{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H5VASNQ2EE2YTEFRBDLZU2KRRL","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":"eb15a75666ea88006a8d6ec3edd322a23abe86057e8372cb703f65c5335670cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-27T12:27:18Z","title_canon_sha256":"cef9b539afad9875a72eb80dce1173ed81d1ff3b0ea19fd4d4c2e2cd0d7dae57"},"schema_version":"1.0","source":{"id":"2402.17455","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17455","created_at":"2026-07-05T10:36:24Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17455v5","created_at":"2026-07-05T10:36:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17455","created_at":"2026-07-05T10:36:24Z"},{"alias_kind":"pith_short_12","alias_value":"H5VASNQ2EE2Y","created_at":"2026-07-05T10:36:24Z"},{"alias_kind":"pith_short_16","alias_value":"H5VASNQ2EE2YTEFR","created_at":"2026-07-05T10:36:24Z"},{"alias_kind":"pith_short_8","alias_value":"H5VASNQ2","created_at":"2026-07-05T10:36:24Z"}],"graph_snapshots":[{"event_id":"sha256:cff6de71225625328ad69201c2f30a978081e2425eff4986b0b354c758c8365c","target":"graph","created_at":"2026-07-05T10:36:24Z","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/2402.17455/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings. This can be achieved by language-queried target sound extraction (TSE), which typically consists of two components: a query network that converts user queries into conditional embeddings, and a separation network that extracts the target sound accordingly. Existing methods commonly train models from scratch. As a consequence, substantial data and computational resources are required to make the randomly initialized model comprehend sound events and perform separation accordingly. In this pape","authors_text":"Hao Ma, Ju Liu, Mingjie Shao, Xixin Wu, Xu Li, Zhiyuan Peng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-27T12:27:18Z","title":"CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17455","kind":"arxiv","version":5},"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":"sha256:314459f2644fbb6eeddce399fb3e015e27ee306eaa0bfe3a1932f492bed731cd","target":"record","created_at":"2026-07-05T10:36:24Z","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":"eb15a75666ea88006a8d6ec3edd322a23abe86057e8372cb703f65c5335670cc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-27T12:27:18Z","title_canon_sha256":"cef9b539afad9875a72eb80dce1173ed81d1ff3b0ea19fd4d4c2e2cd0d7dae57"},"schema_version":"1.0","source":{"id":"2402.17455","kind":"arxiv","version":5}},"canonical_sha256":"3f6a09361a21358990b108d79a69518ada1f61d0d762502306d213a05c730e0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f6a09361a21358990b108d79a69518ada1f61d0d762502306d213a05c730e0c","first_computed_at":"2026-07-05T10:36:24.125000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:36:24.125000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WAjuZo86emfkcRk7n7SwO15eVpT3kdm76jAJ30nPe4P+lfN9VKj9VIAkPeKurCTmAfmAzMyOQm5dG2oViHZHAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:36:24.125739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17455","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:314459f2644fbb6eeddce399fb3e015e27ee306eaa0bfe3a1932f492bed731cd","sha256:cff6de71225625328ad69201c2f30a978081e2425eff4986b0b354c758c8365c"],"state_sha256":"01130f14d855ee3eb6e1fb0acd7c650371c2e6eeae2aee33af4a067fab1a5590"}