{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GP5Z5F3MITUS6GAIDKOOYZC4EU","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":"eadfba5766fdc11d9877f4afb5de63887411eaa7c203d06ee909f78900bc69fe","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-04-26T18:07:17Z","title_canon_sha256":"9d86c9d58abcc1500a4a4119827b9e004fc82abc17ff5bd60cc76c6a882f7815"},"schema_version":"1.0","source":{"id":"2104.12807","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.12807","created_at":"2026-07-05T02:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"2104.12807v2","created_at":"2026-07-05T02:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.12807","created_at":"2026-07-05T02:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"GP5Z5F3MITUS","created_at":"2026-07-05T02:36:04Z"},{"alias_kind":"pith_short_16","alias_value":"GP5Z5F3MITUS6GAI","created_at":"2026-07-05T02:36:04Z"},{"alias_kind":"pith_short_8","alias_value":"GP5Z5F3M","created_at":"2026-07-05T02:36:04Z"}],"graph_snapshots":[{"event_id":"sha256:3d051022eaeb689434d00b2b844bcf3b45b05428d4ef120bf702310ce9893b92","target":"graph","created_at":"2026-07-05T02:36:04Z","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/2104.12807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a multimodal framework to learn general audio representations from videos. Existing contrastive audio representation learning methods mainly focus on using the audio modality alone during training. In this work, we show that additional information contained in video can be utilized to greatly improve the learned features. First, we demonstrate that our contrastive framework does not require high resolution images to learn good audio features. This allows us to scale up the training batch size, while keeping the computational load incurred by the additional video modality to a reason","authors_text":"Aaron van den Oord, Adria Recasens, Jean-Baptiste Alayrac, Luyu Wang, Pauline Luc","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-04-26T18:07:17Z","title":"Multimodal Self-Supervised Learning of General Audio Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.12807","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:ac16144963009a8d33c98e3d0e5406593d47713fbe0cea6bf855fd12c115569c","target":"record","created_at":"2026-07-05T02:36:04Z","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":"eadfba5766fdc11d9877f4afb5de63887411eaa7c203d06ee909f78900bc69fe","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-04-26T18:07:17Z","title_canon_sha256":"9d86c9d58abcc1500a4a4119827b9e004fc82abc17ff5bd60cc76c6a882f7815"},"schema_version":"1.0","source":{"id":"2104.12807","kind":"arxiv","version":2}},"canonical_sha256":"33fb9e976c44e92f18081a9cec645c252fa66dbfa8e309332dded689588e09ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33fb9e976c44e92f18081a9cec645c252fa66dbfa8e309332dded689588e09ee","first_computed_at":"2026-07-05T02:36:04.194496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:36:04.194496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qw0Lq77qapjIvJ6bS21yHcA19eZL6RbO1NDwSJB5JbeG2Gjo+S5uJTairSUMgs7D3Bypmi+9PvlfFhZrxBPbAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:36:04.194902Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.12807","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac16144963009a8d33c98e3d0e5406593d47713fbe0cea6bf855fd12c115569c","sha256:3d051022eaeb689434d00b2b844bcf3b45b05428d4ef120bf702310ce9893b92"],"state_sha256":"335c70cfcb83c18e882dfa28927ed4cb1ced63c80dac8842bf8d5ed68e924ae0"}