{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HPUJVBJ5EOROKBJF2GSVDTT3KJ","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":"4efd1cbcd4cf550c7884f612932c828f3b01683b019e4cf6705696dd2a7ce12f","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-17T16:41:15Z","title_canon_sha256":"4a5e9425e668342b48256c62083ba0217d4ba0e03b414442f9f26315178dafce"},"schema_version":"1.0","source":{"id":"2607.16107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16107","created_at":"2026-07-20T02:19:33Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16107v1","created_at":"2026-07-20T02:19:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16107","created_at":"2026-07-20T02:19:33Z"},{"alias_kind":"pith_short_12","alias_value":"HPUJVBJ5EORO","created_at":"2026-07-20T02:19:33Z"},{"alias_kind":"pith_short_16","alias_value":"HPUJVBJ5EOROKBJF","created_at":"2026-07-20T02:19:33Z"},{"alias_kind":"pith_short_8","alias_value":"HPUJVBJ5","created_at":"2026-07-20T02:19:33Z"}],"graph_snapshots":[{"event_id":"sha256:c91a00c91eb744b8a7964f847d890c639cd2402e1cca57673a430892059cf547","target":"graph","created_at":"2026-07-20T02:19:33Z","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/2607.16107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-17T16:41:15Z","title":"Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16107","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":"sha256:64a268dd090dbf737dbe7585b56d9cd11a68f51d809b1a56e9dbdfe200957581","target":"record","created_at":"2026-07-20T02:19:33Z","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":"4efd1cbcd4cf550c7884f612932c828f3b01683b019e4cf6705696dd2a7ce12f","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-17T16:41:15Z","title_canon_sha256":"4a5e9425e668342b48256c62083ba0217d4ba0e03b414442f9f26315178dafce"},"schema_version":"1.0","source":{"id":"2607.16107","kind":"arxiv","version":1}},"canonical_sha256":"3be89a853d23a2e50525d1a551ce7b527312e6097da7292b0d4732ac57bff0c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3be89a853d23a2e50525d1a551ce7b527312e6097da7292b0d4732ac57bff0c2","first_computed_at":"2026-07-20T02:19:33.611611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T02:19:33.611611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u+Zlk2wir5UeH0H/d6DJHERhn88Kk21TVXYWiSj0muR3CzTrfe1tvLc+coNZ6T2P0cerxMQWor4sOXKvE3DuCA==","signature_status":"signed_v1","signed_at":"2026-07-20T02:19:33.612457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64a268dd090dbf737dbe7585b56d9cd11a68f51d809b1a56e9dbdfe200957581","sha256:c91a00c91eb744b8a7964f847d890c639cd2402e1cca57673a430892059cf547"],"state_sha256":"3ab979fbea6c29e808717c41aef009cac637614ab648fc0c0332fb0b47a28db8"}