{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EREO3DDLRP5UIMHPDA25GTKPVR","short_pith_number":"pith:EREO3DDL","canonical_record":{"source":{"id":"2411.14153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-21T14:18:10Z","cross_cats_sorted":[],"title_canon_sha256":"fcffe9ef03aa6e8ffc696e7ed16b1f351e917910b3bc0865b183771b2075a69e","abstract_canon_sha256":"7da5d3ff456ace422ad8af641d8337ed4b1a30ca0950f61d3494efab49815a60"},"schema_version":"1.0"},"canonical_sha256":"2448ed8c6b8bfb4430ef1835d34d4fac7894b9dfbab233088ec5d6d2ee5a300b","source":{"kind":"arxiv","id":"2411.14153","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14153","created_at":"2026-07-05T09:38:42Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14153v1","created_at":"2026-07-05T09:38:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14153","created_at":"2026-07-05T09:38:42Z"},{"alias_kind":"pith_short_12","alias_value":"EREO3DDLRP5U","created_at":"2026-07-05T09:38:42Z"},{"alias_kind":"pith_short_16","alias_value":"EREO3DDLRP5UIMHP","created_at":"2026-07-05T09:38:42Z"},{"alias_kind":"pith_short_8","alias_value":"EREO3DDL","created_at":"2026-07-05T09:38:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EREO3DDLRP5UIMHPDA25GTKPVR","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-21T14:18:10Z","cross_cats_sorted":[],"title_canon_sha256":"fcffe9ef03aa6e8ffc696e7ed16b1f351e917910b3bc0865b183771b2075a69e","abstract_canon_sha256":"7da5d3ff456ace422ad8af641d8337ed4b1a30ca0950f61d3494efab49815a60"},"schema_version":"1.0"},"canonical_sha256":"2448ed8c6b8bfb4430ef1835d34d4fac7894b9dfbab233088ec5d6d2ee5a300b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:42.438779Z","signature_b64":"CA9yjwpu6w9PuZ1seW6RFj9G/bwy94Pqr1gL9cj0E8g/kIjH817hPGv32/QagdfrmKdKYDuXSXZMeuKh15GQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2448ed8c6b8bfb4430ef1835d34d4fac7894b9dfbab233088ec5d6d2ee5a300b","last_reissued_at":"2026-07-05T09:38:42.438269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:42.438269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14153","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:38:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kEIaqcPm6TFekMtRXN5Vac2mQBdNIlS6baPAmNY2yLysfafy4X7RVkFVFOFvnYXxavOKhRM5DTyMVNuiLwFUDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:11:45.772304Z"},"content_sha256":"b7292cc3e1aeb9aeeb8fd302fe78df4d0f7d497329e39df29a221a75a674cbc2","schema_version":"1.0","event_id":"sha256:b7292cc3e1aeb9aeeb8fd302fe78df4d0f7d497329e39df29a221a75a674cbc2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EREO3DDLRP5UIMHPDA25GTKPVR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MVANet: Multi-Stage Video Attention Network for Sound Event Localization and Detection with Source Distance Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hengyi Hong, Jun Du, Mingqi Cai, Qing Wang, Ruoyu Wei, Xin Fang","submitted_at":"2024-11-21T14:18:10Z","abstract_excerpt":"Sound event localization and detection with source distance estimation (3D SELD) involves not only identifying the sound category and its direction-of-arrival (DOA) but also predicting the source's distance, aiming to provide full information about the sound position. This paper proposes a multi-stage video attention network (MVANet) for audio-visual (AV) 3D SELD. Multi-stage audio features are used to adaptively capture the spatial information of sound sources in videos. We propose a novel output representation that combines the DOA with distance of sound sources by calculating the real Carte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14153","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/2411.14153/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:38:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sqwP4AWtxYUP7K/YtF5+p5TEkRhg1eLKClU96kB1qfe9GBoQwjuQtcGB2FxPq+Vzyelq9Z+CGrVWwdob85eoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T09:11:45.772844Z"},"content_sha256":"c92d3a2dd157fe92346de346761c07088d4a2fe58866008676f46ac369e85bee","schema_version":"1.0","event_id":"sha256:c92d3a2dd157fe92346de346761c07088d4a2fe58866008676f46ac369e85bee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EREO3DDLRP5UIMHPDA25GTKPVR/bundle.json","state_url":"https://pith.science/pith/EREO3DDLRP5UIMHPDA25GTKPVR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EREO3DDLRP5UIMHPDA25GTKPVR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T09:11:45Z","links":{"resolver":"https://pith.science/pith/EREO3DDLRP5UIMHPDA25GTKPVR","bundle":"https://pith.science/pith/EREO3DDLRP5UIMHPDA25GTKPVR/bundle.json","state":"https://pith.science/pith/EREO3DDLRP5UIMHPDA25GTKPVR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EREO3DDLRP5UIMHPDA25GTKPVR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EREO3DDLRP5UIMHPDA25GTKPVR","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":"7da5d3ff456ace422ad8af641d8337ed4b1a30ca0950f61d3494efab49815a60","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-21T14:18:10Z","title_canon_sha256":"fcffe9ef03aa6e8ffc696e7ed16b1f351e917910b3bc0865b183771b2075a69e"},"schema_version":"1.0","source":{"id":"2411.14153","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14153","created_at":"2026-07-05T09:38:42Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14153v1","created_at":"2026-07-05T09:38:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14153","created_at":"2026-07-05T09:38:42Z"},{"alias_kind":"pith_short_12","alias_value":"EREO3DDLRP5U","created_at":"2026-07-05T09:38:42Z"},{"alias_kind":"pith_short_16","alias_value":"EREO3DDLRP5UIMHP","created_at":"2026-07-05T09:38:42Z"},{"alias_kind":"pith_short_8","alias_value":"EREO3DDL","created_at":"2026-07-05T09:38:42Z"}],"graph_snapshots":[{"event_id":"sha256:c92d3a2dd157fe92346de346761c07088d4a2fe58866008676f46ac369e85bee","target":"graph","created_at":"2026-07-05T09:38:42Z","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/2411.14153/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sound event localization and detection with source distance estimation (3D SELD) involves not only identifying the sound category and its direction-of-arrival (DOA) but also predicting the source's distance, aiming to provide full information about the sound position. This paper proposes a multi-stage video attention network (MVANet) for audio-visual (AV) 3D SELD. Multi-stage audio features are used to adaptively capture the spatial information of sound sources in videos. We propose a novel output representation that combines the DOA with distance of sound sources by calculating the real Carte","authors_text":"Hengyi Hong, Jun Du, Mingqi Cai, Qing Wang, Ruoyu Wei, Xin Fang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-21T14:18:10Z","title":"MVANet: Multi-Stage Video Attention Network for Sound Event Localization and Detection with Source Distance Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14153","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:b7292cc3e1aeb9aeeb8fd302fe78df4d0f7d497329e39df29a221a75a674cbc2","target":"record","created_at":"2026-07-05T09:38:42Z","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":"7da5d3ff456ace422ad8af641d8337ed4b1a30ca0950f61d3494efab49815a60","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-21T14:18:10Z","title_canon_sha256":"fcffe9ef03aa6e8ffc696e7ed16b1f351e917910b3bc0865b183771b2075a69e"},"schema_version":"1.0","source":{"id":"2411.14153","kind":"arxiv","version":1}},"canonical_sha256":"2448ed8c6b8bfb4430ef1835d34d4fac7894b9dfbab233088ec5d6d2ee5a300b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2448ed8c6b8bfb4430ef1835d34d4fac7894b9dfbab233088ec5d6d2ee5a300b","first_computed_at":"2026-07-05T09:38:42.438269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:42.438269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CA9yjwpu6w9PuZ1seW6RFj9G/bwy94Pqr1gL9cj0E8g/kIjH817hPGv32/QagdfrmKdKYDuXSXZMeuKh15GQCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:42.438779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14153","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7292cc3e1aeb9aeeb8fd302fe78df4d0f7d497329e39df29a221a75a674cbc2","sha256:c92d3a2dd157fe92346de346761c07088d4a2fe58866008676f46ac369e85bee"],"state_sha256":"a68c2d6cbfabf9453904c8cb59d03d3857b34a80e89093215a1bb80af3289c33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YEbwJTHDB6UEJ50dm6cwGI6ACz4cjU0hjxYs/pKeVGlIVjhTkqEQ+pVLvVmJTDuDdLQKDT+XGiCnFtLw5Pa+Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T09:11:45.776249Z","bundle_sha256":"ba8bff9746967d0db2126a9242db5b3e9b56dff78cf1994b68f71e940f5b7501"}}