{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MCH77ZRRTAGB7T2NRFMCZDRKYI","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":"81fa72deaa4a58f1af98004eade4806a341ce6c2900b4266df1e3889c8d18c15","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T23:16:28Z","title_canon_sha256":"3e7ff4e98f29fe6c87d41f3ccd4f03a100b960a3b1abb6364372a5501b18bf55"},"schema_version":"1.0","source":{"id":"2410.12109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12109","created_at":"2026-07-05T09:21:14Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12109v1","created_at":"2026-07-05T09:21:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12109","created_at":"2026-07-05T09:21:14Z"},{"alias_kind":"pith_short_12","alias_value":"MCH77ZRRTAGB","created_at":"2026-07-05T09:21:14Z"},{"alias_kind":"pith_short_16","alias_value":"MCH77ZRRTAGB7T2N","created_at":"2026-07-05T09:21:14Z"},{"alias_kind":"pith_short_8","alias_value":"MCH77ZRR","created_at":"2026-07-05T09:21:14Z"}],"graph_snapshots":[{"event_id":"sha256:61ece9c1dae1315a4290edb6859da9f1da8c9b38847660d22344e1a328ec305d","target":"graph","created_at":"2026-07-05T09:21:14Z","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/2410.12109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have made significant strides in text generation and comprehension, with recent advancements extending into multimodal LLMs that integrate visual and audio inputs. However, these models continue to struggle with fine-grained, cross-modal temporal understanding, particularly when correlating events across audio and video streams. We address these challenges with two key contributions: a new dataset and model, called OCTAV and OMCAT respectively. OCTAV (Omni Context and Temporal Audio Video) is a novel dataset designed to capture event transitions across audio and vi","authors_text":"Andrew Tao, Arushi Goel, Bryan Catanzaro, Karan Sapra, Matthieu Le, Rafael Valle","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T23:16:28Z","title":"OMCAT: Omni Context Aware Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12109","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":"sha256:613db020cb4d1c1b2b155ab3be0fe22bc00afaa6d04bebceb39231c7b6b35eba","target":"record","created_at":"2026-07-05T09:21:14Z","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":"81fa72deaa4a58f1af98004eade4806a341ce6c2900b4266df1e3889c8d18c15","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T23:16:28Z","title_canon_sha256":"3e7ff4e98f29fe6c87d41f3ccd4f03a100b960a3b1abb6364372a5501b18bf55"},"schema_version":"1.0","source":{"id":"2410.12109","kind":"arxiv","version":1}},"canonical_sha256":"608fffe631980c1fcf4d89582c8e2ac23fbd48be599c269ed2e372124fc89829","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"608fffe631980c1fcf4d89582c8e2ac23fbd48be599c269ed2e372124fc89829","first_computed_at":"2026-07-05T09:21:14.338380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:14.338380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d0jYAFaIbUvmj/y2Qn9RvHXkV/ovZ/uaGqT3bB6EeiFJjyaG/hor/PdAeKwXAjdC9PZvOXeAOfUDYrZn4c3EBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:14.338874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:613db020cb4d1c1b2b155ab3be0fe22bc00afaa6d04bebceb39231c7b6b35eba","sha256:61ece9c1dae1315a4290edb6859da9f1da8c9b38847660d22344e1a328ec305d"],"state_sha256":"ceeefd66fbc80f381cd7b5a40846cb9caac924d03dd2c1687d3de9d848988761"}