{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UFEXWP2YCRCUJQG2L7MZY2MMDB","short_pith_number":"pith:UFEXWP2Y","schema_version":"1.0","canonical_sha256":"a1497b3f58144544c0da5fd99c698c184330c2f2bd8c049d681073d1fe9f42c4","source":{"kind":"arxiv","id":"2004.14368","version":2},"attestation_state":"computed","paper":{"title":"VGGSound: A Large-scale Audio-Visual Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Honglie Chen, Weidi Xie","submitted_at":"2020-04-29T17:46:54Z","abstract_excerpt":"Our goal is to collect a large-scale audio-visual dataset with low label noise from videos in the wild using computer vision techniques. The resulting dataset can be used for training and evaluating audio recognition models. We make three contributions. First, we propose a scalable pipeline based on computer vision techniques to create an audio dataset from open-source media. Our pipeline involves obtaining videos from YouTube; using image classification algorithms to localize audio-visual correspondence; and filtering out ambient noise using audio verification. Second, we use this pipeline to"},"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":"2004.14368","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-29T17:46:54Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4d8e2259031cf50b3647fac9a945fbc0045258154b5f71f89164bf7f98a6d6da","abstract_canon_sha256":"0a5799e5326bc9ddc00065d2a2872cbda8f76dfcc8a23992e795b971f8523afb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:54.158574Z","signature_b64":"dRhxuTsbI4fdcngWE/5+szFR712GCgJACDnaT84VwiZHi6deJ+rNM0NaiLKIMSjP5Y3DQwIozMaLgLmXiHLdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1497b3f58144544c0da5fd99c698c184330c2f2bd8c049d681073d1fe9f42c4","last_reissued_at":"2026-07-05T01:37:54.158089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:54.158089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VGGSound: A Large-scale Audio-Visual Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Honglie Chen, Weidi Xie","submitted_at":"2020-04-29T17:46:54Z","abstract_excerpt":"Our goal is to collect a large-scale audio-visual dataset with low label noise from videos in the wild using computer vision techniques. The resulting dataset can be used for training and evaluating audio recognition models. We make three contributions. First, we propose a scalable pipeline based on computer vision techniques to create an audio dataset from open-source media. Our pipeline involves obtaining videos from YouTube; using image classification algorithms to localize audio-visual correspondence; and filtering out ambient noise using audio verification. Second, we use this pipeline to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14368","kind":"arxiv","version":2},"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/2004.14368/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":"2004.14368","created_at":"2026-07-05T01:37:54.158149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.14368v2","created_at":"2026-07-05T01:37:54.158149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14368","created_at":"2026-07-05T01:37:54.158149+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFEXWP2YCRCU","created_at":"2026-07-05T01:37:54.158149+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFEXWP2YCRCUJQG2","created_at":"2026-07-05T01:37:54.158149+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFEXWP2Y","created_at":"2026-07-05T01:37:54.158149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03168","citing_title":"JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12145","citing_title":"Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12145","citing_title":"Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14129","citing_title":"Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB","json":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB.json","graph_json":"https://pith.science/api/pith-number/UFEXWP2YCRCUJQG2L7MZY2MMDB/graph.json","events_json":"https://pith.science/api/pith-number/UFEXWP2YCRCUJQG2L7MZY2MMDB/events.json","paper":"https://pith.science/paper/UFEXWP2Y"},"agent_actions":{"view_html":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB","download_json":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB.json","view_paper":"https://pith.science/paper/UFEXWP2Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.14368&json=true","fetch_graph":"https://pith.science/api/pith-number/UFEXWP2YCRCUJQG2L7MZY2MMDB/graph.json","fetch_events":"https://pith.science/api/pith-number/UFEXWP2YCRCUJQG2L7MZY2MMDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB/action/storage_attestation","attest_author":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB/action/author_attestation","sign_citation":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB/action/citation_signature","submit_replication":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB/action/replication_record"}},"created_at":"2026-07-05T01:37:54.158149+00:00","updated_at":"2026-07-05T01:37:54.158149+00:00"}