{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Y3WQIVZWCJISEO2WOVIRZ5DQFS","short_pith_number":"pith:Y3WQIVZW","canonical_record":{"source":{"id":"2505.23625","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-29T16:31:45Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"5963e875bde4c808fa1cda1895eab273555fb511be581c599a61087eb7f5e8a9","abstract_canon_sha256":"4a4536de7fea3750f41392a714ef3041c28469eba75e7fe15c50f1355b362b23"},"schema_version":"1.0"},"canonical_sha256":"c6ed0457361251223b5675511cf4702ca55b227107ee362c477c7b4f063bfd67","source":{"kind":"arxiv","id":"2505.23625","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23625","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23625v1","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23625","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_12","alias_value":"Y3WQIVZWCJIS","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_16","alias_value":"Y3WQIVZWCJISEO2W","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_8","alias_value":"Y3WQIVZW","created_at":"2026-07-05T11:12:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Y3WQIVZWCJISEO2WOVIRZ5DQFS","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23625","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-29T16:31:45Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"5963e875bde4c808fa1cda1895eab273555fb511be581c599a61087eb7f5e8a9","abstract_canon_sha256":"4a4536de7fea3750f41392a714ef3041c28469eba75e7fe15c50f1355b362b23"},"schema_version":"1.0"},"canonical_sha256":"c6ed0457361251223b5675511cf4702ca55b227107ee362c477c7b4f063bfd67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:12.495915Z","signature_b64":"y/KUf6PsrdE2wIz9Ev1FLealywRNgqOY1+TOHWQDb9jpo7lhZfat2bTd+TH8XYgv5QJ9XwJDKM+qrdQoaHBIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6ed0457361251223b5675511cf4702ca55b227107ee362c477c7b4f063bfd67","last_reissued_at":"2026-07-05T11:12:12.495361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:12.495361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23625","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":"2026-07-05T11:12:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O0nk0jg7PHZtYNZSMuCndApiUrB04O+0v1SYD1i4ADTp4nNByw/2xM3GoremIGKrlr+d3q9lHbCkaiRCqaJLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T07:56:40.581830Z"},"content_sha256":"4b5fc489eb495614ca7faeeae495124e4e90b98617d6bf72c1e59a15211612bc","schema_version":"1.0","event_id":"sha256:4b5fc489eb495614ca7faeeae495124e4e90b98617d6bf72c1e59a15211612bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Y3WQIVZWCJISEO2WOVIRZ5DQFS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ZeroSep: Separate Anything in Audio with Zero Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chao Huang, Chenliang Xu, Jing Bi, Junxuan Huang, Nima Mesgarani, Susan Liang, Wenqiang Liu, Yuesheng Ma, Yunlong Tang","submitted_at":"2025-05-29T16:31:45Z","abstract_excerpt":"Audio source separation is fundamental for machines to understand complex acoustic environments and underpins numerous audio applications. Current supervised deep learning approaches, while powerful, are limited by the need for extensive, task-specific labeled data and struggle to generalize to the immense variability and open-set nature of real-world acoustic scenes. Inspired by the success of generative foundation models, we investigate whether pre-trained text-guided audio diffusion models can overcome these limitations. We make a surprising discovery: zero-shot source separation can be ach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23625","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/2505.23625/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":"2026-07-05T11:12:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J7W4WV9xOynUbphK1Xm06DN4Ae6hCbQfRuDEm72vc+0wmaQifru0yPbHi6KaoY8baHDxUPTx/UGeas2gNI35BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T07:56:40.582201Z"},"content_sha256":"4bd38c8a2435678aac529e8bb81630874a1186cf4c7b8eadce12ca73037ca7e4","schema_version":"1.0","event_id":"sha256:4bd38c8a2435678aac529e8bb81630874a1186cf4c7b8eadce12ca73037ca7e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y3WQIVZWCJISEO2WOVIRZ5DQFS/bundle.json","state_url":"https://pith.science/pith/Y3WQIVZWCJISEO2WOVIRZ5DQFS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y3WQIVZWCJISEO2WOVIRZ5DQFS/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":"2026-07-16T07:56:40Z","links":{"resolver":"https://pith.science/pith/Y3WQIVZWCJISEO2WOVIRZ5DQFS","bundle":"https://pith.science/pith/Y3WQIVZWCJISEO2WOVIRZ5DQFS/bundle.json","state":"https://pith.science/pith/Y3WQIVZWCJISEO2WOVIRZ5DQFS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y3WQIVZWCJISEO2WOVIRZ5DQFS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y3WQIVZWCJISEO2WOVIRZ5DQFS","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":"4a4536de7fea3750f41392a714ef3041c28469eba75e7fe15c50f1355b362b23","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-29T16:31:45Z","title_canon_sha256":"5963e875bde4c808fa1cda1895eab273555fb511be581c599a61087eb7f5e8a9"},"schema_version":"1.0","source":{"id":"2505.23625","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23625","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23625v1","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23625","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_12","alias_value":"Y3WQIVZWCJIS","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_16","alias_value":"Y3WQIVZWCJISEO2W","created_at":"2026-07-05T11:12:12Z"},{"alias_kind":"pith_short_8","alias_value":"Y3WQIVZW","created_at":"2026-07-05T11:12:12Z"}],"graph_snapshots":[{"event_id":"sha256:4bd38c8a2435678aac529e8bb81630874a1186cf4c7b8eadce12ca73037ca7e4","target":"graph","created_at":"2026-07-05T11:12:12Z","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/2505.23625/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio source separation is fundamental for machines to understand complex acoustic environments and underpins numerous audio applications. Current supervised deep learning approaches, while powerful, are limited by the need for extensive, task-specific labeled data and struggle to generalize to the immense variability and open-set nature of real-world acoustic scenes. Inspired by the success of generative foundation models, we investigate whether pre-trained text-guided audio diffusion models can overcome these limitations. We make a surprising discovery: zero-shot source separation can be ach","authors_text":"Chao Huang, Chenliang Xu, Jing Bi, Junxuan Huang, Nima Mesgarani, Susan Liang, Wenqiang Liu, Yuesheng Ma, Yunlong Tang","cross_cats":["cs.CV","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-29T16:31:45Z","title":"ZeroSep: Separate Anything in Audio with Zero Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23625","kind":"arxiv","version":1},"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":"sha256:4b5fc489eb495614ca7faeeae495124e4e90b98617d6bf72c1e59a15211612bc","target":"record","created_at":"2026-07-05T11:12:12Z","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":"4a4536de7fea3750f41392a714ef3041c28469eba75e7fe15c50f1355b362b23","cross_cats_sorted":["cs.CV","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-29T16:31:45Z","title_canon_sha256":"5963e875bde4c808fa1cda1895eab273555fb511be581c599a61087eb7f5e8a9"},"schema_version":"1.0","source":{"id":"2505.23625","kind":"arxiv","version":1}},"canonical_sha256":"c6ed0457361251223b5675511cf4702ca55b227107ee362c477c7b4f063bfd67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6ed0457361251223b5675511cf4702ca55b227107ee362c477c7b4f063bfd67","first_computed_at":"2026-07-05T11:12:12.495361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:12.495361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y/KUf6PsrdE2wIz9Ev1FLealywRNgqOY1+TOHWQDb9jpo7lhZfat2bTd+TH8XYgv5QJ9XwJDKM+qrdQoaHBIAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:12.495915Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23625","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b5fc489eb495614ca7faeeae495124e4e90b98617d6bf72c1e59a15211612bc","sha256:4bd38c8a2435678aac529e8bb81630874a1186cf4c7b8eadce12ca73037ca7e4"],"state_sha256":"35369b2d2e23ffc65dfe67f4d269b491dfec48a217820022d44c0d7800e6740d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4WhvJyVo9K9c4FkfnW4/FKO7VE/z830UE00L3iumEnb8RVoTwv1kpdQlUVkAkEcFo+NYavtRJ0zpxeWdj5aEBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T07:56:40.584783Z","bundle_sha256":"f6cc7f07fff98b3af3bf2cf117a114456df0719a8ccbfff91d4d9f39708b16e5"}}