{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:52CADFP74XF2OEZTK5YEQRA3TL","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":"7e845d16882cd8b4547466ba1a147fc722403292f11f558c4f2bfb7f55f0fd27","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-12T15:25:20Z","title_canon_sha256":"ecc0a44d67b0ed1685c379a9b141453c54dbbbd87fd1ba99c0134afbe1805536"},"schema_version":"1.0","source":{"id":"2211.06687","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06687","created_at":"2026-07-05T07:59:13Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06687v4","created_at":"2026-07-05T07:59:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06687","created_at":"2026-07-05T07:59:13Z"},{"alias_kind":"pith_short_12","alias_value":"52CADFP74XF2","created_at":"2026-07-05T07:59:13Z"},{"alias_kind":"pith_short_16","alias_value":"52CADFP74XF2OEZT","created_at":"2026-07-05T07:59:13Z"},{"alias_kind":"pith_short_8","alias_value":"52CADFP7","created_at":"2026-07-05T07:59:13Z"}],"graph_snapshots":[{"event_id":"sha256:f7fe9dababab5d5340923c2f7dd3124cae59bf622de07f576d0d7742c444d244","target":"graph","created_at":"2026-07-05T07:59:13Z","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/2211.06687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive learning has shown remarkable success in the field of multimodal representation learning. In this paper, we propose a pipeline of contrastive language-audio pretraining to develop an audio representation by combining audio data with natural language descriptions. To accomplish this target, we first release LAION-Audio-630K, a large collection of 633,526 audio-text pairs from different data sources. Second, we construct a contrastive language-audio pretraining model by considering different audio encoders and text encoders. We incorporate the feature fusion mechanism and keyword-to-","authors_text":"Ke Chen, Marianna Nezhurina, Shlomo Dubnov, Taylor Berg-Kirkpatrick, Tianyu Zhang, Yuchen Hui, Yusong Wu","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-12T15:25:20Z","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06687","kind":"arxiv","version":4},"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":"sha256:32d445362090804c0faab5b8f34da4305ca987be95dd06cf80307800817ff6ef","target":"record","created_at":"2026-07-05T07:59:13Z","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":"7e845d16882cd8b4547466ba1a147fc722403292f11f558c4f2bfb7f55f0fd27","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-12T15:25:20Z","title_canon_sha256":"ecc0a44d67b0ed1685c379a9b141453c54dbbbd87fd1ba99c0134afbe1805536"},"schema_version":"1.0","source":{"id":"2211.06687","kind":"arxiv","version":4}},"canonical_sha256":"ee840195ffe5cba71333577048441b9ac93165e8bd1723823be501ad42dc0519","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee840195ffe5cba71333577048441b9ac93165e8bd1723823be501ad42dc0519","first_computed_at":"2026-07-05T07:59:13.408349Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:13.408349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zR6WzeRI3Uw005mvfkCgZ7mNzVORM53tW6v21td9Qz6qcjvjjRwG2P95bjQoYM3ecYhAMayUZcLEUpOS+68fDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:13.408773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.06687","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32d445362090804c0faab5b8f34da4305ca987be95dd06cf80307800817ff6ef","sha256:f7fe9dababab5d5340923c2f7dd3124cae59bf622de07f576d0d7742c444d244"],"state_sha256":"bd2ce1a5c8ba69ff726f54886390deba0717951931b5f6004cb3cdb5c3bb4677"}