{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UFEXWP2YCRCUJQG2L7MZY2MMDB","short_pith_number":"pith:UFEXWP2Y","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"},"canonical_sha256":"a1497b3f58144544c0da5fd99c698c184330c2f2bd8c049d681073d1fe9f42c4","source":{"kind":"arxiv","id":"2004.14368","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14368","created_at":"2026-07-05T01:37:54Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14368v2","created_at":"2026-07-05T01:37:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14368","created_at":"2026-07-05T01:37:54Z"},{"alias_kind":"pith_short_12","alias_value":"UFEXWP2YCRCU","created_at":"2026-07-05T01:37:54Z"},{"alias_kind":"pith_short_16","alias_value":"UFEXWP2YCRCUJQG2","created_at":"2026-07-05T01:37:54Z"},{"alias_kind":"pith_short_8","alias_value":"UFEXWP2Y","created_at":"2026-07-05T01:37:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UFEXWP2YCRCUJQG2L7MZY2MMDB","target":"record","payload":{"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"},"canonical_sha256":"a1497b3f58144544c0da5fd99c698c184330c2f2bd8c049d681073d1fe9f42c4","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"},"source_kind":"arxiv","source_id":"2004.14368","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:37:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fsnxd/KEMZC+VFGlmO6CRgrzVJaa2JDXGQiPqFmaPf/mn47YOmr5sCxFWBnsy4/+FVrEXdz21Ucwndr4MDfsCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:23:50.572970Z"},"content_sha256":"452644515d13d0211439a07d59cd328bd2c78e5e94179a75592d9f595e9b2087","schema_version":"1.0","event_id":"sha256:452644515d13d0211439a07d59cd328bd2c78e5e94179a75592d9f595e9b2087"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UFEXWP2YCRCUJQG2L7MZY2MMDB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:37:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yAz37UbWPh3Vn94jL2bP9qP94RUY+Ri8fP/0WKD/FooXx+vepK8fTga0MPvmNU/vSYftI3liNyMAhJGh3NrBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:23:50.573370Z"},"content_sha256":"994d9263673888bef86ed1b1f8854e93df40cb5ec0936f55d2add06c257fbcc6","schema_version":"1.0","event_id":"sha256:994d9263673888bef86ed1b1f8854e93df40cb5ec0936f55d2add06c257fbcc6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB/bundle.json","state_url":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T23:23:50Z","links":{"resolver":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB","bundle":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB/bundle.json","state":"https://pith.science/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UFEXWP2YCRCUJQG2L7MZY2MMDB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UFEXWP2YCRCUJQG2L7MZY2MMDB","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":"0a5799e5326bc9ddc00065d2a2872cbda8f76dfcc8a23992e795b971f8523afb","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-29T17:46:54Z","title_canon_sha256":"4d8e2259031cf50b3647fac9a945fbc0045258154b5f71f89164bf7f98a6d6da"},"schema_version":"1.0","source":{"id":"2004.14368","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14368","created_at":"2026-07-05T01:37:54Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14368v2","created_at":"2026-07-05T01:37:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14368","created_at":"2026-07-05T01:37:54Z"},{"alias_kind":"pith_short_12","alias_value":"UFEXWP2YCRCU","created_at":"2026-07-05T01:37:54Z"},{"alias_kind":"pith_short_16","alias_value":"UFEXWP2YCRCUJQG2","created_at":"2026-07-05T01:37:54Z"},{"alias_kind":"pith_short_8","alias_value":"UFEXWP2Y","created_at":"2026-07-05T01:37:54Z"}],"graph_snapshots":[{"event_id":"sha256:994d9263673888bef86ed1b1f8854e93df40cb5ec0936f55d2add06c257fbcc6","target":"graph","created_at":"2026-07-05T01:37:54Z","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/2004.14368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andrea Vedaldi, Andrew Zisserman, Honglie Chen, Weidi Xie","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-29T17:46:54Z","title":"VGGSound: A Large-scale Audio-Visual Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14368","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":"sha256:452644515d13d0211439a07d59cd328bd2c78e5e94179a75592d9f595e9b2087","target":"record","created_at":"2026-07-05T01:37:54Z","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":"0a5799e5326bc9ddc00065d2a2872cbda8f76dfcc8a23992e795b971f8523afb","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-29T17:46:54Z","title_canon_sha256":"4d8e2259031cf50b3647fac9a945fbc0045258154b5f71f89164bf7f98a6d6da"},"schema_version":"1.0","source":{"id":"2004.14368","kind":"arxiv","version":2}},"canonical_sha256":"a1497b3f58144544c0da5fd99c698c184330c2f2bd8c049d681073d1fe9f42c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1497b3f58144544c0da5fd99c698c184330c2f2bd8c049d681073d1fe9f42c4","first_computed_at":"2026-07-05T01:37:54.158089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:37:54.158089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dRhxuTsbI4fdcngWE/5+szFR712GCgJACDnaT84VwiZHi6deJ+rNM0NaiLKIMSjP5Y3DQwIozMaLgLmXiHLdAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:37:54.158574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14368","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:452644515d13d0211439a07d59cd328bd2c78e5e94179a75592d9f595e9b2087","sha256:994d9263673888bef86ed1b1f8854e93df40cb5ec0936f55d2add06c257fbcc6"],"state_sha256":"1ceafb890aa925fff0add72b0ac9c1d6968846be4202ab0b1e38986ac7e49f86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IoIQKNf87ljvaD6r++zM1joLw90MvoTRtuSK3isHWzRnC27Vwc04X3h6i1MZiFNn+J2CwFf1TAH+joY7xPP8AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:23:50.575387Z","bundle_sha256":"0a941d808bf0847351b5dda9c6ea6370898d370dc786b8d11ee5159975e630fd"}}