9da8e7507fa67a66dbe8cd","schema_version":"1.0","event_id":"sha256:c20b2b783043b2d4151536fbc91cf58126e01de2bf9da8e7507fa67a66dbe8cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RDD4AZXZQSROS63EE5R3YSQWQD/bundle.json","state_url":"https://pith.science/pith/RDD4AZXZQSROS63EE5R3YSQWQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RDD4AZXZQSROS63EE5R3YSQWQD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T12:56:56Z","links":{"resolver":"https://pith.science/pith/RDD4AZXZQSROS63EE5R3YSQWQD","bundle":"https://pith.science/pith/RDD4AZXZQSROS63EE5R3YSQWQD/bundle.json","state":"https://pith.science/pith/RDD4AZXZQSROS63EE5R3YSQWQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RDD4AZXZQSROS63EE5R3YSQWQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RDD4AZXZQSROS63EE5R3YSQWQD","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":"60db55c2c77733f27ac54e50d1532535a013f0983c6978808bc1ca6c5ca79007","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-21T19:02:13Z","title_canon_sha256":"e7f4b95ed4f03f938e06e6d5dbba3d2dfdcecb207b42c0de17c40feac51555e6"},"schema_version":"1.0","source":{"id":"2410.16438","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16438","created_at":"2026-07-05T09:24:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16438v1","created_at":"2026-07-05T09:24:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16438","created_at":"2026-07-05T09:24:02Z"},{"alias_kind":"pith_short_12","alias_value":"RDD4AZXZQSRO","created_at":"2026-07-05T09:24:02Z"},{"alias_kind":"pith_short_16","alias_value":"RDD4AZXZQSROS63E","created_at":"2026-07-05T09:24:02Z"},{"alias_kind":"pith_short_8","alias_value":"RDD4AZXZ","created_at":"2026-07-05T09:24:02Z"}],"graph_snapshots":[{"event_id":"sha256:c20b2b783043b2d4151536fbc91cf58126e01de2bf9da8e7507fa67a66dbe8cd","target":"graph","created_at":"2026-07-05T09:24:02Z","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/2410.16438/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 corresponding text by analyzing visual information from lip movements. Due to the high variability and weak information of lip movements, VSR tasks require effectively utilizing any information from any source and at any level. In this paper, we propose a VSR method based on audio-visual cross-modal alignment, named AlignVSR. The method leverages the audio modality as an auxiliary information source and utilizes the global and local correspondence between the audio and visual modalities to improve visual-to-text inference. Specifically, the met","authors_text":"Chen Chen, Dong Wang, Lantian Li, Li Guo, Xiaolou Li, Zehua Liu","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-21T19:02:13Z","title":"AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16438","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":"sha256:96fc634d75e90f94e975cf5eccc8b8e045bf9431afcb4b938b55f250f0182504","target":"record","created_at":"2026-07-05T09:24:02Z","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":"60db55c2c77733f27ac54e50d1532535a013f0983c6978808bc1ca6c5ca79007","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-21T19:02:13Z","title_canon_sha256":"e7f4b95ed4f03f938e06e6d5dbba3d2dfdcecb207b42c0de17c40feac51555e6"},"schema_version":"1.0","source":{"id":"2410.16438","kind":"arxiv","version":1}},"canonical_sha256":"88c7c066f984a2e97b642763bc4a1680ff8f1234c390fa9ee8d00e3b1524a4a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88c7c066f984a2e97b642763bc4a1680ff8f1234c390fa9ee8d00e3b1524a4a6","first_computed_at":"2026-07-05T09:24:02.171250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:02.171250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eiXp8paDYJ4lYrBPDhDK3hauoDUU1p5ET7FAKbtWEkovbXNSsMYNfbdvusyRFc6JnuFWvB5vFRV5YZcUc59nCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:02.171795Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16438","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96fc634d75e90f94e975cf5eccc8b8e045bf9431afcb4b938b55f250f0182504","sha256:c20b2b783043b2d4151536fbc91cf58126e01de2bf9da8e7507fa67a66dbe8cd"],"state_sha256":"12c896682cd6a6374af9c0389ddbbc34128f816e58b50e886b9cab22f970fe1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dmdw1hpY0VLQirSwwTPqK7+qFISui7foV8RP8n+Ct3Wg1G1SmX2ZkifQVczq2QAaw0wJlqHRzPtEp8jvB+s8DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:56:56.906021Z","bundle_sha256":"536152086d4c6ea00452a5182d7000f5c8b3a9ec9a6b223e3478741a14b8819c"}}