{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PAW5ZN2DOSMZ5KQRR6G5I4KFSX","short_pith_number":"pith:PAW5ZN2D","schema_version":"1.0","canonical_sha256":"782ddcb74374999eaa118f8dd4714595f6be0bbbf6fa67b1441104795732896a","source":{"kind":"arxiv","id":"2308.05037","version":3},"attestation_state":"computed","paper":{"title":"Separate Anything You Describe","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Haohe Liu, Mark D. Plumbley, Qiuqiang Kong, Rui Xia, Wenwu Wang, Xubo Liu, Yan Zhao, Yi Yuan, Yuxuan Wang, Yuzhuo Liu","submitted_at":"2023-08-09T16:09:44Z","abstract_excerpt":"Language-queried audio source separation (LASS) is a new paradigm for computational auditory scene analysis (CASA). LASS aims to separate a target sound from an audio mixture given a natural language query, which provides a natural and scalable interface for digital audio applications. Recent works on LASS, despite attaining promising separation performance on specific sources (e.g., musical instruments, limited classes of audio events), are unable to separate audio concepts in the open domain. In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with"},"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":"2308.05037","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-08-09T16:09:44Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"title_canon_sha256":"6ab6cee41b6abf13aa5588b7f1c6fad3af286849e16bfe17b1f448d97f2748fd","abstract_canon_sha256":"23837776e524453c66fc6784a3108930fd9a8729e78a6f7d84a2b2412aa64d7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:19.645729Z","signature_b64":"qB8iyZGHOQKBu7j35eR6Ush7BzqyCeOrAo/u7zIPmLJWyaVo7Kstj+f3/OrozsqZR+hbs6nNnCl2/WI0l3p3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"782ddcb74374999eaa118f8dd4714595f6be0bbbf6fa67b1441104795732896a","last_reissued_at":"2026-07-05T09:42:19.645221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:19.645221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Separate Anything You Describe","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Haohe Liu, Mark D. Plumbley, Qiuqiang Kong, Rui Xia, Wenwu Wang, Xubo Liu, Yan Zhao, Yi Yuan, Yuxuan Wang, Yuzhuo Liu","submitted_at":"2023-08-09T16:09:44Z","abstract_excerpt":"Language-queried audio source separation (LASS) is a new paradigm for computational auditory scene analysis (CASA). LASS aims to separate a target sound from an audio mixture given a natural language query, which provides a natural and scalable interface for digital audio applications. Recent works on LASS, despite attaining promising separation performance on specific sources (e.g., musical instruments, limited classes of audio events), are unable to separate audio concepts in the open domain. In this work, we introduce AudioSep, a foundation model for open-domain audio source separation with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.05037","kind":"arxiv","version":3},"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/2308.05037/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":"2308.05037","created_at":"2026-07-05T09:42:19.645286+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.05037v3","created_at":"2026-07-05T09:42:19.645286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.05037","created_at":"2026-07-05T09:42:19.645286+00:00"},{"alias_kind":"pith_short_12","alias_value":"PAW5ZN2DOSMZ","created_at":"2026-07-05T09:42:19.645286+00:00"},{"alias_kind":"pith_short_16","alias_value":"PAW5ZN2DOSMZ5KQR","created_at":"2026-07-05T09:42:19.645286+00:00"},{"alias_kind":"pith_short_8","alias_value":"PAW5ZN2D","created_at":"2026-07-05T09:42:19.645286+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01804","citing_title":"SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11717","citing_title":"CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2510.09065","citing_title":"MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PAW5ZN2DOSMZ5KQRR6G5I4KFSX","json":"https://pith.science/pith/PAW5ZN2DOSMZ5KQRR6G5I4KFSX.json","graph_json":"https://pith.science/api/pith-number/PAW5ZN2DOSMZ5KQRR6G5I4KFSX/graph.json","events_json":"https://pith.science/api/pith-number/PAW5ZN2DOSMZ5KQRR6G5I4KFSX/events.json","paper":"https://pith.science/paper/PAW5ZN2D"},"agent_actions":{"view_html":"https://pith.science/pith/PAW5ZN2DOSMZ5KQRR6G5I4KFSX","download_json":"https://pith.science/pith/PAW5ZN2DOSMZ5KQRR6G5I4KFSX.json","view_paper":"https://pith.science/paper/PAW5ZN2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.05037&json=true","fetch_graph":"https://pith.science/api/pith-number/PAW5ZN2DOSMZ5KQRR6G5I4KFSX/graph.json","fetch_events":"https://pith.science/api/pith-number/PAW5ZN2DOSMZ5KQRR6G5I4KFSX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PAW5ZN2DOSMZ5KQRR6G5I4KFSX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PAW5ZN2DOSMZ5KQRR6G5I4KFSX/action/storage_attestation","attest_author":"https://pith.science/pith/PAW5ZN2DOSMZ5KQRR6G5I4KFSX/action/author_attestation","sign_citation":"https://pith.science/pith/PAW5ZN2DOSMZ5KQRR6G5I4KFSX/action/citation_signature","submit_replication":"https://pith.science/pith/PAW5ZN2DOSMZ5KQRR6G5I4KFSX/action/replication_record"}},"created_at":"2026-07-05T09:42:19.645286+00:00","updated_at":"2026-07-05T09:42:19.645286+00:00"}