{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U2QNEWSNTOZMWYH33Z4TZRXDG3","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":"55d4f43682f317a876bc70cac609eb5d69ab6f0b88c4280bd749cc2f32f4cb4f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T19:41:49Z","title_canon_sha256":"285ce96bb1b777a59a99c5d491feb205125e0a042fddf514f270f1f30b4854fa"},"schema_version":"1.0","source":{"id":"2308.00122","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.00122","created_at":"2026-07-05T09:18:51Z"},{"alias_kind":"arxiv_version","alias_value":"2308.00122v2","created_at":"2026-07-05T09:18:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.00122","created_at":"2026-07-05T09:18:51Z"},{"alias_kind":"pith_short_12","alias_value":"U2QNEWSNTOZM","created_at":"2026-07-05T09:18:51Z"},{"alias_kind":"pith_short_16","alias_value":"U2QNEWSNTOZMWYH3","created_at":"2026-07-05T09:18:51Z"},{"alias_kind":"pith_short_8","alias_value":"U2QNEWSN","created_at":"2026-07-05T09:18:51Z"}],"graph_snapshots":[{"event_id":"sha256:c252d079ba1c8f51104c811175f455a0ed86bc8af7ae1143600f97d083c65754","target":"graph","created_at":"2026-07-05T09:18:51Z","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/2308.00122/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning. Existing methods typically frame sound separation as a mask-based regression problem, achieving significant progress. However, they face limitations in capturing the complex data distribution required for high-quality separation of sounds from diverse categories. In contrast, DAVIS leverages a generative diffusion model and a Separation U-Net to synthesize separated sounds directly from Gaussian noise, conditioned on both the audio mixture","authors_text":"Anurag Kumar, Chao Huang, Chenliang Xu, Susan Liang, Yapeng Tian","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T19:41:49Z","title":"High-Quality Visually-Guided Sound Separation from Diverse Categories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.00122","kind":"arxiv","version":2},"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:ce9b18b6fa733d3ae816c6feae134c16fba5730c5f0e548dc1dc3f8b8df2a57c","target":"record","created_at":"2026-07-05T09:18:51Z","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":"55d4f43682f317a876bc70cac609eb5d69ab6f0b88c4280bd749cc2f32f4cb4f","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-31T19:41:49Z","title_canon_sha256":"285ce96bb1b777a59a99c5d491feb205125e0a042fddf514f270f1f30b4854fa"},"schema_version":"1.0","source":{"id":"2308.00122","kind":"arxiv","version":2}},"canonical_sha256":"a6a0d25a4d9bb2cb60fbde793cc6e336d9e56a7cfa57129f0638b400f3041fcc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6a0d25a4d9bb2cb60fbde793cc6e336d9e56a7cfa57129f0638b400f3041fcc","first_computed_at":"2026-07-05T09:18:51.039609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:51.039609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2lusl+2S/Zy/mAKqyuNQD/Wojo51ERGCRE+GF9gnCF6nub+EHLL3WtAwqX+v+qiRVfCu8VR7UthPAeC1v89PAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:51.040046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.00122","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce9b18b6fa733d3ae816c6feae134c16fba5730c5f0e548dc1dc3f8b8df2a57c","sha256:c252d079ba1c8f51104c811175f455a0ed86bc8af7ae1143600f97d083c65754"],"state_sha256":"a1104ba345d6e767da5af6e50001a0085b6aaea23e5782e1155b1aee352f8ddd"}