{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WJCYMB4MLAUR742D5KKED3RZBV","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":"3c11ae57396701e0ad6b7ebd851ee63de301f525c8cde4416587522e13b34709","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-28T17:58:15Z","title_canon_sha256":"ac3bdc65c95f29afd614e6eb9ed620395a84c9e248ff7389c3c087b777f4d8b2"},"schema_version":"1.0","source":{"id":"2410.21269","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21269","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21269v1","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21269","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"pith_short_12","alias_value":"WJCYMB4MLAUR","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"pith_short_16","alias_value":"WJCYMB4MLAUR742D","created_at":"2026-07-05T09:27:17Z"},{"alias_kind":"pith_short_8","alias_value":"WJCYMB4M","created_at":"2026-07-05T09:27:17Z"}],"graph_snapshots":[{"event_id":"sha256:3da251a1d2087c2fbc562c3a5afe56d0a3f4c5be57f0dc148c1eb49f8264bccf","target":"graph","created_at":"2026-07-05T09:27:17Z","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/2410.21269/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jialong Zuo, Minghui Fang, Rongjie Huang, Shengpeng Ji, Siqi Zheng, Tao Jin, Xize Cheng, Zehan Wang, Zhou Zhao, Ziang Zhang, Ziyang Ma","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-28T17:58:15Z","title":"OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21269","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":"sha256:225ddde14d4f5c617341a926a082ad421e1c737b65a7d994c05e8512bdf0b119","target":"record","created_at":"2026-07-05T09:27:17Z","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":"3c11ae57396701e0ad6b7ebd851ee63de301f525c8cde4416587522e13b34709","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-28T17:58:15Z","title_canon_sha256":"ac3bdc65c95f29afd614e6eb9ed620395a84c9e248ff7389c3c087b777f4d8b2"},"schema_version":"1.0","source":{"id":"2410.21269","kind":"arxiv","version":1}},"canonical_sha256":"b24586078c58291ff343ea9441ee390d6b755e04c1868b4c1ac5670015452d4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b24586078c58291ff343ea9441ee390d6b755e04c1868b4c1ac5670015452d4a","first_computed_at":"2026-07-05T09:27:17.701306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:17.701306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N/uTeiMozLIIyEnuWJyTt37YmqPryaP4GVWl0ZuiHc71z6lBUQjsKJR9IF08J6zRnyKc34ykM61ANrDjUlsTAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:17.701846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.21269","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:225ddde14d4f5c617341a926a082ad421e1c737b65a7d994c05e8512bdf0b119","sha256:3da251a1d2087c2fbc562c3a5afe56d0a3f4c5be57f0dc148c1eb49f8264bccf"],"state_sha256":"af350686553b580cdb1f3124ac0643b2131830b6b419f7d0b0ab04d556927a20"}