{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PIVOGWKQFA3HF57SSBD5ISDLKZ","short_pith_number":"pith:PIVOGWKQ","schema_version":"1.0","canonical_sha256":"7a2ae35950283672f7f29047d4486b564233810e9b509e88e36530ab6286da24","source":{"kind":"arxiv","id":"2505.16076","version":1},"attestation_state":"computed","paper":{"title":"AudioMorphix: Training-free audio editing with diffusion probabilistic models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Dongya Jia, Jinhua Liang, Xiaobin Zhuang, Yi Yuan, Yuanzhe Chen, Yuping Wang, Yuxuan Wang, Zhuo Chen","submitted_at":"2025-05-21T23:23:37Z","abstract_excerpt":"Editing sound with precision is a crucial yet underexplored challenge in audio content creation. While existing works can manipulate sounds by text instructions or audio exemplar pairs, they often struggled to modify audio content precisely while preserving fidelity to the original recording. In this work, we introduce a novel editing approach that enables localized modifications to specific time-frequency regions while keeping the remaining of the audio intact by operating on spectrograms directly. To achieve this, we propose AudioMorphix, a training-free audio editor that manipulates a targe"},"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":"2505.16076","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-05-21T23:23:37Z","cross_cats_sorted":[],"title_canon_sha256":"cd2e62362f3c98b2ec892ffd95cb33124dc723dd0debc3601f565680be5a3ddb","abstract_canon_sha256":"36f3dcb29237ce7c01a409c2ec3ea230d98915333ff0f6a7805f7c33eb31d0f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:29.482260Z","signature_b64":"XVEwTTBRILSvw16Y/0U4Unqa6fk7M6ViaEnaaChJXjZIp6lkynPXY46a4oudozzYMc2U4jwZ8qgrsd3Micu3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a2ae35950283672f7f29047d4486b564233810e9b509e88e36530ab6286da24","last_reissued_at":"2026-07-05T11:07:29.481785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:29.481785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioMorphix: Training-free audio editing with diffusion probabilistic models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Dongya Jia, Jinhua Liang, Xiaobin Zhuang, Yi Yuan, Yuanzhe Chen, Yuping Wang, Yuxuan Wang, Zhuo Chen","submitted_at":"2025-05-21T23:23:37Z","abstract_excerpt":"Editing sound with precision is a crucial yet underexplored challenge in audio content creation. While existing works can manipulate sounds by text instructions or audio exemplar pairs, they often struggled to modify audio content precisely while preserving fidelity to the original recording. In this work, we introduce a novel editing approach that enables localized modifications to specific time-frequency regions while keeping the remaining of the audio intact by operating on spectrograms directly. To achieve this, we propose AudioMorphix, a training-free audio editor that manipulates a targe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16076","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/2505.16076/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":"2505.16076","created_at":"2026-07-05T11:07:29.481841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16076v1","created_at":"2026-07-05T11:07:29.481841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16076","created_at":"2026-07-05T11:07:29.481841+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIVOGWKQFA3H","created_at":"2026-07-05T11:07:29.481841+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIVOGWKQFA3HF57S","created_at":"2026-07-05T11:07:29.481841+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIVOGWKQ","created_at":"2026-07-05T11:07:29.481841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23139","citing_title":"Audio Editing in the Era of Foundation Models: A Survey","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20101","citing_title":"Hybrid Diffusion Transformer for Instruction-Guided Audio Editing via Rectified Flow","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20101","citing_title":"Hybrid Diffusion Transformer for Instruction-Guided Audio Editing via Rectified Flow","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07229","citing_title":"MMAE: A Massive Multitask Audio Editing Benchmark","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PIVOGWKQFA3HF57SSBD5ISDLKZ","json":"https://pith.science/pith/PIVOGWKQFA3HF57SSBD5ISDLKZ.json","graph_json":"https://pith.science/api/pith-number/PIVOGWKQFA3HF57SSBD5ISDLKZ/graph.json","events_json":"https://pith.science/api/pith-number/PIVOGWKQFA3HF57SSBD5ISDLKZ/events.json","paper":"https://pith.science/paper/PIVOGWKQ"},"agent_actions":{"view_html":"https://pith.science/pith/PIVOGWKQFA3HF57SSBD5ISDLKZ","download_json":"https://pith.science/pith/PIVOGWKQFA3HF57SSBD5ISDLKZ.json","view_paper":"https://pith.science/paper/PIVOGWKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16076&json=true","fetch_graph":"https://pith.science/api/pith-number/PIVOGWKQFA3HF57SSBD5ISDLKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/PIVOGWKQFA3HF57SSBD5ISDLKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIVOGWKQFA3HF57SSBD5ISDLKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIVOGWKQFA3HF57SSBD5ISDLKZ/action/storage_attestation","attest_author":"https://pith.science/pith/PIVOGWKQFA3HF57SSBD5ISDLKZ/action/author_attestation","sign_citation":"https://pith.science/pith/PIVOGWKQFA3HF57SSBD5ISDLKZ/action/citation_signature","submit_replication":"https://pith.science/pith/PIVOGWKQFA3HF57SSBD5ISDLKZ/action/replication_record"}},"created_at":"2026-07-05T11:07:29.481841+00:00","updated_at":"2026-07-05T11:07:29.481841+00:00"}