{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DSFUPISWMNBSL46J4WUYD2YRZS","short_pith_number":"pith:DSFUPISW","canonical_record":{"source":{"id":"2605.13931","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-13T16:04:12Z","cross_cats_sorted":[],"title_canon_sha256":"7f0629ab88b1e4ef9a7109420dbebfcf0a21949cbf7e679c1095d9ff8fe8f41a","abstract_canon_sha256":"6fd4fd1153ce42a214604c87155603399c2bcd1f5461f6e9aff336891341ffb9"},"schema_version":"1.0"},"canonical_sha256":"1c8b47a256634325f3c9e5a981eb11cc8d88f1f672d6b6360391a27c8651238f","source":{"kind":"arxiv","id":"2605.13931","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13931","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13931v1","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13931","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"DSFUPISWMNBS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DSFUPISWMNBSL46J","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DSFUPISW","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DSFUPISWMNBSL46J4WUYD2YRZS","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13931","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-13T16:04:12Z","cross_cats_sorted":[],"title_canon_sha256":"7f0629ab88b1e4ef9a7109420dbebfcf0a21949cbf7e679c1095d9ff8fe8f41a","abstract_canon_sha256":"6fd4fd1153ce42a214604c87155603399c2bcd1f5461f6e9aff336891341ffb9"},"schema_version":"1.0"},"canonical_sha256":"1c8b47a256634325f3c9e5a981eb11cc8d88f1f672d6b6360391a27c8651238f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:13.979098Z","signature_b64":"dQpzSYfsmPVVon2PKsImPHRryi8su+wnX4MDdCPcX/vAz0scqtjsEUW3q3iR7anX6cpLrrh+qrVD93i7tqclCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c8b47a256634325f3c9e5a981eb11cc8d88f1f672d6b6360391a27c8651238f","last_reissued_at":"2026-05-17T23:39:13.978417Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:13.978417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13931","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":"2026-05-17T23:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AfHxGWL8kU8f4HTs6+jX93dfFLbUnTDPXnAsPK4yys/WYmOU6HjObdpMfxlOQiMA7JRNsJQAEgJT5lO/+cPrCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:39:47.612873Z"},"content_sha256":"62ea96fbc75e223fd705528708729e8068df5534d1e2bc9de738f9b2f4a55cc2","schema_version":"1.0","event_id":"sha256:62ea96fbc75e223fd705528708729e8068df5534d1e2bc9de738f9b2f4a55cc2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DSFUPISWMNBSL46J4WUYD2YRZS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FSD50K-Solo: Automated Curation of Single-Source Sound Events","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A framework using diffusion-generated mixtures and a pre-trained classifier automatically filters multi-source samples from FSD50K to produce the single-source subset FSD50K-Solo.","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Bryce Irvin, Li-Chia Yang, Marko Stamenovic, Ningyuan Yang, Shuo Zhang, Sile Yin, Xiao Quan","submitted_at":"2026-05-13T16:04:12Z","abstract_excerpt":"High-quality training datasets are essential for the performance of neural networks. However, the audio domain still lacks a large-scale, strongly-labeled, and single-source sound event dataset. The FSD50K dataset, despite being relatively large and open, contains a considerable fraction of multi-source samples where background interference or overlapping events could limit the usefulness of the data. To address this challenge, we introduce a data curation framework designed for large-scale open audio corpora. Our approach leverages a generative diffusion model to synthesize clean single-class"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments show that our framework achieves strong performance on a human expert-curated test set.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The pre-trained audio encoder and discriminative classifier can reliably distinguish single-source from multi-source samples when trained on diffusion-generated mixtures.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The authors present a scalable curation method that combines diffusion-based mixture synthesis with a discriminative classifier to automatically extract single-source sound events from FSD50K and release the cleaned FSD50K-Solo subset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A framework using diffusion-generated mixtures and a pre-trained classifier automatically filters multi-source samples from FSD50K to produce the single-source subset FSD50K-Solo.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8ae00d3250cc2cdfa2c47dd101c00aea3cacbf99b96ca335b5564b9f24d5495a"},"source":{"id":"2605.13931","kind":"arxiv","version":1},"verdict":{"id":"180276c2-fb26-4424-b9d1-9ec627472708","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:46:22.824941Z","strongest_claim":"Experiments show that our framework achieves strong performance on a human expert-curated test set.","one_line_summary":"The authors present a scalable curation method that combines diffusion-based mixture synthesis with a discriminative classifier to automatically extract single-source sound events from FSD50K and release the cleaned FSD50K-Solo subset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The pre-trained audio encoder and discriminative classifier can reliably distinguish single-source from multi-source samples when trained on diffusion-generated mixtures.","pith_extraction_headline":"A framework using diffusion-generated mixtures and a pre-trained classifier automatically filters multi-source samples from FSD50K to produce the single-source subset FSD50K-Solo."},"references":{"count":27,"sample":[{"doi":"","year":2025,"title":"Pseldnets: Pre-trained neural networks on a large-scale synthetic dataset for sound event localization and detection,","work_id":"1affe7d6-f32d-4240-9253-4fd46480c2d8","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Hissnet: Sound event detection and speaker identification via hierarchical prototypical networks for low-resource headphones,","work_id":"7a97c1e6-1343-4956-9881-a7b76b6782e1","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Conette: An efficient audio captioning system leveraging multiple datasets with task embedding,","work_id":"a2c839e0-8527-4abb-9567-fb54904ac4cc","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Wavcaps: A chatgpt-assisted weakly-labelled au- dio captioning dataset for audio-language multimodal research,","work_id":"b5885d8e-682b-4bfc-a808-7f3fc0ac45af","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Real-time target sound extraction,","work_id":"b0a24a79-bf89-4923-9df8-a09d28e12305","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":27,"snapshot_sha256":"d9a450525eb8a1a5a61a289d17938c10120e30f449e9bc06d6f8ce5cbe532b94","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"edf6585e7b40736339054cc53a38f7b07d5292cd561728f15afe80f6f6868824"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"180276c2-fb26-4424-b9d1-9ec627472708"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mFqNt2Sjr5WnZOm8q13i87HfE3i3oN6NcAbt4bUs/XXY7u7tADI3Yi3wMzo5z+P4v+2zg8yF1N6jGBA+yt5jAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T14:39:47.613712Z"},"content_sha256":"996b94c22e670d573210d13c0630bfd8b1568b61719484f311339451f2808dac","schema_version":"1.0","event_id":"sha256:996b94c22e670d573210d13c0630bfd8b1568b61719484f311339451f2808dac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSFUPISWMNBSL46J4WUYD2YRZS/bundle.json","state_url":"https://pith.science/pith/DSFUPISWMNBSL46J4WUYD2YRZS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSFUPISWMNBSL46J4WUYD2YRZS/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":"2026-05-26T14:39:47Z","links":{"resolver":"https://pith.science/pith/DSFUPISWMNBSL46J4WUYD2YRZS","bundle":"https://pith.science/pith/DSFUPISWMNBSL46J4WUYD2YRZS/bundle.json","state":"https://pith.science/pith/DSFUPISWMNBSL46J4WUYD2YRZS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSFUPISWMNBSL46J4WUYD2YRZS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DSFUPISWMNBSL46J4WUYD2YRZS","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":"6fd4fd1153ce42a214604c87155603399c2bcd1f5461f6e9aff336891341ffb9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-13T16:04:12Z","title_canon_sha256":"7f0629ab88b1e4ef9a7109420dbebfcf0a21949cbf7e679c1095d9ff8fe8f41a"},"schema_version":"1.0","source":{"id":"2605.13931","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13931","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13931v1","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13931","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"DSFUPISWMNBS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DSFUPISWMNBSL46J","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DSFUPISW","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:996b94c22e670d573210d13c0630bfd8b1568b61719484f311339451f2808dac","target":"graph","created_at":"2026-05-17T23:39:13Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Experiments show that our framework achieves strong performance on a human expert-curated test set."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The pre-trained audio encoder and discriminative classifier can reliably distinguish single-source from multi-source samples when trained on diffusion-generated mixtures."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"The authors present a scalable curation method that combines diffusion-based mixture synthesis with a discriminative classifier to automatically extract single-source sound events from FSD50K and release the cleaned FSD50K-Solo subset."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A framework using diffusion-generated mixtures and a pre-trained classifier automatically filters multi-source samples from FSD50K to produce the single-source subset FSD50K-Solo."}],"snapshot_sha256":"8ae00d3250cc2cdfa2c47dd101c00aea3cacbf99b96ca335b5564b9f24d5495a"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"edf6585e7b40736339054cc53a38f7b07d5292cd561728f15afe80f6f6868824"},"paper":{"abstract_excerpt":"High-quality training datasets are essential for the performance of neural networks. However, the audio domain still lacks a large-scale, strongly-labeled, and single-source sound event dataset. The FSD50K dataset, despite being relatively large and open, contains a considerable fraction of multi-source samples where background interference or overlapping events could limit the usefulness of the data. To address this challenge, we introduce a data curation framework designed for large-scale open audio corpora. Our approach leverages a generative diffusion model to synthesize clean single-class","authors_text":"Bryce Irvin, Li-Chia Yang, Marko Stamenovic, Ningyuan Yang, Shuo Zhang, Sile Yin, Xiao Quan","cross_cats":[],"headline":"A framework using diffusion-generated mixtures and a pre-trained classifier automatically filters multi-source samples from FSD50K to produce the single-source subset FSD50K-Solo.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-13T16:04:12Z","title":"FSD50K-Solo: Automated Curation of Single-Source Sound Events"},"references":{"count":27,"internal_anchors":3,"resolved_work":27,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Pseldnets: Pre-trained neural networks on a large-scale synthetic dataset for sound event localization and detection,","work_id":"1affe7d6-f32d-4240-9253-4fd46480c2d8","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Hissnet: Sound event detection and speaker identification via hierarchical prototypical networks for low-resource headphones,","work_id":"7a97c1e6-1343-4956-9881-a7b76b6782e1","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Conette: An efficient audio captioning system leveraging multiple datasets with task embedding,","work_id":"a2c839e0-8527-4abb-9567-fb54904ac4cc","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Wavcaps: A chatgpt-assisted weakly-labelled au- dio captioning dataset for audio-language multimodal research,","work_id":"b5885d8e-682b-4bfc-a808-7f3fc0ac45af","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Real-time target sound extraction,","work_id":"b0a24a79-bf89-4923-9df8-a09d28e12305","year":2023}],"snapshot_sha256":"d9a450525eb8a1a5a61a289d17938c10120e30f449e9bc06d6f8ce5cbe532b94"},"source":{"id":"2605.13931","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:46:22.824941Z","id":"180276c2-fb26-4424-b9d1-9ec627472708","model_set":{"reader":"grok-4.3"},"one_line_summary":"The authors present a scalable curation method that combines diffusion-based mixture synthesis with a discriminative classifier to automatically extract single-source sound events from FSD50K and release the cleaned FSD50K-Solo subset.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A framework using diffusion-generated mixtures and a pre-trained classifier automatically filters multi-source samples from FSD50K to produce the single-source subset FSD50K-Solo.","strongest_claim":"Experiments show that our framework achieves strong performance on a human expert-curated test set.","weakest_assumption":"The pre-trained audio encoder and discriminative classifier can reliably distinguish single-source from multi-source samples when trained on diffusion-generated mixtures."}},"verdict_id":"180276c2-fb26-4424-b9d1-9ec627472708"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:62ea96fbc75e223fd705528708729e8068df5534d1e2bc9de738f9b2f4a55cc2","target":"record","created_at":"2026-05-17T23:39:13Z","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":"6fd4fd1153ce42a214604c87155603399c2bcd1f5461f6e9aff336891341ffb9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-13T16:04:12Z","title_canon_sha256":"7f0629ab88b1e4ef9a7109420dbebfcf0a21949cbf7e679c1095d9ff8fe8f41a"},"schema_version":"1.0","source":{"id":"2605.13931","kind":"arxiv","version":1}},"canonical_sha256":"1c8b47a256634325f3c9e5a981eb11cc8d88f1f672d6b6360391a27c8651238f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c8b47a256634325f3c9e5a981eb11cc8d88f1f672d6b6360391a27c8651238f","first_computed_at":"2026-05-17T23:39:13.978417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:13.978417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dQpzSYfsmPVVon2PKsImPHRryi8su+wnX4MDdCPcX/vAz0scqtjsEUW3q3iR7anX6cpLrrh+qrVD93i7tqclCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:13.979098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13931","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62ea96fbc75e223fd705528708729e8068df5534d1e2bc9de738f9b2f4a55cc2","sha256:996b94c22e670d573210d13c0630bfd8b1568b61719484f311339451f2808dac"],"state_sha256":"6b6894fb72dacfc4788d1f1575a2c11ab8f10452f1e926bae3479e9d998fde16"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PKW14mfkx5giKHh5z6YAe/bhO9fSsl67Tdw2EsuIaS6fS037j36/DV1HlF3PhxDQDvCtdsU6ywU6fIqae+S+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T14:39:47.617494Z","bundle_sha256":"da7f59435d05d61a460309746df1c6f3f4968c04876b5cb3b080fceab616c255"}}