{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FCQ3EGNQTRYIDPVW2R6XMUW4CT","short_pith_number":"pith:FCQ3EGNQ","schema_version":"1.0","canonical_sha256":"28a1b219b09c7081beb6d47d7652dc14d5a9b965c770c8282ee3cf7f8c46437f","source":{"kind":"arxiv","id":"2402.10009","version":4},"attestation_state":"computed","paper":{"title":"Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hila Manor, Tomer Michaeli","submitted_at":"2024-02-15T15:17:26Z","abstract_excerpt":"Editing signals using large pre-trained models, in a zero-shot manner, has recently seen rapid advancements in the image domain. However, this wave has yet to reach the audio domain. In this paper, we explore two zero-shot editing techniques for audio signals, which use DDPM inversion with pre-trained diffusion models. The first, which we coin ZEro-shot Text-based Audio (ZETA) editing, is adopted from the image domain. The second, named ZEro-shot UnSupervized (ZEUS) editing, is a novel approach for discovering semantically meaningful editing directions without supervision. When applied to musi"},"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":"2402.10009","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-02-15T15:17:26Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"946a1d3a29e970f11594284a0cc889313da41ea02388af15e1f69587b058dbd6","abstract_canon_sha256":"4eba53f1d84f105e7bc9f5db01fefdd1ec10e35f9271464da5787a92a27415ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:41.311118Z","signature_b64":"0IIAPr4h1b6ufYy1t6AYCQmyLMw/xJc29UbscXiRDcTrpv35GrE/EKrz6Gu0v39FZi2RHjBtHHqjvunkIo+5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28a1b219b09c7081beb6d47d7652dc14d5a9b965c770c8282ee3cf7f8c46437f","last_reissued_at":"2026-07-05T08:24:41.310693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:41.310693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Unsupervised and Text-Based Audio Editing Using DDPM Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hila Manor, Tomer Michaeli","submitted_at":"2024-02-15T15:17:26Z","abstract_excerpt":"Editing signals using large pre-trained models, in a zero-shot manner, has recently seen rapid advancements in the image domain. However, this wave has yet to reach the audio domain. In this paper, we explore two zero-shot editing techniques for audio signals, which use DDPM inversion with pre-trained diffusion models. The first, which we coin ZEro-shot Text-based Audio (ZETA) editing, is adopted from the image domain. The second, named ZEro-shot UnSupervized (ZEUS) editing, is a novel approach for discovering semantically meaningful editing directions without supervision. When applied to musi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10009","kind":"arxiv","version":4},"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/2402.10009/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":"2402.10009","created_at":"2026-07-05T08:24:41.310749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10009v4","created_at":"2026-07-05T08:24:41.310749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10009","created_at":"2026-07-05T08:24:41.310749+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCQ3EGNQTRYI","created_at":"2026-07-05T08:24:41.310749+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCQ3EGNQTRYIDPVW","created_at":"2026-07-05T08:24:41.310749+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCQ3EGNQ","created_at":"2026-07-05T08:24:41.310749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13675","citing_title":"Improving Robotic Generalist Policies via Flow Reversal Steering","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31053","citing_title":"AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2502.04230","citing_title":"XAttnMark: Learning Robust Audio Watermarking with Cross-Attention","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2508.03448","citing_title":"SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14003","citing_title":"RFM-Editing: Rectified Flow Matching for Text-guided Audio Editing","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCQ3EGNQTRYIDPVW2R6XMUW4CT","json":"https://pith.science/pith/FCQ3EGNQTRYIDPVW2R6XMUW4CT.json","graph_json":"https://pith.science/api/pith-number/FCQ3EGNQTRYIDPVW2R6XMUW4CT/graph.json","events_json":"https://pith.science/api/pith-number/FCQ3EGNQTRYIDPVW2R6XMUW4CT/events.json","paper":"https://pith.science/paper/FCQ3EGNQ"},"agent_actions":{"view_html":"https://pith.science/pith/FCQ3EGNQTRYIDPVW2R6XMUW4CT","download_json":"https://pith.science/pith/FCQ3EGNQTRYIDPVW2R6XMUW4CT.json","view_paper":"https://pith.science/paper/FCQ3EGNQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10009&json=true","fetch_graph":"https://pith.science/api/pith-number/FCQ3EGNQTRYIDPVW2R6XMUW4CT/graph.json","fetch_events":"https://pith.science/api/pith-number/FCQ3EGNQTRYIDPVW2R6XMUW4CT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCQ3EGNQTRYIDPVW2R6XMUW4CT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCQ3EGNQTRYIDPVW2R6XMUW4CT/action/storage_attestation","attest_author":"https://pith.science/pith/FCQ3EGNQTRYIDPVW2R6XMUW4CT/action/author_attestation","sign_citation":"https://pith.science/pith/FCQ3EGNQTRYIDPVW2R6XMUW4CT/action/citation_signature","submit_replication":"https://pith.science/pith/FCQ3EGNQTRYIDPVW2R6XMUW4CT/action/replication_record"}},"created_at":"2026-07-05T08:24:41.310749+00:00","updated_at":"2026-07-05T08:24:41.310749+00:00"}