{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XXERCPYLWX4BW2FYPUPUSH5IQC","short_pith_number":"pith:XXERCPYL","canonical_record":{"source":{"id":"2409.12319","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-18T21:17:27Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"0ff785e68eeff8a98867570299e673cb54b51a35dc0bb6fb59b456603e91afc1","abstract_canon_sha256":"39e9686f700cd5088ee0451748deaa18dfdefb037c6c158a71c27f9ceea6fc71"},"schema_version":"1.0"},"canonical_sha256":"bdc9113f0bb5f81b68b87d1f491fa8808b74c8a73a27a71300a2b9200c2751c6","source":{"kind":"arxiv","id":"2409.12319","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12319","created_at":"2026-07-05T10:26:07Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12319v2","created_at":"2026-07-05T10:26:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12319","created_at":"2026-07-05T10:26:07Z"},{"alias_kind":"pith_short_12","alias_value":"XXERCPYLWX4B","created_at":"2026-07-05T10:26:07Z"},{"alias_kind":"pith_short_16","alias_value":"XXERCPYLWX4BW2FY","created_at":"2026-07-05T10:26:07Z"},{"alias_kind":"pith_short_8","alias_value":"XXERCPYL","created_at":"2026-07-05T10:26:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XXERCPYLWX4BW2FYPUPUSH5IQC","target":"record","payload":{"canonical_record":{"source":{"id":"2409.12319","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-18T21:17:27Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"0ff785e68eeff8a98867570299e673cb54b51a35dc0bb6fb59b456603e91afc1","abstract_canon_sha256":"39e9686f700cd5088ee0451748deaa18dfdefb037c6c158a71c27f9ceea6fc71"},"schema_version":"1.0"},"canonical_sha256":"bdc9113f0bb5f81b68b87d1f491fa8808b74c8a73a27a71300a2b9200c2751c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:07.551611Z","signature_b64":"G5h02vOVd6ZB/cvBtHho/GGH79lQBO91TPivTHyFVjyAOxvkeUxHJjf8BwAZ6bp1h/Odh4k5bHPbvy4Lz8mQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdc9113f0bb5f81b68b87d1f491fa8808b74c8a73a27a71300a2b9200c2751c6","last_reissued_at":"2026-07-05T10:26:07.551061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:07.551061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.12319","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:26:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IV8fh9LPoPvFdLNM7bE64arkRNMf2aGVWUHAoIlcx+tOAzMCjDuPxoE1o181zqr2YIKi7ajD7EjLAKGrHZ5tCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:09:20.549226Z"},"content_sha256":"c1940c40cad40e93eb9aa0cb23441970d5d4fb79303525bbf0d3a2e31e34ee69","schema_version":"1.0","event_id":"sha256:c1940c40cad40e93eb9aa0cb23441970d5d4fb79303525bbf0d3a2e31e34ee69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XXERCPYLWX4BW2FYPUPUSH5IQC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models are Strong Audio-Visual Speech Recognition Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Alessio Brutti, Daniele Falavigna, Honglie Chen, Maja Pantic, Minsu Kim, Pingchuan Ma, Stavros Petridis, Umberto Cappellazzo","submitted_at":"2024-09-18T21:17:27Z","abstract_excerpt":"Multimodal large language models (MLLMs) have recently become a focal point of research due to their formidable multimodal understanding capabilities. For example, in the audio and speech domains, an LLM can be equipped with (automatic) speech recognition (ASR) abilities by just concatenating the audio tokens, computed with an audio encoder, and the text tokens to achieve state-of-the-art results. On the contrary, tasks like visual and audio-visual speech recognition (VSR/AVSR), which also exploit noise-invariant lip movement information, have received little or no attention. To bridge this ga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12319","kind":"arxiv","version":2},"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/2409.12319/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":"2026-07-05T10:26:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pmBZ1RvBJEQYhOXSPkecX/dOAnSrCvilyKS9vkZ0wD/fmZoVLes6qTsd9oo2B18cKTT0jp7xOjfa7deXK2esDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:09:20.549615Z"},"content_sha256":"50d9cb460c909b9c2726fe6b069618fdc5030a1e7ccb89bdc68ffb0306530abd","schema_version":"1.0","event_id":"sha256:50d9cb460c909b9c2726fe6b069618fdc5030a1e7ccb89bdc68ffb0306530abd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XXERCPYLWX4BW2FYPUPUSH5IQC/bundle.json","state_url":"https://pith.science/pith/XXERCPYLWX4BW2FYPUPUSH5IQC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XXERCPYLWX4BW2FYPUPUSH5IQC/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":"2026-07-07T10:09:20Z","links":{"resolver":"https://pith.science/pith/XXERCPYLWX4BW2FYPUPUSH5IQC","bundle":"https://pith.science/pith/XXERCPYLWX4BW2FYPUPUSH5IQC/bundle.json","state":"https://pith.science/pith/XXERCPYLWX4BW2FYPUPUSH5IQC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XXERCPYLWX4BW2FYPUPUSH5IQC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XXERCPYLWX4BW2FYPUPUSH5IQC","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":"39e9686f700cd5088ee0451748deaa18dfdefb037c6c158a71c27f9ceea6fc71","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-18T21:17:27Z","title_canon_sha256":"0ff785e68eeff8a98867570299e673cb54b51a35dc0bb6fb59b456603e91afc1"},"schema_version":"1.0","source":{"id":"2409.12319","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12319","created_at":"2026-07-05T10:26:07Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12319v2","created_at":"2026-07-05T10:26:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12319","created_at":"2026-07-05T10:26:07Z"},{"alias_kind":"pith_short_12","alias_value":"XXERCPYLWX4B","created_at":"2026-07-05T10:26:07Z"},{"alias_kind":"pith_short_16","alias_value":"XXERCPYLWX4BW2FY","created_at":"2026-07-05T10:26:07Z"},{"alias_kind":"pith_short_8","alias_value":"XXERCPYL","created_at":"2026-07-05T10:26:07Z"}],"graph_snapshots":[{"event_id":"sha256:50d9cb460c909b9c2726fe6b069618fdc5030a1e7ccb89bdc68ffb0306530abd","target":"graph","created_at":"2026-07-05T10:26:07Z","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/2409.12319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have recently become a focal point of research due to their formidable multimodal understanding capabilities. For example, in the audio and speech domains, an LLM can be equipped with (automatic) speech recognition (ASR) abilities by just concatenating the audio tokens, computed with an audio encoder, and the text tokens to achieve state-of-the-art results. On the contrary, tasks like visual and audio-visual speech recognition (VSR/AVSR), which also exploit noise-invariant lip movement information, have received little or no attention. To bridge this ga","authors_text":"Alessio Brutti, Daniele Falavigna, Honglie Chen, Maja Pantic, Minsu Kim, Pingchuan Ma, Stavros Petridis, Umberto Cappellazzo","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-18T21:17:27Z","title":"Large Language Models are Strong Audio-Visual Speech Recognition Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12319","kind":"arxiv","version":2},"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:c1940c40cad40e93eb9aa0cb23441970d5d4fb79303525bbf0d3a2e31e34ee69","target":"record","created_at":"2026-07-05T10:26:07Z","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":"39e9686f700cd5088ee0451748deaa18dfdefb037c6c158a71c27f9ceea6fc71","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-18T21:17:27Z","title_canon_sha256":"0ff785e68eeff8a98867570299e673cb54b51a35dc0bb6fb59b456603e91afc1"},"schema_version":"1.0","source":{"id":"2409.12319","kind":"arxiv","version":2}},"canonical_sha256":"bdc9113f0bb5f81b68b87d1f491fa8808b74c8a73a27a71300a2b9200c2751c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdc9113f0bb5f81b68b87d1f491fa8808b74c8a73a27a71300a2b9200c2751c6","first_computed_at":"2026-07-05T10:26:07.551061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:07.551061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G5h02vOVd6ZB/cvBtHho/GGH79lQBO91TPivTHyFVjyAOxvkeUxHJjf8BwAZ6bp1h/Odh4k5bHPbvy4Lz8mQCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:07.551611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.12319","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1940c40cad40e93eb9aa0cb23441970d5d4fb79303525bbf0d3a2e31e34ee69","sha256:50d9cb460c909b9c2726fe6b069618fdc5030a1e7ccb89bdc68ffb0306530abd"],"state_sha256":"c52b745a7e116c1bfbe2750ff651440c09be126ae509140a5a632052a4713d18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PeSuh75ZsTM5wsKD2Bb5HpFBtot/lfaoL9LQdphhOZf5FgAIywF0RIOWk9mXvnA2yT+2+zs5HpB7IMvTOhm1DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:09:20.551582Z","bundle_sha256":"afdf5181fd5c8ee2a181013231dbf2e0da3d680e7f7fedbdfde84c20ec2b6e75"}}