{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VI232EBVICDUT3G3UESPV336K5","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":"2c0d86c89b3748c8453045520fbf4cd951acc9170466a9242f27eb8cb27a7633","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-11T09:58:05Z","title_canon_sha256":"53362850006e9362e421d41ecec736b8763e452536333c2a08f6be0072ea0b4d"},"schema_version":"1.0","source":{"id":"2110.05122","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05122","created_at":"2026-07-05T03:21:25Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05122v1","created_at":"2026-07-05T03:21:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05122","created_at":"2026-07-05T03:21:25Z"},{"alias_kind":"pith_short_12","alias_value":"VI232EBVICDU","created_at":"2026-07-05T03:21:25Z"},{"alias_kind":"pith_short_16","alias_value":"VI232EBVICDUT3G3","created_at":"2026-07-05T03:21:25Z"},{"alias_kind":"pith_short_8","alias_value":"VI232EBV","created_at":"2026-07-05T03:21:25Z"}],"graph_snapshots":[{"event_id":"sha256:84df2efdb203538911b583411f3092247aaafd7ece6b0d97cdb0e1c640827511","target":"graph","created_at":"2026-07-05T03:21:25Z","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/2110.05122/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"360$^\\circ$ videos convey holistic views for the surroundings of a scene. It provides audio-visual cues beyond pre-determined normal field of views and displays distinctive spatial relations on a sphere. However, previous benchmark tasks for panoramic videos are still limited to evaluate the semantic understanding of audio-visual relationships or spherical spatial property in surroundings. We propose a novel benchmark named Pano-AVQA as a large-scale grounded audio-visual question answering dataset on panoramic videos. Using 5.4K 360$^\\circ$ video clips harvested online, we collect two types o","authors_text":"Gunhee Kim, Heeseung Yun, Kangil Lee, Wonsuk Yang, Youngjae Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-11T09:58:05Z","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05122","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:a0143b39b358b018f8825246ce1fe7aae4ad9b1ea9cf3c01bee75cf21e24df58","target":"record","created_at":"2026-07-05T03:21:25Z","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":"2c0d86c89b3748c8453045520fbf4cd951acc9170466a9242f27eb8cb27a7633","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-11T09:58:05Z","title_canon_sha256":"53362850006e9362e421d41ecec736b8763e452536333c2a08f6be0072ea0b4d"},"schema_version":"1.0","source":{"id":"2110.05122","kind":"arxiv","version":1}},"canonical_sha256":"aa35bd1035408749ecdba124faef7e5750f515c6b17838f8336c677858d59433","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa35bd1035408749ecdba124faef7e5750f515c6b17838f8336c677858d59433","first_computed_at":"2026-07-05T03:21:25.437755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:21:25.437755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cmoAyF2YV9CgVpdneiobvHtMUZv5xVpHvUMBecrb6z3XPOcmgoKnuav9D+zzacPk2jwf43yKkT8R8nbO8Nj8Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:21:25.438193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.05122","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0143b39b358b018f8825246ce1fe7aae4ad9b1ea9cf3c01bee75cf21e24df58","sha256:84df2efdb203538911b583411f3092247aaafd7ece6b0d97cdb0e1c640827511"],"state_sha256":"069284cd677cd9790367fb2028606454b724657cf7f26b1ab63da40d7f20c024"}