{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2FRBDBLJWVXLEJNR4XALAWDSAM","short_pith_number":"pith:2FRBDBLJ","schema_version":"1.0","canonical_sha256":"d162118569b56eb225b1e5c0b05872032e50ac84fbab426286d3d0cfdb16b1bc","source":{"kind":"arxiv","id":"2507.11096","version":1},"attestation_state":"computed","paper":{"title":"EditGen: Harnessing Cross-Attention Control for Instruction-Based Auto-Regressive Audio Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexandros Potamianos, Giorgos Paraskevopoulos, Vassilis Sioros","submitted_at":"2025-07-15T08:44:11Z","abstract_excerpt":"In this study, we investigate leveraging cross-attention control for efficient audio editing within auto-regressive models. Inspired by image editing methodologies, we develop a Prompt-to-Prompt-like approach that guides edits through cross and self-attention mechanisms. Integrating a diffusion-based strategy, influenced by Auffusion, we extend the model's functionality to support refinement edits, establishing a baseline for prompt-guided audio editing. Additionally, we introduce an alternative approach by incorporating MUSICGEN, a pre-trained frozen auto-regressive model, and propose three e"},"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":"2507.11096","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-15T08:44:11Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"ab2b3503dd32350b0c4fb3e2985cf71c841422b059b63acb1df8f27d292fc509","abstract_canon_sha256":"4704d71a589e73845adf629e8721bfaaf4eaa604ec4b369f488568e03b05f61f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:31.903990Z","signature_b64":"hYP3MJD09h1QWeECSgTS6t4yZEFsGsnSlRx/pRP8s0TN2+qIi6UDcCcDsfYmuPXy3+gSb5ZQ93S4z7wT/CupBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d162118569b56eb225b1e5c0b05872032e50ac84fbab426286d3d0cfdb16b1bc","last_reissued_at":"2026-07-05T11:37:31.903481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:31.903481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EditGen: Harnessing Cross-Attention Control for Instruction-Based Auto-Regressive Audio Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexandros Potamianos, Giorgos Paraskevopoulos, Vassilis Sioros","submitted_at":"2025-07-15T08:44:11Z","abstract_excerpt":"In this study, we investigate leveraging cross-attention control for efficient audio editing within auto-regressive models. Inspired by image editing methodologies, we develop a Prompt-to-Prompt-like approach that guides edits through cross and self-attention mechanisms. Integrating a diffusion-based strategy, influenced by Auffusion, we extend the model's functionality to support refinement edits, establishing a baseline for prompt-guided audio editing. Additionally, we introduce an alternative approach by incorporating MUSICGEN, a pre-trained frozen auto-regressive model, and propose three e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11096","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/2507.11096/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":"2507.11096","created_at":"2026-07-05T11:37:31.903551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.11096v1","created_at":"2026-07-05T11:37:31.903551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11096","created_at":"2026-07-05T11:37:31.903551+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FRBDBLJWVXL","created_at":"2026-07-05T11:37:31.903551+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FRBDBLJWVXLEJNR","created_at":"2026-07-05T11:37:31.903551+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FRBDBLJ","created_at":"2026-07-05T11:37:31.903551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21227","citing_title":"Bagpiper-Edit: Zero-Shot Open-Ended Audio Editing via Rich-Caption","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FRBDBLJWVXLEJNR4XALAWDSAM","json":"https://pith.science/pith/2FRBDBLJWVXLEJNR4XALAWDSAM.json","graph_json":"https://pith.science/api/pith-number/2FRBDBLJWVXLEJNR4XALAWDSAM/graph.json","events_json":"https://pith.science/api/pith-number/2FRBDBLJWVXLEJNR4XALAWDSAM/events.json","paper":"https://pith.science/paper/2FRBDBLJ"},"agent_actions":{"view_html":"https://pith.science/pith/2FRBDBLJWVXLEJNR4XALAWDSAM","download_json":"https://pith.science/pith/2FRBDBLJWVXLEJNR4XALAWDSAM.json","view_paper":"https://pith.science/paper/2FRBDBLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.11096&json=true","fetch_graph":"https://pith.science/api/pith-number/2FRBDBLJWVXLEJNR4XALAWDSAM/graph.json","fetch_events":"https://pith.science/api/pith-number/2FRBDBLJWVXLEJNR4XALAWDSAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FRBDBLJWVXLEJNR4XALAWDSAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FRBDBLJWVXLEJNR4XALAWDSAM/action/storage_attestation","attest_author":"https://pith.science/pith/2FRBDBLJWVXLEJNR4XALAWDSAM/action/author_attestation","sign_citation":"https://pith.science/pith/2FRBDBLJWVXLEJNR4XALAWDSAM/action/citation_signature","submit_replication":"https://pith.science/pith/2FRBDBLJWVXLEJNR4XALAWDSAM/action/replication_record"}},"created_at":"2026-07-05T11:37:31.903551+00:00","updated_at":"2026-07-05T11:37:31.903551+00:00"}