{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XP4GBOISSINKAWWLCUDEI7WII6","short_pith_number":"pith:XP4GBOIS","canonical_record":{"source":{"id":"2507.04845","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-07T10:08:57Z","cross_cats_sorted":["cs.LG","eess.IV","eess.SP"],"title_canon_sha256":"e2ad34952634e071a8bd060e20889516d203ef20979d48f5c3ee73f102ed1b00","abstract_canon_sha256":"a843601cbe9f894129c676682c2843ae71d84ad14d83b005d688ce99f6fb0e1a"},"schema_version":"1.0"},"canonical_sha256":"bbf860b912921aa05acb1506447ec847924db9ff61de4dddaed833112ed364dd","source":{"kind":"arxiv","id":"2507.04845","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04845","created_at":"2026-07-05T11:32:55Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04845v1","created_at":"2026-07-05T11:32:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04845","created_at":"2026-07-05T11:32:55Z"},{"alias_kind":"pith_short_12","alias_value":"XP4GBOISSINK","created_at":"2026-07-05T11:32:55Z"},{"alias_kind":"pith_short_16","alias_value":"XP4GBOISSINKAWWL","created_at":"2026-07-05T11:32:55Z"},{"alias_kind":"pith_short_8","alias_value":"XP4GBOIS","created_at":"2026-07-05T11:32:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XP4GBOISSINKAWWLCUDEI7WII6","target":"record","payload":{"canonical_record":{"source":{"id":"2507.04845","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-07T10:08:57Z","cross_cats_sorted":["cs.LG","eess.IV","eess.SP"],"title_canon_sha256":"e2ad34952634e071a8bd060e20889516d203ef20979d48f5c3ee73f102ed1b00","abstract_canon_sha256":"a843601cbe9f894129c676682c2843ae71d84ad14d83b005d688ce99f6fb0e1a"},"schema_version":"1.0"},"canonical_sha256":"bbf860b912921aa05acb1506447ec847924db9ff61de4dddaed833112ed364dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:55.148910Z","signature_b64":"Xjp/k3M8sT3+MZePGU5n3ozncuPL4fqSsHBv+pF/2FDafzOH6j6BqOsQ57bNtoxzlKXWf93VpP3x4DU5bMPtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbf860b912921aa05acb1506447ec847924db9ff61de4dddaed833112ed364dd","last_reissued_at":"2026-07-05T11:32:55.148454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:55.148454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.04845","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":"2026-07-05T11:32:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bQrPhIx8Q+SrZlfdImlWxU6XiDpdanFFJ5/W50f3KYiQgrGGqDq9RK+ZJfZx/EmMnR3YnNF/dOhZXHRGeEvQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:30:25.629007Z"},"content_sha256":"3de5050617b2654f24c42869dda601b4da05de0adfb8dd7496b7a3d207041461","schema_version":"1.0","event_id":"sha256:3de5050617b2654f24c42869dda601b4da05de0adfb8dd7496b7a3d207041461"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XP4GBOISSINKAWWLCUDEI7WII6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spatial and Semantic Embedding Integration for Stereo Sound Event Localization and Detection in Regular Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV","eess.SP"],"primary_cat":"eess.AS","authors_text":"Davide Berghi, Philip J. B. Jackson","submitted_at":"2025-07-07T10:08:57Z","abstract_excerpt":"This report presents our systems submitted to the audio-only and audio-visual tracks of the DCASE2025 Task 3 Challenge: Stereo Sound Event Localization and Detection (SELD) in Regular Video Content. SELD is a complex task that combines temporal event classification with spatial localization, requiring reasoning across spatial, temporal, and semantic dimensions. The last is arguably the most challenging to model. Traditional SELD architectures rely on multichannel input, which limits their ability to leverage large-scale pre-training due to data constraints. To address this, we enhance standard"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04845","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/2507.04845/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":"2026-07-05T11:32:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gE5CMLR1z4OKjynNYi/JPITNEV4d1sqfroPFT0eUyVmAVEymx6BHpsgcYbFzecUr8ulkGGTzfC4HBKP0sGEfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:30:25.629504Z"},"content_sha256":"7ba17a1ef9332975969863a0d027af1c1360e2ae25c2813ba25e1d82cc62974e","schema_version":"1.0","event_id":"sha256:7ba17a1ef9332975969863a0d027af1c1360e2ae25c2813ba25e1d82cc62974e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XP4GBOISSINKAWWLCUDEI7WII6/bundle.json","state_url":"https://pith.science/pith/XP4GBOISSINKAWWLCUDEI7WII6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XP4GBOISSINKAWWLCUDEI7WII6/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":"2026-08-09T15:30:25Z","links":{"resolver":"https://pith.science/pith/XP4GBOISSINKAWWLCUDEI7WII6","bundle":"https://pith.science/pith/XP4GBOISSINKAWWLCUDEI7WII6/bundle.json","state":"https://pith.science/pith/XP4GBOISSINKAWWLCUDEI7WII6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XP4GBOISSINKAWWLCUDEI7WII6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XP4GBOISSINKAWWLCUDEI7WII6","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":"a843601cbe9f894129c676682c2843ae71d84ad14d83b005d688ce99f6fb0e1a","cross_cats_sorted":["cs.LG","eess.IV","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-07T10:08:57Z","title_canon_sha256":"e2ad34952634e071a8bd060e20889516d203ef20979d48f5c3ee73f102ed1b00"},"schema_version":"1.0","source":{"id":"2507.04845","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04845","created_at":"2026-07-05T11:32:55Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04845v1","created_at":"2026-07-05T11:32:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04845","created_at":"2026-07-05T11:32:55Z"},{"alias_kind":"pith_short_12","alias_value":"XP4GBOISSINK","created_at":"2026-07-05T11:32:55Z"},{"alias_kind":"pith_short_16","alias_value":"XP4GBOISSINKAWWL","created_at":"2026-07-05T11:32:55Z"},{"alias_kind":"pith_short_8","alias_value":"XP4GBOIS","created_at":"2026-07-05T11:32:55Z"}],"graph_snapshots":[{"event_id":"sha256:7ba17a1ef9332975969863a0d027af1c1360e2ae25c2813ba25e1d82cc62974e","target":"graph","created_at":"2026-07-05T11:32:55Z","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/2507.04845/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This report presents our systems submitted to the audio-only and audio-visual tracks of the DCASE2025 Task 3 Challenge: Stereo Sound Event Localization and Detection (SELD) in Regular Video Content. SELD is a complex task that combines temporal event classification with spatial localization, requiring reasoning across spatial, temporal, and semantic dimensions. The last is arguably the most challenging to model. Traditional SELD architectures rely on multichannel input, which limits their ability to leverage large-scale pre-training due to data constraints. To address this, we enhance standard","authors_text":"Davide Berghi, Philip J. B. Jackson","cross_cats":["cs.LG","eess.IV","eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-07T10:08:57Z","title":"Spatial and Semantic Embedding Integration for Stereo Sound Event Localization and Detection in Regular Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04845","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":"sha256:3de5050617b2654f24c42869dda601b4da05de0adfb8dd7496b7a3d207041461","target":"record","created_at":"2026-07-05T11:32:55Z","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":"a843601cbe9f894129c676682c2843ae71d84ad14d83b005d688ce99f6fb0e1a","cross_cats_sorted":["cs.LG","eess.IV","eess.SP"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-07T10:08:57Z","title_canon_sha256":"e2ad34952634e071a8bd060e20889516d203ef20979d48f5c3ee73f102ed1b00"},"schema_version":"1.0","source":{"id":"2507.04845","kind":"arxiv","version":1}},"canonical_sha256":"bbf860b912921aa05acb1506447ec847924db9ff61de4dddaed833112ed364dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbf860b912921aa05acb1506447ec847924db9ff61de4dddaed833112ed364dd","first_computed_at":"2026-07-05T11:32:55.148454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:55.148454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xjp/k3M8sT3+MZePGU5n3ozncuPL4fqSsHBv+pF/2FDafzOH6j6BqOsQ57bNtoxzlKXWf93VpP3x4DU5bMPtCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:55.148910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04845","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3de5050617b2654f24c42869dda601b4da05de0adfb8dd7496b7a3d207041461","sha256:7ba17a1ef9332975969863a0d027af1c1360e2ae25c2813ba25e1d82cc62974e"],"state_sha256":"a9727215e20cb8a49390b1efb0504728123cd20d2e07e4f1a48272ece422c4fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kLf6Ky/L7XS/sy9mT59xHvD2mfeo6p+vmiDvcE+egJzY+6y6oY/AD1aI6xn1NjSi1WhMMkrjZrKtKiiHezI2DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:30:25.633512Z","bundle_sha256":"13f555b1f843b654e83e7d25cb18727ed39b40d4c76a962b3feef2a78e6721eb"}}