{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DNZFGKYLOFOXOZW3DAVNQKHP6A","short_pith_number":"pith:DNZFGKYL","schema_version":"1.0","canonical_sha256":"1b72532b0b715d7766db182ad828eff01c58d414f5ace8f5a5a1bdd7b8295073","source":{"kind":"arxiv","id":"2608.09435","version":1},"attestation_state":"computed","paper":{"title":"Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng Zhang, Di Zhang, Guodong Li, Jiaying Wu, Minnan Luo, Rendong Pi, Yifei Zheng, Yu Xiang, Zesheng Yang, Zhi Zeng, Zhou Yang, Zihan Ma","submitted_at":"2026-08-10T11:06:28Z","abstract_excerpt":"Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time. Yet existing audio-language models often represent clips as global acoustic events, while vision-language models lack the spatial audio cues needed to localize and track individual sources. To evaluate this missing capability, we introduce ST-OmniQA, a spatio-temporal audio-visual question-answering benchmark built from panoramic videos paired with synchronized first-order Ambisonics (FOA) audio of moving sound sources. It contains 40K videos and 400K"},"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":"2608.09435","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T11:06:28Z","cross_cats_sorted":[],"title_canon_sha256":"3a3b14925a3fa06abb814b788add038f5d6ec506691453fb62240aeff0c73941","abstract_canon_sha256":"6e387e29da61700297aac80fa924e79854654d2449f084549a1fcd2fdcbee3c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:22:36.363729Z","signature_b64":"CtlGbT2EBZF0Opt5dzvQutU2ohQU+e8kYj0+CrMirYdgN8fzaGVWQaRNpUwsmOtZdm9kSALbMEMDoNKIdLCbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b72532b0b715d7766db182ad828eff01c58d414f5ace8f5a5a1bdd7b8295073","last_reissued_at":"2026-08-11T02:22:36.361695Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:22:36.361695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng Zhang, Di Zhang, Guodong Li, Jiaying Wu, Minnan Luo, Rendong Pi, Yifei Zheng, Yu Xiang, Zesheng Yang, Zhi Zeng, Zhou Yang, Zihan Ma","submitted_at":"2026-08-10T11:06:28Z","abstract_excerpt":"Understanding dynamic sound sources requires jointly determining what produces a sound, where the source is located, and how it moves over time. Yet existing audio-language models often represent clips as global acoustic events, while vision-language models lack the spatial audio cues needed to localize and track individual sources. To evaluate this missing capability, we introduce ST-OmniQA, a spatio-temporal audio-visual question-answering benchmark built from panoramic videos paired with synchronized first-order Ambisonics (FOA) audio of moving sound sources. It contains 40K videos and 400K"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09435","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/2608.09435/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":"2608.09435","created_at":"2026-08-11T02:22:36.362623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09435v1","created_at":"2026-08-11T02:22:36.362623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09435","created_at":"2026-08-11T02:22:36.362623+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNZFGKYLOFOX","created_at":"2026-08-11T02:22:36.362623+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNZFGKYLOFOXOZW3","created_at":"2026-08-11T02:22:36.362623+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNZFGKYL","created_at":"2026-08-11T02:22:36.362623+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/DNZFGKYLOFOXOZW3DAVNQKHP6A","json":"https://pith.science/pith/DNZFGKYLOFOXOZW3DAVNQKHP6A.json","graph_json":"https://pith.science/api/pith-number/DNZFGKYLOFOXOZW3DAVNQKHP6A/graph.json","events_json":"https://pith.science/api/pith-number/DNZFGKYLOFOXOZW3DAVNQKHP6A/events.json","paper":"https://pith.science/paper/DNZFGKYL"},"agent_actions":{"view_html":"https://pith.science/pith/DNZFGKYLOFOXOZW3DAVNQKHP6A","download_json":"https://pith.science/pith/DNZFGKYLOFOXOZW3DAVNQKHP6A.json","view_paper":"https://pith.science/paper/DNZFGKYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09435&json=true","fetch_graph":"https://pith.science/api/pith-number/DNZFGKYLOFOXOZW3DAVNQKHP6A/graph.json","fetch_events":"https://pith.science/api/pith-number/DNZFGKYLOFOXOZW3DAVNQKHP6A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNZFGKYLOFOXOZW3DAVNQKHP6A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNZFGKYLOFOXOZW3DAVNQKHP6A/action/storage_attestation","attest_author":"https://pith.science/pith/DNZFGKYLOFOXOZW3DAVNQKHP6A/action/author_attestation","sign_citation":"https://pith.science/pith/DNZFGKYLOFOXOZW3DAVNQKHP6A/action/citation_signature","submit_replication":"https://pith.science/pith/DNZFGKYLOFOXOZW3DAVNQKHP6A/action/replication_record"}},"created_at":"2026-08-11T02:22:36.362623+00:00","updated_at":"2026-08-11T02:22:36.362623+00:00"}