{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3NTTMYPT3RBMM6VQ7H6237SPF7","short_pith_number":"pith:3NTTMYPT","schema_version":"1.0","canonical_sha256":"db673661f3dc42c67ab0f9fdadfe4f2fe9f854ec8b8710512650b913b0e01b5a","source":{"kind":"arxiv","id":"2212.07065","version":2},"attestation_state":"computed","paper":{"title":"CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hao-Wen Dong, Julian McAuley, Naoya Takahashi, Taylor Berg-Kirkpatrick, Yuki Mitsufuji","submitted_at":"2022-12-14T07:21:45Z","abstract_excerpt":"Recent years have seen progress beyond domain-specific sound separation for speech or music towards universal sound separation for arbitrary sounds. Prior work on universal sound separation has investigated separating a target sound out of an audio mixture given a text query. Such text-queried sound separation systems provide a natural and scalable interface for specifying arbitrary target sounds. However, supervised text-queried sound separation systems require costly labeled audio-text pairs for training. Moreover, the audio provided in existing datasets is often recorded in a controlled env"},"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":"2212.07065","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-12-14T07:21:45Z","cross_cats_sorted":["cs.CV","cs.LG","cs.MM","eess.AS"],"title_canon_sha256":"92886f6e8e4e4b8ca0d167176b9d3f342bec675e54b648f0be3e3a65c8dfd3d1","abstract_canon_sha256":"d8541cfccc46a74d896f2a68214b745f0f0df6b00b5f6eb215cba47c21b9c077"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:04.599243Z","signature_b64":"yqgNQXocf8xMKRI/JFXpkcHm2l+Ij61TmU2+p8lNhAwWWaUHUkcxDSraEEVOt4e3YhPNWZ/0LbQplxd+wBn6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db673661f3dc42c67ab0f9fdadfe4f2fe9f854ec8b8710512650b913b0e01b5a","last_reissued_at":"2026-07-05T05:48:04.598772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:04.598772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hao-Wen Dong, Julian McAuley, Naoya Takahashi, Taylor Berg-Kirkpatrick, Yuki Mitsufuji","submitted_at":"2022-12-14T07:21:45Z","abstract_excerpt":"Recent years have seen progress beyond domain-specific sound separation for speech or music towards universal sound separation for arbitrary sounds. Prior work on universal sound separation has investigated separating a target sound out of an audio mixture given a text query. Such text-queried sound separation systems provide a natural and scalable interface for specifying arbitrary target sounds. However, supervised text-queried sound separation systems require costly labeled audio-text pairs for training. Moreover, the audio provided in existing datasets is often recorded in a controlled env"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07065","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/2212.07065/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":"2212.07065","created_at":"2026-07-05T05:48:04.598828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.07065v2","created_at":"2026-07-05T05:48:04.598828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07065","created_at":"2026-07-05T05:48:04.598828+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NTTMYPT3RBM","created_at":"2026-07-05T05:48:04.598828+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NTTMYPT3RBMM6VQ","created_at":"2026-07-05T05:48:04.598828+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NTTMYPT","created_at":"2026-07-05T05:48:04.598828+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02343","citing_title":"SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NTTMYPT3RBMM6VQ7H6237SPF7","json":"https://pith.science/pith/3NTTMYPT3RBMM6VQ7H6237SPF7.json","graph_json":"https://pith.science/api/pith-number/3NTTMYPT3RBMM6VQ7H6237SPF7/graph.json","events_json":"https://pith.science/api/pith-number/3NTTMYPT3RBMM6VQ7H6237SPF7/events.json","paper":"https://pith.science/paper/3NTTMYPT"},"agent_actions":{"view_html":"https://pith.science/pith/3NTTMYPT3RBMM6VQ7H6237SPF7","download_json":"https://pith.science/pith/3NTTMYPT3RBMM6VQ7H6237SPF7.json","view_paper":"https://pith.science/paper/3NTTMYPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.07065&json=true","fetch_graph":"https://pith.science/api/pith-number/3NTTMYPT3RBMM6VQ7H6237SPF7/graph.json","fetch_events":"https://pith.science/api/pith-number/3NTTMYPT3RBMM6VQ7H6237SPF7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NTTMYPT3RBMM6VQ7H6237SPF7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NTTMYPT3RBMM6VQ7H6237SPF7/action/storage_attestation","attest_author":"https://pith.science/pith/3NTTMYPT3RBMM6VQ7H6237SPF7/action/author_attestation","sign_citation":"https://pith.science/pith/3NTTMYPT3RBMM6VQ7H6237SPF7/action/citation_signature","submit_replication":"https://pith.science/pith/3NTTMYPT3RBMM6VQ7H6237SPF7/action/replication_record"}},"created_at":"2026-07-05T05:48:04.598828+00:00","updated_at":"2026-07-05T05:48:04.598828+00:00"}