{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T5JGLSQFQJ4GH55DYJVSRG43YP","short_pith_number":"pith:T5JGLSQF","schema_version":"1.0","canonical_sha256":"9f5265ca05827863f7a3c26b289b9bc3eb8ccd5b2e7a482fe1e6161da5fd991c","source":{"kind":"arxiv","id":"2606.07643","version":1},"attestation_state":"computed","paper":{"title":"AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Cheng Liang, Guangyao Li, Hao Fei, Henghui Ding, Shaoxuan Xu, Weijun Wang, Wenjie Du, Wenming Tu, Yaoting Wang, Yuanchao Li, Yuanchun Li, Yunxin Liu, Ziyi Zhang","submitted_at":"2026-06-01T19:12:09Z","abstract_excerpt":"Recent advances in Omni-Multimodal Large Language Models (Omni-MLLMs) have enabled strong integration of vision, audio, and language. However, their audio-visual intelligence (AVI) remains insufficiently evaluated due to the lack of systematic and comprehensive benchmarks. We introduce AVI-Bench, a cognitively inspired benchmark that evaluates Omni-MLLMs across three stages, perception, understanding, and reasoning, through cross-modal tasks requiring joint audio-visual interpretation. This design enables fine-grained diagnosis of model capabilities and failure modes. To further assess robustn"},"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":"2606.07643","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T19:12:09Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"a06b08f9ff4c05e2fcc0ced30af1e67649d3d11449792dfc21119205985e99b0","abstract_canon_sha256":"9c5d1bb224099ee8cbee3260d329ced94a3935dbe24be4fa1c6d093615eb7868"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T00:04:45.663623Z","signature_b64":"ynp+Gfqp89l1jXsLSWqxA/pAF2NlaWp3L7/DIFCa5qZHm8u82HDH0Wzd6CcrUM4LU0Np81ZUBFgAR/Y7AAtLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f5265ca05827863f7a3c26b289b9bc3eb8ccd5b2e7a482fe1e6161da5fd991c","last_reissued_at":"2026-06-09T00:04:45.663255Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T00:04:45.663255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Cheng Liang, Guangyao Li, Hao Fei, Henghui Ding, Shaoxuan Xu, Weijun Wang, Wenjie Du, Wenming Tu, Yaoting Wang, Yuanchao Li, Yuanchun Li, Yunxin Liu, Ziyi Zhang","submitted_at":"2026-06-01T19:12:09Z","abstract_excerpt":"Recent advances in Omni-Multimodal Large Language Models (Omni-MLLMs) have enabled strong integration of vision, audio, and language. However, their audio-visual intelligence (AVI) remains insufficiently evaluated due to the lack of systematic and comprehensive benchmarks. We introduce AVI-Bench, a cognitively inspired benchmark that evaluates Omni-MLLMs across three stages, perception, understanding, and reasoning, through cross-modal tasks requiring joint audio-visual interpretation. This design enables fine-grained diagnosis of model capabilities and failure modes. To further assess robustn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07643","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/2606.07643/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":"2606.07643","created_at":"2026-06-09T00:04:45.663313+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07643v1","created_at":"2026-06-09T00:04:45.663313+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07643","created_at":"2026-06-09T00:04:45.663313+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5JGLSQFQJ4G","created_at":"2026-06-09T00:04:45.663313+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5JGLSQFQJ4GH55D","created_at":"2026-06-09T00:04:45.663313+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5JGLSQF","created_at":"2026-06-09T00:04:45.663313+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/T5JGLSQFQJ4GH55DYJVSRG43YP","json":"https://pith.science/pith/T5JGLSQFQJ4GH55DYJVSRG43YP.json","graph_json":"https://pith.science/api/pith-number/T5JGLSQFQJ4GH55DYJVSRG43YP/graph.json","events_json":"https://pith.science/api/pith-number/T5JGLSQFQJ4GH55DYJVSRG43YP/events.json","paper":"https://pith.science/paper/T5JGLSQF"},"agent_actions":{"view_html":"https://pith.science/pith/T5JGLSQFQJ4GH55DYJVSRG43YP","download_json":"https://pith.science/pith/T5JGLSQFQJ4GH55DYJVSRG43YP.json","view_paper":"https://pith.science/paper/T5JGLSQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07643&json=true","fetch_graph":"https://pith.science/api/pith-number/T5JGLSQFQJ4GH55DYJVSRG43YP/graph.json","fetch_events":"https://pith.science/api/pith-number/T5JGLSQFQJ4GH55DYJVSRG43YP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5JGLSQFQJ4GH55DYJVSRG43YP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5JGLSQFQJ4GH55DYJVSRG43YP/action/storage_attestation","attest_author":"https://pith.science/pith/T5JGLSQFQJ4GH55DYJVSRG43YP/action/author_attestation","sign_citation":"https://pith.science/pith/T5JGLSQFQJ4GH55DYJVSRG43YP/action/citation_signature","submit_replication":"https://pith.science/pith/T5JGLSQFQJ4GH55DYJVSRG43YP/action/replication_record"}},"created_at":"2026-06-09T00:04:45.663313+00:00","updated_at":"2026-06-09T00:04:45.663313+00:00"}