{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:62JDGXTLY4SWJGEORX6BDU4UGP","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":"e2dde1695ac18295b358c4bcd41ac1d5041a6e669992adf73e548df0b960f1ec","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-21T22:00:13Z","title_canon_sha256":"db9bdb35efddfa5af1369a2eae02894317baaf12f9bdb71e95d13837c1724e11"},"schema_version":"1.0","source":{"id":"2110.11499","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.11499","created_at":"2026-07-05T03:56:51Z"},{"alias_kind":"arxiv_version","alias_value":"2110.11499v2","created_at":"2026-07-05T03:56:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.11499","created_at":"2026-07-05T03:56:51Z"},{"alias_kind":"pith_short_12","alias_value":"62JDGXTLY4SW","created_at":"2026-07-05T03:56:51Z"},{"alias_kind":"pith_short_16","alias_value":"62JDGXTLY4SWJGEO","created_at":"2026-07-05T03:56:51Z"},{"alias_kind":"pith_short_8","alias_value":"62JDGXTL","created_at":"2026-07-05T03:56:51Z"}],"graph_snapshots":[{"event_id":"sha256:ff6c8a739067364b7b2e02c1ed428e0d6ae23dacaad6f9693a33a53c62a149bf","target":"graph","created_at":"2026-07-05T03:56:51Z","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/2110.11499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Wav2CLIP, a robust audio representation learning method by distilling from Contrastive Language-Image Pre-training (CLIP). We systematically evaluate Wav2CLIP on a variety of audio tasks including classification, retrieval, and generation, and show that Wav2CLIP can outperform several publicly available pre-trained audio representation algorithms. Wav2CLIP projects audio into a shared embedding space with images and text, which enables multimodal applications such as zero-shot classification, and cross-modal retrieval. Furthermore, Wav2CLIP needs just ~10% of the data to achieve com","authors_text":"Ho-Hsiang Wu, Juan Pablo Bello, Kundan Kumar, Prem Seetharaman","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-21T22:00:13Z","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.11499","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:b346b563f218ebef89f056af97d859028b086263378a9372f6cb1a27e04c7542","target":"record","created_at":"2026-07-05T03:56:51Z","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":"e2dde1695ac18295b358c4bcd41ac1d5041a6e669992adf73e548df0b960f1ec","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-21T22:00:13Z","title_canon_sha256":"db9bdb35efddfa5af1369a2eae02894317baaf12f9bdb71e95d13837c1724e11"},"schema_version":"1.0","source":{"id":"2110.11499","kind":"arxiv","version":2}},"canonical_sha256":"f692335e6bc72564988e8dfc11d39433deda659b0672f89886921631bdf2842d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f692335e6bc72564988e8dfc11d39433deda659b0672f89886921631bdf2842d","first_computed_at":"2026-07-05T03:56:51.236964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:56:51.236964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5zbeh5Uoofb094neuCB3qzBB0qpDraN9FMdfi5QP4+Xx+wV7AIR43dwPHUO3HooLfH1QsBWB+ByJctfLTim2Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T03:56:51.237377Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.11499","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b346b563f218ebef89f056af97d859028b086263378a9372f6cb1a27e04c7542","sha256:ff6c8a739067364b7b2e02c1ed428e0d6ae23dacaad6f9693a33a53c62a149bf"],"state_sha256":"92231cbdc6c82f4b9559f5c41310a41bc5603eab1c68bce3eadff9a455ec2635"}