{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HUWGCQ7H4N7IL7XHLNEI3XS46K","short_pith_number":"pith:HUWGCQ7H","schema_version":"1.0","canonical_sha256":"3d2c6143e7e37e85fee75b488dde5cf2b78d6dbd99da27632b07006639e83d81","source":{"kind":"arxiv","id":"2606.01804","version":1},"attestation_state":"computed","paper":{"title":"SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daxin Tan, Dehua Tao, Hanlin Zhang, Haochen Tan, Linqi Song, Xiao Chen","submitted_at":"2026-06-01T07:21:02Z","abstract_excerpt":"Instruction-guided speech editing requires a model to modify specified speech attributes while preserving unrelated characteristics. Despite rapid progress in Speech Large Language Models (Speech LLMs), systematic evaluation of this capability remains challenging, as existing benchmarks are fragmented across isolated editing tasks. To bridge this gap, we introduce \\textbf{SpeechEditBench}, a bilingual multi-attribute benchmark for instruction-guided speech editing. SpeechEditBench encompasses seven atomic editing tasks, as well as compositional editing tasks that integrate multiple operations "},"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":"2606.01804","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-01T07:21:02Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"00a709267775b32369f5a68cac7ae0ab509ee4111c61b176fe5a6d63b591da43","abstract_canon_sha256":"7d85c4d3bd67dbe1b946a4c83b8bda6d9c75cec0158277bbcdf6a38f8616a3f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:57.369686Z","signature_b64":"jDuCONaAW62venXqtHVqRuVJCM+xB/MnyGJvc0DwRn5b1F2zh3G1AujgMoSZsVINd7fvtjsAvmzzq0oZTZEcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d2c6143e7e37e85fee75b488dde5cf2b78d6dbd99da27632b07006639e83d81","last_reissued_at":"2026-06-02T02:04:57.369297Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:57.369297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daxin Tan, Dehua Tao, Hanlin Zhang, Haochen Tan, Linqi Song, Xiao Chen","submitted_at":"2026-06-01T07:21:02Z","abstract_excerpt":"Instruction-guided speech editing requires a model to modify specified speech attributes while preserving unrelated characteristics. Despite rapid progress in Speech Large Language Models (Speech LLMs), systematic evaluation of this capability remains challenging, as existing benchmarks are fragmented across isolated editing tasks. To bridge this gap, we introduce \\textbf{SpeechEditBench}, a bilingual multi-attribute benchmark for instruction-guided speech editing. SpeechEditBench encompasses seven atomic editing tasks, as well as compositional editing tasks that integrate multiple operations "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01804","kind":"arxiv","version":1},"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/2606.01804/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":"2606.01804","created_at":"2026-06-02T02:04:57.369371+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01804v1","created_at":"2026-06-02T02:04:57.369371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01804","created_at":"2026-06-02T02:04:57.369371+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUWGCQ7H4N7I","created_at":"2026-06-02T02:04:57.369371+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUWGCQ7H4N7IL7XH","created_at":"2026-06-02T02:04:57.369371+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUWGCQ7H","created_at":"2026-06-02T02:04:57.369371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HUWGCQ7H4N7IL7XHLNEI3XS46K","json":"https://pith.science/pith/HUWGCQ7H4N7IL7XHLNEI3XS46K.json","graph_json":"https://pith.science/api/pith-number/HUWGCQ7H4N7IL7XHLNEI3XS46K/graph.json","events_json":"https://pith.science/api/pith-number/HUWGCQ7H4N7IL7XHLNEI3XS46K/events.json","paper":"https://pith.science/paper/HUWGCQ7H"},"agent_actions":{"view_html":"https://pith.science/pith/HUWGCQ7H4N7IL7XHLNEI3XS46K","download_json":"https://pith.science/pith/HUWGCQ7H4N7IL7XHLNEI3XS46K.json","view_paper":"https://pith.science/paper/HUWGCQ7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01804&json=true","fetch_graph":"https://pith.science/api/pith-number/HUWGCQ7H4N7IL7XHLNEI3XS46K/graph.json","fetch_events":"https://pith.science/api/pith-number/HUWGCQ7H4N7IL7XHLNEI3XS46K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUWGCQ7H4N7IL7XHLNEI3XS46K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUWGCQ7H4N7IL7XHLNEI3XS46K/action/storage_attestation","attest_author":"https://pith.science/pith/HUWGCQ7H4N7IL7XHLNEI3XS46K/action/author_attestation","sign_citation":"https://pith.science/pith/HUWGCQ7H4N7IL7XHLNEI3XS46K/action/citation_signature","submit_replication":"https://pith.science/pith/HUWGCQ7H4N7IL7XHLNEI3XS46K/action/replication_record"}},"created_at":"2026-06-02T02:04:57.369371+00:00","updated_at":"2026-06-02T02:04:57.369371+00:00"}