{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QALHAX2ARO7HJMWK5IAXOHWMBQ","short_pith_number":"pith:QALHAX2A","canonical_record":{"source":{"id":"2409.08425","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-12T23:12:25Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"53fe194d438a706cdc14c261c9795aea7e5728764953cc04d929af25fc5d6194","abstract_canon_sha256":"215d0b9a7e91ee6ad80c4496115b3332fee16c5acf0c4b0b1999f3b908bd9457"},"schema_version":"1.0"},"canonical_sha256":"8016705f408bbe74b2caea01771ecc0c295cdb83e66045b43dbca1860521e54d","source":{"kind":"arxiv","id":"2409.08425","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08425","created_at":"2026-07-05T09:56:00Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08425v2","created_at":"2026-07-05T09:56:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08425","created_at":"2026-07-05T09:56:00Z"},{"alias_kind":"pith_short_12","alias_value":"QALHAX2ARO7H","created_at":"2026-07-05T09:56:00Z"},{"alias_kind":"pith_short_16","alias_value":"QALHAX2ARO7HJMWK","created_at":"2026-07-05T09:56:00Z"},{"alias_kind":"pith_short_8","alias_value":"QALHAX2A","created_at":"2026-07-05T09:56:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QALHAX2ARO7HJMWK5IAXOHWMBQ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.08425","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-12T23:12:25Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"53fe194d438a706cdc14c261c9795aea7e5728764953cc04d929af25fc5d6194","abstract_canon_sha256":"215d0b9a7e91ee6ad80c4496115b3332fee16c5acf0c4b0b1999f3b908bd9457"},"schema_version":"1.0"},"canonical_sha256":"8016705f408bbe74b2caea01771ecc0c295cdb83e66045b43dbca1860521e54d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:00.561731Z","signature_b64":"ysL5Pr5GL/bJv1x70+eJyU2LTMjXsPltBIM9ladjiLJKwONYq82Q40BvuxGgQzv4eO8h3Kj8EgPLiy3moph7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8016705f408bbe74b2caea01771ecc0c295cdb83e66045b43dbca1860521e54d","last_reissued_at":"2026-07-05T09:56:00.561240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:00.561240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.08425","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:56:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dn41iS+febzEklNzEoWTnfuOvq4Xajlu9w8J1MY9plz6RuwpAIF+L+dmmmueQi444wOoMwG4aQUa07VXrZVgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:11:37.576073Z"},"content_sha256":"a5721eb9a8614356125dbfb67066bb467d4402dab1a38d7d35518f8899498515","schema_version":"1.0","event_id":"sha256:a5721eb9a8614356125dbfb67066bb467d4402dab1a38d7d35518f8899498515"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QALHAX2ARO7HJMWK5IAXOHWMBQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Helin Wang, Jiarui Hai, Karan Thakkar, Mounya Elhilali, Najim Dehak, Yen-Ju Lu","submitted_at":"2024-09-12T23:12:25Z","abstract_excerpt":"In this paper, we introduce SoloAudio, a novel diffusion-based generative model for target sound extraction (TSE). Our approach trains latent diffusion models on audio, replacing the previous U-Net backbone with a skip-connected Transformer that operates on latent features. SoloAudio supports both audio-oriented and language-oriented TSE by utilizing a CLAP model as the feature extractor for target sounds. Furthermore, SoloAudio leverages synthetic audio generated by state-of-the-art text-to-audio models for training, demonstrating strong generalization to out-of-domain data and unseen sound e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08425","kind":"arxiv","version":2},"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/2409.08425/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":"2026-07-05T09:56:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2voGPbiSMH57bwyfFKtLMKVxIElicw7Fo2vBaqkUrts1RBEz5ZYVZa5HsEJdPsVhSsPeB74ERXaiVz5NEs51CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:11:37.576667Z"},"content_sha256":"0ce946ac96f594a38ede7446cfd069eac224c6352b6f55c70bc7f959364ca3a7","schema_version":"1.0","event_id":"sha256:0ce946ac96f594a38ede7446cfd069eac224c6352b6f55c70bc7f959364ca3a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ/bundle.json","state_url":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ/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":"2026-08-08T20:11:37Z","links":{"resolver":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ","bundle":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ/bundle.json","state":"https://pith.science/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QALHAX2ARO7HJMWK5IAXOHWMBQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QALHAX2ARO7HJMWK5IAXOHWMBQ","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":"215d0b9a7e91ee6ad80c4496115b3332fee16c5acf0c4b0b1999f3b908bd9457","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-12T23:12:25Z","title_canon_sha256":"53fe194d438a706cdc14c261c9795aea7e5728764953cc04d929af25fc5d6194"},"schema_version":"1.0","source":{"id":"2409.08425","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.08425","created_at":"2026-07-05T09:56:00Z"},{"alias_kind":"arxiv_version","alias_value":"2409.08425v2","created_at":"2026-07-05T09:56:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08425","created_at":"2026-07-05T09:56:00Z"},{"alias_kind":"pith_short_12","alias_value":"QALHAX2ARO7H","created_at":"2026-07-05T09:56:00Z"},{"alias_kind":"pith_short_16","alias_value":"QALHAX2ARO7HJMWK","created_at":"2026-07-05T09:56:00Z"},{"alias_kind":"pith_short_8","alias_value":"QALHAX2A","created_at":"2026-07-05T09:56:00Z"}],"graph_snapshots":[{"event_id":"sha256:0ce946ac96f594a38ede7446cfd069eac224c6352b6f55c70bc7f959364ca3a7","target":"graph","created_at":"2026-07-05T09:56:00Z","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/2409.08425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce SoloAudio, a novel diffusion-based generative model for target sound extraction (TSE). Our approach trains latent diffusion models on audio, replacing the previous U-Net backbone with a skip-connected Transformer that operates on latent features. SoloAudio supports both audio-oriented and language-oriented TSE by utilizing a CLAP model as the feature extractor for target sounds. Furthermore, SoloAudio leverages synthetic audio generated by state-of-the-art text-to-audio models for training, demonstrating strong generalization to out-of-domain data and unseen sound e","authors_text":"Helin Wang, Jiarui Hai, Karan Thakkar, Mounya Elhilali, Najim Dehak, Yen-Ju Lu","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-12T23:12:25Z","title":"SoloAudio: Target Sound Extraction with Language-oriented Audio Diffusion Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08425","kind":"arxiv","version":2},"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:a5721eb9a8614356125dbfb67066bb467d4402dab1a38d7d35518f8899498515","target":"record","created_at":"2026-07-05T09:56:00Z","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":"215d0b9a7e91ee6ad80c4496115b3332fee16c5acf0c4b0b1999f3b908bd9457","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-12T23:12:25Z","title_canon_sha256":"53fe194d438a706cdc14c261c9795aea7e5728764953cc04d929af25fc5d6194"},"schema_version":"1.0","source":{"id":"2409.08425","kind":"arxiv","version":2}},"canonical_sha256":"8016705f408bbe74b2caea01771ecc0c295cdb83e66045b43dbca1860521e54d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8016705f408bbe74b2caea01771ecc0c295cdb83e66045b43dbca1860521e54d","first_computed_at":"2026-07-05T09:56:00.561240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:00.561240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ysL5Pr5GL/bJv1x70+eJyU2LTMjXsPltBIM9ladjiLJKwONYq82Q40BvuxGgQzv4eO8h3Kj8EgPLiy3moph7Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:00.561731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.08425","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5721eb9a8614356125dbfb67066bb467d4402dab1a38d7d35518f8899498515","sha256:0ce946ac96f594a38ede7446cfd069eac224c6352b6f55c70bc7f959364ca3a7"],"state_sha256":"c14ddfbbde980d271bfba3b3963922d347f95106e7258fb8074c981ec61e06ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i7XFDwmEztF2pKGgpektDIo5nLN6jlcpG9E+MB96tXdmNPr3B07VVcIhLxYPvlaIvkD9SYOakAxbEhxJEaUTAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:11:37.581598Z","bundle_sha256":"1ed80263a372c9147a4e55fcc50f6475e3a616e187a97cbc6e3dcaafe83c3f82"}}