{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HPUJVBJ5EOROKBJF2GSVDTT3KJ","short_pith_number":"pith:HPUJVBJ5","schema_version":"1.0","canonical_sha256":"3be89a853d23a2e50525d1a551ce7b527312e6097da7292b0d4732ac57bff0c2","source":{"kind":"arxiv","id":"2607.16107","version":1},"attestation_state":"computed","paper":{"title":"Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.AS","authors_text":"Andrew Tao, Arushi Goel, Bryan Catanzaro, Dinesh Manocha, Ehsan Hosseini-Asl, Hanrong Ye, Jaehyeon Kim, Kaousheik Jayakumar, Lasha Koroshinadze, Ming-Yu Liu, Mohammad Shoeybi, Nishit Anand, Pritam Biswas, Ramani Duraiswami, Sang-gil Lee, Siddharth Gururani, Sreyan Ghosh, S Sakshi, Sungwon Kim, Wei Ping, Yuanhang Su, Zhifeng Kong","submitted_at":"2026-07-17T16:41:15Z","abstract_excerpt":"We present Audio-Visual Flamingo (AV-Flamingo), a fully open state-of-the-art audio-visual large language model (AV-LLM) for joint understanding and reasoning over audio, images, and long-form videos. Unlike prior AV-LLMs that primarily focus on short clips, AV-Flamingo is designed for understanding and reasoning over long and complex real-world (audio-visual) videos. To support this, we make three key contributions: (i) Audio-Visual-Skills, a large-scale collection of real-world videos with ~7M caption and question-answer training instances designed to emphasize temporal, compositional, and c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.16107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-17T16:41:15Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"4a5e9425e668342b48256c62083ba0217d4ba0e03b414442f9f26315178dafce","abstract_canon_sha256":"4efd1cbcd4cf550c7884f612932c828f3b01683b019e4cf6705696dd2a7ce12f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T02:19:33.612457Z","signature_b64":"u+Zlk2wir5UeH0H/d6DJHERhn88Kk21TVXYWiSj0muR3CzTrfe1tvLc+coNZ6T2P0cerxMQWor4sOXKvE3DuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3be89a853d23a2e50525d1a551ce7b527312e6097da7292b0d4732ac57bff0c2","last_reissued_at":"2026-07-20T02:19:33.611611Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T02:19:33.611611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.AS","authors_text":"Andrew Tao, Arushi Goel, Bryan Catanzaro, Dinesh Manocha, Ehsan Hosseini-Asl, Hanrong Ye, Jaehyeon Kim, Kaousheik Jayakumar, Lasha Koroshinadze, Ming-Yu Liu, Mohammad Shoeybi, Nishit Anand, Pritam Biswas, Ramani Duraiswami, Sang-gil Lee, Siddharth Gururani, Sreyan Ghosh, S Sakshi, Sungwon Kim, Wei Ping, Yuanhang Su, Zhifeng Kong","submitted_at":"2026-07-17T16:41:15Z","abstract_excerpt":"We present Audio-Visual Flamingo (AV-Flamingo), a fully open state-of-the-art audio-visual large language model (AV-LLM) for joint understanding and reasoning over audio, images, and long-form videos. Unlike prior AV-LLMs that primarily focus on short clips, AV-Flamingo is designed for understanding and reasoning over long and complex real-world (audio-visual) videos. To support this, we make three key contributions: (i) Audio-Visual-Skills, a large-scale collection of real-world videos with ~7M caption and question-answer training instances designed to emphasize temporal, compositional, and c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16107","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/2607.16107/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.16107","created_at":"2026-07-20T02:19:33.612036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16107v1","created_at":"2026-07-20T02:19:33.612036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16107","created_at":"2026-07-20T02:19:33.612036+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPUJVBJ5EORO","created_at":"2026-07-20T02:19:33.612036+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPUJVBJ5EOROKBJF","created_at":"2026-07-20T02:19:33.612036+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPUJVBJ5","created_at":"2026-07-20T02:19:33.612036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPUJVBJ5EOROKBJF2GSVDTT3KJ","json":"https://pith.science/pith/HPUJVBJ5EOROKBJF2GSVDTT3KJ.json","graph_json":"https://pith.science/api/pith-number/HPUJVBJ5EOROKBJF2GSVDTT3KJ/graph.json","events_json":"https://pith.science/api/pith-number/HPUJVBJ5EOROKBJF2GSVDTT3KJ/events.json","paper":"https://pith.science/paper/HPUJVBJ5"},"agent_actions":{"view_html":"https://pith.science/pith/HPUJVBJ5EOROKBJF2GSVDTT3KJ","download_json":"https://pith.science/pith/HPUJVBJ5EOROKBJF2GSVDTT3KJ.json","view_paper":"https://pith.science/paper/HPUJVBJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16107&json=true","fetch_graph":"https://pith.science/api/pith-number/HPUJVBJ5EOROKBJF2GSVDTT3KJ/graph.json","fetch_events":"https://pith.science/api/pith-number/HPUJVBJ5EOROKBJF2GSVDTT3KJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPUJVBJ5EOROKBJF2GSVDTT3KJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPUJVBJ5EOROKBJF2GSVDTT3KJ/action/storage_attestation","attest_author":"https://pith.science/pith/HPUJVBJ5EOROKBJF2GSVDTT3KJ/action/author_attestation","sign_citation":"https://pith.science/pith/HPUJVBJ5EOROKBJF2GSVDTT3KJ/action/citation_signature","submit_replication":"https://pith.science/pith/HPUJVBJ5EOROKBJF2GSVDTT3KJ/action/replication_record"}},"created_at":"2026-07-20T02:19:33.612036+00:00","updated_at":"2026-07-20T02:19:33.612036+00:00"}