{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A4YK4IJWWA24Q5XJNV4VFAUGMS","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":"e171aea47a2eec776d482c6f8c312c45d7a4c189b0de41a45d977c4f24bad394","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-20T01:31:29Z","title_canon_sha256":"0d93eea6b5e6b6f79d73c2b342060db979a70129ea2d70b02ab5f0a76402f47a"},"schema_version":"1.0","source":{"id":"2409.13152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.13152","created_at":"2026-07-05T09:09:30Z"},{"alias_kind":"arxiv_version","alias_value":"2409.13152v1","created_at":"2026-07-05T09:09:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.13152","created_at":"2026-07-05T09:09:30Z"},{"alias_kind":"pith_short_12","alias_value":"A4YK4IJWWA24","created_at":"2026-07-05T09:09:30Z"},{"alias_kind":"pith_short_16","alias_value":"A4YK4IJWWA24Q5XJ","created_at":"2026-07-05T09:09:30Z"},{"alias_kind":"pith_short_8","alias_value":"A4YK4IJW","created_at":"2026-07-05T09:09:30Z"}],"graph_snapshots":[{"event_id":"sha256:3e4fc675a09466447a93c0d2d399bed57e70a2943fdf4d41d8b778050cd70227","target":"graph","created_at":"2026-07-05T09:09:30Z","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/2409.13152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of text-queried target sound extraction (TSE) is to extract from a mixture a sound source specified with a natural-language caption. While it is preferable to have access to large-scale text-audio pairs to address a variety of text prompts, the limited number of available high-quality text-audio pairs hinders the data scaling. To this end, this work explores how to leverage audio-only data without any captions for the text-queried TSE task to potentially scale up the data amount. A straightforward way to do so is to use a joint audio-text embedding model, such as the contrastive langu","authors_text":"Fran\\c{c}ois G. Germain, Gordon Wichern, Janek Ebbers, Jonathan Le Roux, Kohei Saijo, Sameer Khurana","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-20T01:31:29Z","title":"Leveraging Audio-Only Data for Text-Queried Target Sound Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.13152","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:b4d5ae5d2015dc5b36ef2f21fafbd777d4788c9732f80f45ba5dda2ccca80c6d","target":"record","created_at":"2026-07-05T09:09:30Z","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":"e171aea47a2eec776d482c6f8c312c45d7a4c189b0de41a45d977c4f24bad394","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-20T01:31:29Z","title_canon_sha256":"0d93eea6b5e6b6f79d73c2b342060db979a70129ea2d70b02ab5f0a76402f47a"},"schema_version":"1.0","source":{"id":"2409.13152","kind":"arxiv","version":1}},"canonical_sha256":"0730ae2136b035c876e96d7952828664bc42fe037613d178f46255bded5dae56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0730ae2136b035c876e96d7952828664bc42fe037613d178f46255bded5dae56","first_computed_at":"2026-07-05T09:09:30.194933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:30.194933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zdp8Sve3i0TD5C5wkhyHo9Uwt+2Q4Wy2eDYzExox6+qcan08gTOyuzUqJ4ho620X7ZpFBtD++8P6myXH9ln5Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:30.195407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.13152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4d5ae5d2015dc5b36ef2f21fafbd777d4788c9732f80f45ba5dda2ccca80c6d","sha256:3e4fc675a09466447a93c0d2d399bed57e70a2943fdf4d41d8b778050cd70227"],"state_sha256":"50504d55d025287f3582751895536106a1c6e32e97e05c6a34efa43e23b5cd69"}