{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WJCYMB4MLAUR742D5KKED3RZBV","short_pith_number":"pith:WJCYMB4M","schema_version":"1.0","canonical_sha256":"b24586078c58291ff343ea9441ee390d6b755e04c1868b4c1ac5670015452d4a","source":{"kind":"arxiv","id":"2410.21269","version":1},"attestation_state":"computed","paper":{"title":"OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jialong Zuo, Minghui Fang, Rongjie Huang, Shengpeng Ji, Siqi Zheng, Tao Jin, Xize Cheng, Zehan Wang, Zhou Zhao, Ziang Zhang, Ziyang Ma","submitted_at":"2024-10-28T17:58:15Z","abstract_excerpt":"The scaling up has brought tremendous success in the fields of vision and language in recent years. When it comes to audio, however, researchers encounter a major challenge in scaling up the training data, as most natural audio contains diverse interfering signals. To address this limitation, we introduce Omni-modal Sound Separation (OmniSep), a novel framework capable of isolating clean soundtracks based on omni-modal queries, encompassing both single-modal and multi-modal composed queries. Specifically, we introduce the Query-Mixup strategy, which blends query features from different modalit"},"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":"2410.21269","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-28T17:58:15Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"ac3bdc65c95f29afd614e6eb9ed620395a84c9e248ff7389c3c087b777f4d8b2","abstract_canon_sha256":"3c11ae57396701e0ad6b7ebd851ee63de301f525c8cde4416587522e13b34709"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:17.701846Z","signature_b64":"N/uTeiMozLIIyEnuWJyTt37YmqPryaP4GVWl0ZuiHc71z6lBUQjsKJR9IF08J6zRnyKc34ykM61ANrDjUlsTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b24586078c58291ff343ea9441ee390d6b755e04c1868b4c1ac5670015452d4a","last_reissued_at":"2026-07-05T09:27:17.701306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:17.701306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jialong Zuo, Minghui Fang, Rongjie Huang, Shengpeng Ji, Siqi Zheng, Tao Jin, Xize Cheng, Zehan Wang, Zhou Zhao, Ziang Zhang, Ziyang Ma","submitted_at":"2024-10-28T17:58:15Z","abstract_excerpt":"The scaling up has brought tremendous success in the fields of vision and language in recent years. When it comes to audio, however, researchers encounter a major challenge in scaling up the training data, as most natural audio contains diverse interfering signals. To address this limitation, we introduce Omni-modal Sound Separation (OmniSep), a novel framework capable of isolating clean soundtracks based on omni-modal queries, encompassing both single-modal and multi-modal composed queries. Specifically, we introduce the Query-Mixup strategy, which blends query features from different modalit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21269","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/2410.21269/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":"2410.21269","created_at":"2026-07-05T09:27:17.701383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.21269v1","created_at":"2026-07-05T09:27:17.701383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21269","created_at":"2026-07-05T09:27:17.701383+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJCYMB4MLAUR","created_at":"2026-07-05T09:27:17.701383+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJCYMB4MLAUR742D","created_at":"2026-07-05T09:27:17.701383+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJCYMB4M","created_at":"2026-07-05T09:27:17.701383+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23954","citing_title":"EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10571","citing_title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WJCYMB4MLAUR742D5KKED3RZBV","json":"https://pith.science/pith/WJCYMB4MLAUR742D5KKED3RZBV.json","graph_json":"https://pith.science/api/pith-number/WJCYMB4MLAUR742D5KKED3RZBV/graph.json","events_json":"https://pith.science/api/pith-number/WJCYMB4MLAUR742D5KKED3RZBV/events.json","paper":"https://pith.science/paper/WJCYMB4M"},"agent_actions":{"view_html":"https://pith.science/pith/WJCYMB4MLAUR742D5KKED3RZBV","download_json":"https://pith.science/pith/WJCYMB4MLAUR742D5KKED3RZBV.json","view_paper":"https://pith.science/paper/WJCYMB4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.21269&json=true","fetch_graph":"https://pith.science/api/pith-number/WJCYMB4MLAUR742D5KKED3RZBV/graph.json","fetch_events":"https://pith.science/api/pith-number/WJCYMB4MLAUR742D5KKED3RZBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJCYMB4MLAUR742D5KKED3RZBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJCYMB4MLAUR742D5KKED3RZBV/action/storage_attestation","attest_author":"https://pith.science/pith/WJCYMB4MLAUR742D5KKED3RZBV/action/author_attestation","sign_citation":"https://pith.science/pith/WJCYMB4MLAUR742D5KKED3RZBV/action/citation_signature","submit_replication":"https://pith.science/pith/WJCYMB4MLAUR742D5KKED3RZBV/action/replication_record"}},"created_at":"2026-07-05T09:27:17.701383+00:00","updated_at":"2026-07-05T09:27:17.701383+00:00"}