{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LRSIJXL4RDR65HHWZL4ZM4WHFP","short_pith_number":"pith:LRSIJXL4","schema_version":"1.0","canonical_sha256":"5c6484dd7c88e3ee9cf6caf99672c72bfb57ede4b994206b5533175722531d81","source":{"kind":"arxiv","id":"2507.12042","version":1},"attestation_state":"computed","paper":{"title":"Stereo Sound Event Localization and Detection with Onscreen/offscreen Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS","eess.IV"],"primary_cat":"cs.SD","authors_text":"Archontis Politis, David Diaz-Guerra, Iran R. Roman, Kazuki Shimada, Kengo Uchida, Naoya Takahashi, Parthasaarathy Sudarsanam, Ruchi Pandey, Shusuke Takahashi, Takashi Shibuya, Tuomas Virtanen, Yuichiro Koyama, Yuki Mitsufuji","submitted_at":"2025-07-16T08:59:09Z","abstract_excerpt":"This paper presents the objective, dataset, baseline, and metrics of Task 3 of the DCASE2025 Challenge on sound event localization and detection (SELD). In previous editions, the challenge used four-channel audio formats of first-order Ambisonics (FOA) and microphone array. In contrast, this year's challenge investigates SELD with stereo audio data (termed stereo SELD). This change shifts the focus from more specialized 360{\\deg} audio and audiovisual scene analysis to more commonplace audio and media scenarios with limited field-of-view (FOV). Due to inherent angular ambiguities in stereo aud"},"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":"2507.12042","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-16T08:59:09Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS","eess.IV"],"title_canon_sha256":"83bf752a6cb593ffe8e29bb20286f4ca92caac34aaa938d49866003f1dbe59a3","abstract_canon_sha256":"b4946ec6efc4b3b48a390e51a36792da7380ab36959aa1cfcf4961bd3b3e5b6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:13.579714Z","signature_b64":"bcI+09fPYElR2omBQJ37HlNA3ciWDs5WomVNuN6XT1M71QNSNv22srR7DXRJt2SgJuVLpp1NxpHQEPziapjrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c6484dd7c88e3ee9cf6caf99672c72bfb57ede4b994206b5533175722531d81","last_reissued_at":"2026-07-05T11:38:13.579118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:13.579118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stereo Sound Event Localization and Detection with Onscreen/offscreen Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS","eess.IV"],"primary_cat":"cs.SD","authors_text":"Archontis Politis, David Diaz-Guerra, Iran R. Roman, Kazuki Shimada, Kengo Uchida, Naoya Takahashi, Parthasaarathy Sudarsanam, Ruchi Pandey, Shusuke Takahashi, Takashi Shibuya, Tuomas Virtanen, Yuichiro Koyama, Yuki Mitsufuji","submitted_at":"2025-07-16T08:59:09Z","abstract_excerpt":"This paper presents the objective, dataset, baseline, and metrics of Task 3 of the DCASE2025 Challenge on sound event localization and detection (SELD). In previous editions, the challenge used four-channel audio formats of first-order Ambisonics (FOA) and microphone array. In contrast, this year's challenge investigates SELD with stereo audio data (termed stereo SELD). This change shifts the focus from more specialized 360{\\deg} audio and audiovisual scene analysis to more commonplace audio and media scenarios with limited field-of-view (FOV). Due to inherent angular ambiguities in stereo aud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12042","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/2507.12042/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":"2507.12042","created_at":"2026-07-05T11:38:13.579188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12042v1","created_at":"2026-07-05T11:38:13.579188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12042","created_at":"2026-07-05T11:38:13.579188+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRSIJXL4RDR6","created_at":"2026-07-05T11:38:13.579188+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRSIJXL4RDR65HHW","created_at":"2026-07-05T11:38:13.579188+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRSIJXL4","created_at":"2026-07-05T11:38:13.579188+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02343","citing_title":"SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05544","citing_title":"Probing Spatial Structure in Pretrained Audio Representations","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRSIJXL4RDR65HHWZL4ZM4WHFP","json":"https://pith.science/pith/LRSIJXL4RDR65HHWZL4ZM4WHFP.json","graph_json":"https://pith.science/api/pith-number/LRSIJXL4RDR65HHWZL4ZM4WHFP/graph.json","events_json":"https://pith.science/api/pith-number/LRSIJXL4RDR65HHWZL4ZM4WHFP/events.json","paper":"https://pith.science/paper/LRSIJXL4"},"agent_actions":{"view_html":"https://pith.science/pith/LRSIJXL4RDR65HHWZL4ZM4WHFP","download_json":"https://pith.science/pith/LRSIJXL4RDR65HHWZL4ZM4WHFP.json","view_paper":"https://pith.science/paper/LRSIJXL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12042&json=true","fetch_graph":"https://pith.science/api/pith-number/LRSIJXL4RDR65HHWZL4ZM4WHFP/graph.json","fetch_events":"https://pith.science/api/pith-number/LRSIJXL4RDR65HHWZL4ZM4WHFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRSIJXL4RDR65HHWZL4ZM4WHFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRSIJXL4RDR65HHWZL4ZM4WHFP/action/storage_attestation","attest_author":"https://pith.science/pith/LRSIJXL4RDR65HHWZL4ZM4WHFP/action/author_attestation","sign_citation":"https://pith.science/pith/LRSIJXL4RDR65HHWZL4ZM4WHFP/action/citation_signature","submit_replication":"https://pith.science/pith/LRSIJXL4RDR65HHWZL4ZM4WHFP/action/replication_record"}},"created_at":"2026-07-05T11:38:13.579188+00:00","updated_at":"2026-07-05T11:38:13.579188+00:00"}