{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BGWWX67DWVYM4M464L2QFL7EAT","short_pith_number":"pith:BGWWX67D","canonical_record":{"source":{"id":"2409.12370","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-19T00:08:28Z","cross_cats_sorted":["cs.CL","cs.CV","cs.SD"],"title_canon_sha256":"e9a83f7e0b87d2ba12f6098c2491cc033cded22ebbdd2180fba7909fea157d17","abstract_canon_sha256":"33a50da710470ca65571297c41eba3c2c303d05fdfc834a21a40f1762d902db2"},"schema_version":"1.0"},"canonical_sha256":"09ad6bfbe3b570ce339ee2f502afe404fe28c921eff47aaeb8fa46e7ff212e0c","source":{"kind":"arxiv","id":"2409.12370","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12370","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12370v1","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12370","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"pith_short_12","alias_value":"BGWWX67DWVYM","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"pith_short_16","alias_value":"BGWWX67DWVYM4M46","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"pith_short_8","alias_value":"BGWWX67D","created_at":"2026-07-05T09:08:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BGWWX67DWVYM4M464L2QFL7EAT","target":"record","payload":{"canonical_record":{"source":{"id":"2409.12370","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-19T00:08:28Z","cross_cats_sorted":["cs.CL","cs.CV","cs.SD"],"title_canon_sha256":"e9a83f7e0b87d2ba12f6098c2491cc033cded22ebbdd2180fba7909fea157d17","abstract_canon_sha256":"33a50da710470ca65571297c41eba3c2c303d05fdfc834a21a40f1762d902db2"},"schema_version":"1.0"},"canonical_sha256":"09ad6bfbe3b570ce339ee2f502afe404fe28c921eff47aaeb8fa46e7ff212e0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:52.865838Z","signature_b64":"tZyM3apJhlKJb28u7L/ZAg5zXVjWz2IEky1LE3seN7j0Ro6bZvPvCaIZSHVLlSBR2HAnzvZ+J6bDWJSsUsvdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09ad6bfbe3b570ce339ee2f502afe404fe28c921eff47aaeb8fa46e7ff212e0c","last_reissued_at":"2026-07-05T09:08:52.865394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:52.865394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.12370","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":"2026-07-05T09:08:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I5dbO0el7x0n71BT0zD7RYnAFzpxine/IA2W2Ti+Q/j8wbb6d7PpJ32C40yN73B6R1ybkSlg3aBzjW5PKpluBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:44:56.599795Z"},"content_sha256":"4285238d5480f2f6d4a429746bdbe37b09f6199c91af96b6004693ec7ebe8606","schema_version":"1.0","event_id":"sha256:4285238d5480f2f6d4a429746bdbe37b09f6199c91af96b6004693ec7ebe8606"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BGWWX67DWVYM4M464L2QFL7EAT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Audiovisual Speech Recognition Models with Mixture-of-Experts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Ruihua Song, Shinji Watanabe, Xuankai Chang, Yichen Lu, Yifan Peng, Yihan Wu","submitted_at":"2024-09-19T00:08:28Z","abstract_excerpt":"Visual signals can enhance audiovisual speech recognition accuracy by providing additional contextual information. Given the complexity of visual signals, an audiovisual speech recognition model requires robust generalization capabilities across diverse video scenarios, presenting a significant challenge. In this paper, we introduce EVA, leveraging the mixture-of-Experts for audioVisual ASR to perform robust speech recognition for ``in-the-wild'' videos. Specifically, we first encode visual information into visual tokens sequence and map them into speech space by a lightweight projection. Then"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12370","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/2409.12370/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":"2026-07-05T09:08:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NFJfa6UH6kdpWxQlgbd37UbL2wPRXVHeuEWK9DPe8GlzL+j39pRZ0pykNH/tur36AMzSzlodiQsfPcPlfnhaCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:44:56.600997Z"},"content_sha256":"afc6b318f405f8d3fa36b2ce162ce3a19bb2a7f1485965480126c7c4927b2f98","schema_version":"1.0","event_id":"sha256:afc6b318f405f8d3fa36b2ce162ce3a19bb2a7f1485965480126c7c4927b2f98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BGWWX67DWVYM4M464L2QFL7EAT/bundle.json","state_url":"https://pith.science/pith/BGWWX67DWVYM4M464L2QFL7EAT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BGWWX67DWVYM4M464L2QFL7EAT/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":"2026-08-04T12:44:56Z","links":{"resolver":"https://pith.science/pith/BGWWX67DWVYM4M464L2QFL7EAT","bundle":"https://pith.science/pith/BGWWX67DWVYM4M464L2QFL7EAT/bundle.json","state":"https://pith.science/pith/BGWWX67DWVYM4M464L2QFL7EAT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BGWWX67DWVYM4M464L2QFL7EAT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BGWWX67DWVYM4M464L2QFL7EAT","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":"33a50da710470ca65571297c41eba3c2c303d05fdfc834a21a40f1762d902db2","cross_cats_sorted":["cs.CL","cs.CV","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-19T00:08:28Z","title_canon_sha256":"e9a83f7e0b87d2ba12f6098c2491cc033cded22ebbdd2180fba7909fea157d17"},"schema_version":"1.0","source":{"id":"2409.12370","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12370","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12370v1","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12370","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"pith_short_12","alias_value":"BGWWX67DWVYM","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"pith_short_16","alias_value":"BGWWX67DWVYM4M46","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"pith_short_8","alias_value":"BGWWX67D","created_at":"2026-07-05T09:08:52Z"}],"graph_snapshots":[{"event_id":"sha256:afc6b318f405f8d3fa36b2ce162ce3a19bb2a7f1485965480126c7c4927b2f98","target":"graph","created_at":"2026-07-05T09:08:52Z","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/2409.12370/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual signals can enhance audiovisual speech recognition accuracy by providing additional contextual information. Given the complexity of visual signals, an audiovisual speech recognition model requires robust generalization capabilities across diverse video scenarios, presenting a significant challenge. In this paper, we introduce EVA, leveraging the mixture-of-Experts for audioVisual ASR to perform robust speech recognition for ``in-the-wild'' videos. Specifically, we first encode visual information into visual tokens sequence and map them into speech space by a lightweight projection. Then","authors_text":"Ruihua Song, Shinji Watanabe, Xuankai Chang, Yichen Lu, Yifan Peng, Yihan Wu","cross_cats":["cs.CL","cs.CV","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-19T00:08:28Z","title":"Robust Audiovisual Speech Recognition Models with Mixture-of-Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12370","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":"sha256:4285238d5480f2f6d4a429746bdbe37b09f6199c91af96b6004693ec7ebe8606","target":"record","created_at":"2026-07-05T09:08:52Z","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":"33a50da710470ca65571297c41eba3c2c303d05fdfc834a21a40f1762d902db2","cross_cats_sorted":["cs.CL","cs.CV","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-19T00:08:28Z","title_canon_sha256":"e9a83f7e0b87d2ba12f6098c2491cc033cded22ebbdd2180fba7909fea157d17"},"schema_version":"1.0","source":{"id":"2409.12370","kind":"arxiv","version":1}},"canonical_sha256":"09ad6bfbe3b570ce339ee2f502afe404fe28c921eff47aaeb8fa46e7ff212e0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09ad6bfbe3b570ce339ee2f502afe404fe28c921eff47aaeb8fa46e7ff212e0c","first_computed_at":"2026-07-05T09:08:52.865394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:52.865394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tZyM3apJhlKJb28u7L/ZAg5zXVjWz2IEky1LE3seN7j0Ro6bZvPvCaIZSHVLlSBR2HAnzvZ+J6bDWJSsUsvdCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:52.865838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.12370","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4285238d5480f2f6d4a429746bdbe37b09f6199c91af96b6004693ec7ebe8606","sha256:afc6b318f405f8d3fa36b2ce162ce3a19bb2a7f1485965480126c7c4927b2f98"],"state_sha256":"af92fa7295810cd689d59d7cba72d212a8517ef84f701e871cb711c6ae1d97fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"573yWMo54u7VzO4oConHdz1+rr5Xq74XVf8+mSeIWlkIrUGHh5IZpjJ7RclXr+rPHokWDWoCqq/qbILmGnmDDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:44:56.669198Z","bundle_sha256":"e4758666dfc7f9bf75b3c30de81642f3dc155cfb8377a3c1787e302431ee0e51"}}