{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IVVA5I6D2DW4F5NG4OIJIZR2A5","short_pith_number":"pith:IVVA5I6D","schema_version":"1.0","canonical_sha256":"456a0ea3c3d0edc2f5a6e39094663a076575d4ac93d05b3c3bec330fe12f9463","source":{"kind":"arxiv","id":"2601.21666","version":2},"attestation_state":"computed","paper":{"title":"SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Ahmed Y. Radwan, Christos Emmanouilidis, Deval Pandya, Hina Tabassum, Shaina Raza","submitted_at":"2026-01-29T13:01:07Z","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"},"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":"2601.21666","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-29T13:01:07Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"514234859775fbdd7e58fb314d5e679146a530b1e4921821b8ac20dad31a6e9e","abstract_canon_sha256":"50dffd3e2cab56707b66a9e00dc2155cf16eda53744d480c07449e5eb59c43eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:35.934634Z","signature_b64":"G8aJx4uyhish8rdv9gqDaXPlDFk/E/TbGZxqVDzQfV10bWy5laE/j0c2USVcTmDR8QPTA15IONJHWkYa2dcVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"456a0ea3c3d0edc2f5a6e39094663a076575d4ac93d05b3c3bec330fe12f9463","last_reissued_at":"2026-05-28T01:04:35.934159Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:35.934159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Ahmed Y. Radwan, Christos Emmanouilidis, Deval Pandya, Hina Tabassum, Shaina Raza","submitted_at":"2026-01-29T13:01:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21666","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/2601.21666/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":"2601.21666","created_at":"2026-05-28T01:04:35.934217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.21666v2","created_at":"2026-05-28T01:04:35.934217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21666","created_at":"2026-05-28T01:04:35.934217+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVVA5I6D2DW4","created_at":"2026-05-28T01:04:35.934217+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVVA5I6D2DW4F5NG","created_at":"2026-05-28T01:04:35.934217+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVVA5I6D","created_at":"2026-05-28T01:04:35.934217+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/IVVA5I6D2DW4F5NG4OIJIZR2A5","json":"https://pith.science/pith/IVVA5I6D2DW4F5NG4OIJIZR2A5.json","graph_json":"https://pith.science/api/pith-number/IVVA5I6D2DW4F5NG4OIJIZR2A5/graph.json","events_json":"https://pith.science/api/pith-number/IVVA5I6D2DW4F5NG4OIJIZR2A5/events.json","paper":"https://pith.science/paper/IVVA5I6D"},"agent_actions":{"view_html":"https://pith.science/pith/IVVA5I6D2DW4F5NG4OIJIZR2A5","download_json":"https://pith.science/pith/IVVA5I6D2DW4F5NG4OIJIZR2A5.json","view_paper":"https://pith.science/paper/IVVA5I6D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.21666&json=true","fetch_graph":"https://pith.science/api/pith-number/IVVA5I6D2DW4F5NG4OIJIZR2A5/graph.json","fetch_events":"https://pith.science/api/pith-number/IVVA5I6D2DW4F5NG4OIJIZR2A5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVVA5I6D2DW4F5NG4OIJIZR2A5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVVA5I6D2DW4F5NG4OIJIZR2A5/action/storage_attestation","attest_author":"https://pith.science/pith/IVVA5I6D2DW4F5NG4OIJIZR2A5/action/author_attestation","sign_citation":"https://pith.science/pith/IVVA5I6D2DW4F5NG4OIJIZR2A5/action/citation_signature","submit_replication":"https://pith.science/pith/IVVA5I6D2DW4F5NG4OIJIZR2A5/action/replication_record"}},"created_at":"2026-05-28T01:04:35.934217+00:00","updated_at":"2026-05-28T01:04:35.934217+00:00"}