{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DNZFGKYLOFOXOZW3DAVNQKHP6A","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":"6e387e29da61700297aac80fa924e79854654d2449f084549a1fcd2fdcbee3c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T11:06:28Z","title_canon_sha256":"3a3b14925a3fa06abb814b788add038f5d6ec506691453fb62240aeff0c73941"},"schema_version":"1.0","source":{"id":"2608.09435","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09435","created_at":"2026-08-11T02:22:36Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09435v1","created_at":"2026-08-11T02:22:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09435","created_at":"2026-08-11T02:22:36Z"},{"alias_kind":"pith_short_12","alias_value":"DNZFGKYLOFOX","created_at":"2026-08-11T02:22:36Z"},{"alias_kind":"pith_short_16","alias_value":"DNZFGKYLOFOXOZW3","created_at":"2026-08-11T02:22:36Z"},{"alias_kind":"pith_short_8","alias_value":"DNZFGKYL","created_at":"2026-08-11T02:22:36Z"}],"graph_snapshots":[{"event_id":"sha256:0d410cefba015c56938ab340f2d89e1ec7d6b2cfd14bb92efcd6ea57e97f754a","target":"graph","created_at":"2026-08-11T02:22:36Z","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/2608.09435/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T11:06:28Z","title":"Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09435","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":"sha256:0b2565d3b55cacbbf8ea6eaff9d3ea9721bad76fe257433144e9f49248af7c37","target":"record","created_at":"2026-08-11T02:22:36Z","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":"6e387e29da61700297aac80fa924e79854654d2449f084549a1fcd2fdcbee3c9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-10T11:06:28Z","title_canon_sha256":"3a3b14925a3fa06abb814b788add038f5d6ec506691453fb62240aeff0c73941"},"schema_version":"1.0","source":{"id":"2608.09435","kind":"arxiv","version":1}},"canonical_sha256":"1b72532b0b715d7766db182ad828eff01c58d414f5ace8f5a5a1bdd7b8295073","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b72532b0b715d7766db182ad828eff01c58d414f5ace8f5a5a1bdd7b8295073","first_computed_at":"2026-08-11T02:22:36.361695Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:22:36.361695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CtlGbT2EBZF0Opt5dzvQutU2ohQU+e8kYj0+CrMirYdgN8fzaGVWQaRNpUwsmOtZdm9kSALbMEMDoNKIdLCbDA==","signature_status":"signed_v1","signed_at":"2026-08-11T02:22:36.363729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09435","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b2565d3b55cacbbf8ea6eaff9d3ea9721bad76fe257433144e9f49248af7c37","sha256:0d410cefba015c56938ab340f2d89e1ec7d6b2cfd14bb92efcd6ea57e97f754a"],"state_sha256":"e416646b2d29cfc14b6cd215cbfba8733b5084b2259aa17c01393fdcb200837f"}