{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L5TV2LJLIQSSOWRJG7EH24WTVT","short_pith_number":"pith:L5TV2LJL","schema_version":"1.0","canonical_sha256":"5f675d2d2b4425275a2937c87d72d3acdf1ea2703817460e655b0c2449e8ac29","source":{"kind":"arxiv","id":"2504.21366","version":1},"attestation_state":"computed","paper":{"title":"DGFNet: End-to-End Audio-Visual Source Separation Based on Dynamic Gating Fusion","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Shiyu Sun, Yinfeng Yu","submitted_at":"2025-04-30T06:55:24Z","abstract_excerpt":"Current Audio-Visual Source Separation methods primarily adopt two design strategies. The first strategy involves fusing audio and visual features at the bottleneck layer of the encoder, followed by processing the fused features through the decoder. However, when there is a significant disparity between the two modalities, this approach may lead to the loss of critical information. The second strategy avoids direct fusion and instead relies on the decoder to handle the interaction between audio and visual features. Nonetheless, if the encoder fails to integrate information across modalities ad"},"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":"2504.21366","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2025-04-30T06:55:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3565e562a712a23ea947e71f0852504c3dd11f5b4e026cf303a529f8e0f7a810","abstract_canon_sha256":"19509f79302a8a3ac79370bc8570955b0cc73284c555b019fabef5e4afd3197d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:22.827920Z","signature_b64":"2X2wAf7BMgrlGK8ac37xyyAwtbIFbglVhFOnLSEwD1+VeAqkcc6TDbBbYh0X67pxk3+O4Bcq0WSL6TPY3Dt+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f675d2d2b4425275a2937c87d72d3acdf1ea2703817460e655b0c2449e8ac29","last_reissued_at":"2026-07-05T10:56:22.827551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:22.827551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DGFNet: End-to-End Audio-Visual Source Separation Based on Dynamic Gating Fusion","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Shiyu Sun, Yinfeng Yu","submitted_at":"2025-04-30T06:55:24Z","abstract_excerpt":"Current Audio-Visual Source Separation methods primarily adopt two design strategies. The first strategy involves fusing audio and visual features at the bottleneck layer of the encoder, followed by processing the fused features through the decoder. However, when there is a significant disparity between the two modalities, this approach may lead to the loss of critical information. The second strategy avoids direct fusion and instead relies on the decoder to handle the interaction between audio and visual features. Nonetheless, if the encoder fails to integrate information across modalities ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21366","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/2504.21366/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":"2504.21366","created_at":"2026-07-05T10:56:22.827612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21366v1","created_at":"2026-07-05T10:56:22.827612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21366","created_at":"2026-07-05T10:56:22.827612+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5TV2LJLIQSS","created_at":"2026-07-05T10:56:22.827612+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5TV2LJLIQSSOWRJ","created_at":"2026-07-05T10:56:22.827612+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5TV2LJL","created_at":"2026-07-05T10:56:22.827612+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/L5TV2LJLIQSSOWRJG7EH24WTVT","json":"https://pith.science/pith/L5TV2LJLIQSSOWRJG7EH24WTVT.json","graph_json":"https://pith.science/api/pith-number/L5TV2LJLIQSSOWRJG7EH24WTVT/graph.json","events_json":"https://pith.science/api/pith-number/L5TV2LJLIQSSOWRJG7EH24WTVT/events.json","paper":"https://pith.science/paper/L5TV2LJL"},"agent_actions":{"view_html":"https://pith.science/pith/L5TV2LJLIQSSOWRJG7EH24WTVT","download_json":"https://pith.science/pith/L5TV2LJLIQSSOWRJG7EH24WTVT.json","view_paper":"https://pith.science/paper/L5TV2LJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21366&json=true","fetch_graph":"https://pith.science/api/pith-number/L5TV2LJLIQSSOWRJG7EH24WTVT/graph.json","fetch_events":"https://pith.science/api/pith-number/L5TV2LJLIQSSOWRJG7EH24WTVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5TV2LJLIQSSOWRJG7EH24WTVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5TV2LJLIQSSOWRJG7EH24WTVT/action/storage_attestation","attest_author":"https://pith.science/pith/L5TV2LJLIQSSOWRJG7EH24WTVT/action/author_attestation","sign_citation":"https://pith.science/pith/L5TV2LJLIQSSOWRJG7EH24WTVT/action/citation_signature","submit_replication":"https://pith.science/pith/L5TV2LJLIQSSOWRJG7EH24WTVT/action/replication_record"}},"created_at":"2026-07-05T10:56:22.827612+00:00","updated_at":"2026-07-05T10:56:22.827612+00:00"}