{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:O6PVFN6J5L4AKTVVPCC3WWYA42","short_pith_number":"pith:O6PVFN6J","schema_version":"1.0","canonical_sha256":"779f52b7c9eaf8054eb57885bb5b00e696c9e79f02f7d8ee9529497576d63c2b","source":{"kind":"arxiv","id":"2601.22504","version":1},"attestation_state":"computed","paper":{"title":"Class-Aware Permutation-Invariant Signal-to-Distortion Ratio for Semantic Segmentation of Sound Scene with Same-Class Sources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Binh Thien Nguyen, Daiki Takeuchi, Daisuke Niizumi, Masahiro Yasuda, Noboru Harada","submitted_at":"2026-01-30T03:31:20Z","abstract_excerpt":"To advance immersive communication, the Detection and Classification of Acoustic Scenes and Events (DCASE) 2025 Challenge recently introduced Task 4 on Spatial Semantic Segmentation of Sound Scenes (S5). An S5 system takes a multi-channel audio mixture as input and outputs single-channel dry sources along with their corresponding class labels. Although the DCASE 2025 Challenge simplifies the task by constraining class labels in each mixture to be mutually exclusive, real-world mixtures frequently contain multiple sources from the same class. The presence of duplicated labels can significantly "},"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":"2601.22504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-30T03:31:20Z","cross_cats_sorted":[],"title_canon_sha256":"0816919dfcd2e0a68d01f6baf7701889ffa4785c1973640d00af8f4b4b04783c","abstract_canon_sha256":"791bc5ace55273bc715bfbf16f7cab4d5b7863256c8781d241968ca96781cfec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:50.312811Z","signature_b64":"AuSq01+hDBjBZj7maqTPHGu+d8I3YCwwpjvwUVAr9sXFpbZlahotx7PvOTBKZlsZ5LaL7EPvlMe760PY4pI/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"779f52b7c9eaf8054eb57885bb5b00e696c9e79f02f7d8ee9529497576d63c2b","last_reissued_at":"2026-06-02T02:04:50.312284Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:50.312284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class-Aware Permutation-Invariant Signal-to-Distortion Ratio for Semantic Segmentation of Sound Scene with Same-Class Sources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Binh Thien Nguyen, Daiki Takeuchi, Daisuke Niizumi, Masahiro Yasuda, Noboru Harada","submitted_at":"2026-01-30T03:31:20Z","abstract_excerpt":"To advance immersive communication, the Detection and Classification of Acoustic Scenes and Events (DCASE) 2025 Challenge recently introduced Task 4 on Spatial Semantic Segmentation of Sound Scenes (S5). An S5 system takes a multi-channel audio mixture as input and outputs single-channel dry sources along with their corresponding class labels. Although the DCASE 2025 Challenge simplifies the task by constraining class labels in each mixture to be mutually exclusive, real-world mixtures frequently contain multiple sources from the same class. The presence of duplicated labels can significantly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22504","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/2601.22504/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":"2601.22504","created_at":"2026-06-02T02:04:50.312356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.22504v1","created_at":"2026-06-02T02:04:50.312356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22504","created_at":"2026-06-02T02:04:50.312356+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6PVFN6J5L4A","created_at":"2026-06-02T02:04:50.312356+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6PVFN6J5L4AKTVV","created_at":"2026-06-02T02:04:50.312356+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6PVFN6J","created_at":"2026-06-02T02:04:50.312356+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O6PVFN6J5L4AKTVVPCC3WWYA42","json":"https://pith.science/pith/O6PVFN6J5L4AKTVVPCC3WWYA42.json","graph_json":"https://pith.science/api/pith-number/O6PVFN6J5L4AKTVVPCC3WWYA42/graph.json","events_json":"https://pith.science/api/pith-number/O6PVFN6J5L4AKTVVPCC3WWYA42/events.json","paper":"https://pith.science/paper/O6PVFN6J"},"agent_actions":{"view_html":"https://pith.science/pith/O6PVFN6J5L4AKTVVPCC3WWYA42","download_json":"https://pith.science/pith/O6PVFN6J5L4AKTVVPCC3WWYA42.json","view_paper":"https://pith.science/paper/O6PVFN6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.22504&json=true","fetch_graph":"https://pith.science/api/pith-number/O6PVFN6J5L4AKTVVPCC3WWYA42/graph.json","fetch_events":"https://pith.science/api/pith-number/O6PVFN6J5L4AKTVVPCC3WWYA42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6PVFN6J5L4AKTVVPCC3WWYA42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6PVFN6J5L4AKTVVPCC3WWYA42/action/storage_attestation","attest_author":"https://pith.science/pith/O6PVFN6J5L4AKTVVPCC3WWYA42/action/author_attestation","sign_citation":"https://pith.science/pith/O6PVFN6J5L4AKTVVPCC3WWYA42/action/citation_signature","submit_replication":"https://pith.science/pith/O6PVFN6J5L4AKTVVPCC3WWYA42/action/replication_record"}},"created_at":"2026-06-02T02:04:50.312356+00:00","updated_at":"2026-06-02T02:04:50.312356+00:00"}