{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:36R4UTGAAHQNYLOWRTAIQ4Z7GT","short_pith_number":"pith:36R4UTGA","schema_version":"1.0","canonical_sha256":"dfa3ca4cc001e0dc2dd68cc088733f34fe1ac4f7c6f9782c60cf05717cd65d5a","source":{"kind":"arxiv","id":"2511.07075","version":4},"attestation_state":"computed","paper":{"title":"Metric Analysis for Spatial Semantic Segmentation of Sound Scenes","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Mayank Mishra, Paul Magron, Romain Serizel","submitted_at":"2025-11-10T13:06:31Z","abstract_excerpt":"Spatial semantic segmentation of sound scenes (S5) consists of jointly performing audio source separation and sound event classification from a multichannel audio mixture. Evaluating S5 systems with separation and classification metrics individually makes system comparison difficult, whereas existing joint metrics, such as the class-aware signal-to-distortion ratio (CA-SDR), can conflate separation and labeling errors. In particular, CA-SDR relies on predicted class labels for source matching, which may obscure label swaps or misclassifications when the underlying source estimates remain perce"},"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":"2511.07075","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-11-10T13:06:31Z","cross_cats_sorted":[],"title_canon_sha256":"008c63aa8b0d21cb9b5b410bf889d025a74aa07c6fcc49a6e08809cdc2f7df62","abstract_canon_sha256":"14c2d1f9d2bee74c69a47ccab789d3af3773344eb2f0ec43023f49ad66d2302b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:39.741566Z","signature_b64":"i/gUtAaK+7xC0SLFrxFvNp4szqkzvOrTUQOvg7LcNQHlxrR1mGsMdYbD8m+K+7a40JUZI0QtZguikr/tDJrsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfa3ca4cc001e0dc2dd68cc088733f34fe1ac4f7c6f9782c60cf05717cd65d5a","last_reissued_at":"2026-05-27T01:05:39.740723Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:39.740723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metric Analysis for Spatial Semantic Segmentation of Sound Scenes","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Mayank Mishra, Paul Magron, Romain Serizel","submitted_at":"2025-11-10T13:06:31Z","abstract_excerpt":"Spatial semantic segmentation of sound scenes (S5) consists of jointly performing audio source separation and sound event classification from a multichannel audio mixture. Evaluating S5 systems with separation and classification metrics individually makes system comparison difficult, whereas existing joint metrics, such as the class-aware signal-to-distortion ratio (CA-SDR), can conflate separation and labeling errors. In particular, CA-SDR relies on predicted class labels for source matching, which may obscure label swaps or misclassifications when the underlying source estimates remain perce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.07075","kind":"arxiv","version":4},"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/2511.07075/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":"2511.07075","created_at":"2026-05-27T01:05:39.740840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.07075v4","created_at":"2026-05-27T01:05:39.740840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.07075","created_at":"2026-05-27T01:05:39.740840+00:00"},{"alias_kind":"pith_short_12","alias_value":"36R4UTGAAHQN","created_at":"2026-05-27T01:05:39.740840+00:00"},{"alias_kind":"pith_short_16","alias_value":"36R4UTGAAHQNYLOW","created_at":"2026-05-27T01:05:39.740840+00:00"},{"alias_kind":"pith_short_8","alias_value":"36R4UTGA","created_at":"2026-05-27T01:05:39.740840+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/36R4UTGAAHQNYLOWRTAIQ4Z7GT","json":"https://pith.science/pith/36R4UTGAAHQNYLOWRTAIQ4Z7GT.json","graph_json":"https://pith.science/api/pith-number/36R4UTGAAHQNYLOWRTAIQ4Z7GT/graph.json","events_json":"https://pith.science/api/pith-number/36R4UTGAAHQNYLOWRTAIQ4Z7GT/events.json","paper":"https://pith.science/paper/36R4UTGA"},"agent_actions":{"view_html":"https://pith.science/pith/36R4UTGAAHQNYLOWRTAIQ4Z7GT","download_json":"https://pith.science/pith/36R4UTGAAHQNYLOWRTAIQ4Z7GT.json","view_paper":"https://pith.science/paper/36R4UTGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.07075&json=true","fetch_graph":"https://pith.science/api/pith-number/36R4UTGAAHQNYLOWRTAIQ4Z7GT/graph.json","fetch_events":"https://pith.science/api/pith-number/36R4UTGAAHQNYLOWRTAIQ4Z7GT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36R4UTGAAHQNYLOWRTAIQ4Z7GT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36R4UTGAAHQNYLOWRTAIQ4Z7GT/action/storage_attestation","attest_author":"https://pith.science/pith/36R4UTGAAHQNYLOWRTAIQ4Z7GT/action/author_attestation","sign_citation":"https://pith.science/pith/36R4UTGAAHQNYLOWRTAIQ4Z7GT/action/citation_signature","submit_replication":"https://pith.science/pith/36R4UTGAAHQNYLOWRTAIQ4Z7GT/action/replication_record"}},"created_at":"2026-05-27T01:05:39.740840+00:00","updated_at":"2026-05-27T01:05:39.740840+00:00"}