{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ATQNMF3BRTHFSNLMWR5RCPGA66","short_pith_number":"pith:ATQNMF3B","canonical_record":{"source":{"id":"2406.10082","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-14T14:36:54Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"1830c94b2deb42293954c80fbfb501b3d41fc3a22100b95bc2ac604e62721ccf","abstract_canon_sha256":"57825a3d40148e81807a62b4601c047ded19442ed3161794dde15d5467ebfb59"},"schema_version":"1.0"},"canonical_sha256":"04e0d617618cce59356cb47b113cc0f7a79cabc7eab05b294017f1849e1806a6","source":{"kind":"arxiv","id":"2406.10082","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10082","created_at":"2026-07-05T09:37:54Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10082v3","created_at":"2026-07-05T09:37:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10082","created_at":"2026-07-05T09:37:54Z"},{"alias_kind":"pith_short_12","alias_value":"ATQNMF3BRTHF","created_at":"2026-07-05T09:37:54Z"},{"alias_kind":"pith_short_16","alias_value":"ATQNMF3BRTHFSNLM","created_at":"2026-07-05T09:37:54Z"},{"alias_kind":"pith_short_8","alias_value":"ATQNMF3B","created_at":"2026-07-05T09:37:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ATQNMF3BRTHFSNLMWR5RCPGA66","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10082","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-14T14:36:54Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"1830c94b2deb42293954c80fbfb501b3d41fc3a22100b95bc2ac604e62721ccf","abstract_canon_sha256":"57825a3d40148e81807a62b4601c047ded19442ed3161794dde15d5467ebfb59"},"schema_version":"1.0"},"canonical_sha256":"04e0d617618cce59356cb47b113cc0f7a79cabc7eab05b294017f1849e1806a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:54.987018Z","signature_b64":"44j6dAF/jMR1zYojJzymm6VzmFQ54+260FibvtLxa0OF3E5oR6lHz0qP5LY17DLNSDRTVXgPqWKAompP/4XjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04e0d617618cce59356cb47b113cc0f7a79cabc7eab05b294017f1849e1806a6","last_reissued_at":"2026-07-05T09:37:54.986503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:54.986503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10082","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:37:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b5S9n3kSNIbek1QUign8mHrb7se3cXk78BkDC0nsm1a9WiS9pvIXXVSs5IJtsVDjrh08PyXWT+CKI839qYP+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:59:25.377239Z"},"content_sha256":"82467719913bdcda384e7b924262a11bfc0b3e0d48036ee042151d8c07013ff5","schema_version":"1.0","event_id":"sha256:82467719913bdcda384e7b924262a11bfc0b3e0d48036ee042151d8c07013ff5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ATQNMF3BRTHFSNLMWR5RCPGA66","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Andrew Rouditchenko, Hilde Kuehne, James Glass, Leonid Karlinsky, Rogerio Feris, Samuel Thomas, Yuan Gong","submitted_at":"2024-06-14T14:36:54Z","abstract_excerpt":"Audio-Visual Speech Recognition (AVSR) uses lip-based video to improve performance in noise. Since videos are harder to obtain than audio, the video training data of AVSR models is usually limited to a few thousand hours. In contrast, speech models such as Whisper are trained with hundreds of thousands of hours of data, and thus learn a better speech-to-text decoder. The huge training data difference motivates us to adapt Whisper to handle video inputs. Inspired by Flamingo which injects visual features into language models, we propose Whisper-Flamingo which integrates visual features into the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10082","kind":"arxiv","version":3},"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/2406.10082/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":"2026-07-05T09:37:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IcZohYam9I/LmED+CHdfimvlnuMZ4ctvL5vkreeq1pIFzIh8yMfBZize7e52c7Ho0Tnzg7tNI2IFPp/Uf6zgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:59:25.377621Z"},"content_sha256":"21c68014e95c8dfc239ae6e7684d9b7a5e983bd3eae05d89650674f1b70f09be","schema_version":"1.0","event_id":"sha256:21c68014e95c8dfc239ae6e7684d9b7a5e983bd3eae05d89650674f1b70f09be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ATQNMF3BRTHFSNLMWR5RCPGA66/bundle.json","state_url":"https://pith.science/pith/ATQNMF3BRTHFSNLMWR5RCPGA66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ATQNMF3BRTHFSNLMWR5RCPGA66/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":"2026-08-05T03:59:25Z","links":{"resolver":"https://pith.science/pith/ATQNMF3BRTHFSNLMWR5RCPGA66","bundle":"https://pith.science/pith/ATQNMF3BRTHFSNLMWR5RCPGA66/bundle.json","state":"https://pith.science/pith/ATQNMF3BRTHFSNLMWR5RCPGA66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ATQNMF3BRTHFSNLMWR5RCPGA66/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ATQNMF3BRTHFSNLMWR5RCPGA66","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":"57825a3d40148e81807a62b4601c047ded19442ed3161794dde15d5467ebfb59","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-14T14:36:54Z","title_canon_sha256":"1830c94b2deb42293954c80fbfb501b3d41fc3a22100b95bc2ac604e62721ccf"},"schema_version":"1.0","source":{"id":"2406.10082","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10082","created_at":"2026-07-05T09:37:54Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10082v3","created_at":"2026-07-05T09:37:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10082","created_at":"2026-07-05T09:37:54Z"},{"alias_kind":"pith_short_12","alias_value":"ATQNMF3BRTHF","created_at":"2026-07-05T09:37:54Z"},{"alias_kind":"pith_short_16","alias_value":"ATQNMF3BRTHFSNLM","created_at":"2026-07-05T09:37:54Z"},{"alias_kind":"pith_short_8","alias_value":"ATQNMF3B","created_at":"2026-07-05T09:37:54Z"}],"graph_snapshots":[{"event_id":"sha256:21c68014e95c8dfc239ae6e7684d9b7a5e983bd3eae05d89650674f1b70f09be","target":"graph","created_at":"2026-07-05T09:37:54Z","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/2406.10082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Speech Recognition (AVSR) uses lip-based video to improve performance in noise. Since videos are harder to obtain than audio, the video training data of AVSR models is usually limited to a few thousand hours. In contrast, speech models such as Whisper are trained with hundreds of thousands of hours of data, and thus learn a better speech-to-text decoder. The huge training data difference motivates us to adapt Whisper to handle video inputs. Inspired by Flamingo which injects visual features into language models, we propose Whisper-Flamingo which integrates visual features into the","authors_text":"Andrew Rouditchenko, Hilde Kuehne, James Glass, Leonid Karlinsky, Rogerio Feris, Samuel Thomas, Yuan Gong","cross_cats":["cs.CV","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-14T14:36:54Z","title":"Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10082","kind":"arxiv","version":3},"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":"sha256:82467719913bdcda384e7b924262a11bfc0b3e0d48036ee042151d8c07013ff5","target":"record","created_at":"2026-07-05T09:37:54Z","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":"57825a3d40148e81807a62b4601c047ded19442ed3161794dde15d5467ebfb59","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-14T14:36:54Z","title_canon_sha256":"1830c94b2deb42293954c80fbfb501b3d41fc3a22100b95bc2ac604e62721ccf"},"schema_version":"1.0","source":{"id":"2406.10082","kind":"arxiv","version":3}},"canonical_sha256":"04e0d617618cce59356cb47b113cc0f7a79cabc7eab05b294017f1849e1806a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04e0d617618cce59356cb47b113cc0f7a79cabc7eab05b294017f1849e1806a6","first_computed_at":"2026-07-05T09:37:54.986503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:37:54.986503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"44j6dAF/jMR1zYojJzymm6VzmFQ54+260FibvtLxa0OF3E5oR6lHz0qP5LY17DLNSDRTVXgPqWKAompP/4XjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:37:54.987018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10082","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82467719913bdcda384e7b924262a11bfc0b3e0d48036ee042151d8c07013ff5","sha256:21c68014e95c8dfc239ae6e7684d9b7a5e983bd3eae05d89650674f1b70f09be"],"state_sha256":"447d6208e0056e849c4b222948cfff64b265f47917d8ed624d43937519404bcd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"06TMYVM5fp2+CgkzT+wd1FvdTg2iO64L4n8kS1dI0AFN9NqX4UeoS4WovInxkLDL4N3Hd3tAXKwExMtMYZA0Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:59:25.380053Z","bundle_sha256":"84622fd0ccb396fd3a78416300872f2b0135ebbc514c47057b5c4665c16b37b9"}}