{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IVVA5I6D2DW4F5NG4OIJIZR2A5","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":"50dffd3e2cab56707b66a9e00dc2155cf16eda53744d480c07449e5eb59c43eb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-29T13:01:07Z","title_canon_sha256":"514234859775fbdd7e58fb314d5e679146a530b1e4921821b8ac20dad31a6e9e"},"schema_version":"1.0","source":{"id":"2601.21666","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21666","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21666v2","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21666","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"IVVA5I6D2DW4","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"IVVA5I6D2DW4F5NG","created_at":"2026-05-28T01:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"IVVA5I6D","created_at":"2026-05-28T01:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:59a7fb5d019dadd004e85df1138c268e867c4459eb1871d9708181e542f9a993","target":"graph","created_at":"2026-05-28T01:04:35Z","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/2601.21666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) are a major focus of recent AI research. However, most prior work focuses on static image understanding, while their ability to process sequential audio-video data remains underexplored. This gap highlights the need for a high-quality benchmark to systematically evaluate MLLM performance in a real-world setting. We introduce SONIC-O1, a comprehensive, fully human-verified benchmark of 60 hours (231 clips) spanning 13 real-world conversational domains with 4,958 annotations and demographic metadata. SONIC-O1 evaluates three capabilities: open-ended summa","authors_text":"Ahmed Y. Radwan, Christos Emmanouilidis, Deval Pandya, Hina Tabassum, Shaina Raza","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-29T13:01:07Z","title":"SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21666","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":"sha256:6b8ac5c145f43f45277ff856685c23b4a33eee086fa2e01beb5edd0043f12ee7","target":"record","created_at":"2026-05-28T01:04:35Z","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":"50dffd3e2cab56707b66a9e00dc2155cf16eda53744d480c07449e5eb59c43eb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-29T13:01:07Z","title_canon_sha256":"514234859775fbdd7e58fb314d5e679146a530b1e4921821b8ac20dad31a6e9e"},"schema_version":"1.0","source":{"id":"2601.21666","kind":"arxiv","version":2}},"canonical_sha256":"456a0ea3c3d0edc2f5a6e39094663a076575d4ac93d05b3c3bec330fe12f9463","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"456a0ea3c3d0edc2f5a6e39094663a076575d4ac93d05b3c3bec330fe12f9463","first_computed_at":"2026-05-28T01:04:35.934159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:35.934159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G8aJx4uyhish8rdv9gqDaXPlDFk/E/TbGZxqVDzQfV10bWy5laE/j0c2USVcTmDR8QPTA15IONJHWkYa2dcVDg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:35.934634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21666","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b8ac5c145f43f45277ff856685c23b4a33eee086fa2e01beb5edd0043f12ee7","sha256:59a7fb5d019dadd004e85df1138c268e867c4459eb1871d9708181e542f9a993"],"state_sha256":"bde5d7ca2903de129957231fbd1020efeccec21a66d67e793ee1134e7c92df67"}