{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NYGTGKWJUFP65BDQY6YHKTY5W2","short_pith_number":"pith:NYGTGKWJ","canonical_record":{"source":{"id":"2309.05767","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-11T18:50:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"ee7d57de3024bc1cecd0c9b76ac708393c6a75576eacd9f12408bc43c4eeef51","abstract_canon_sha256":"ca298ebc5ad1f3447a9e1f4f866dc63f669548ba233306e1132c3b0c2d44537f"},"schema_version":"1.0"},"canonical_sha256":"6e0d332ac9a15fee8470c7b0754f1db686a0ce56b5f6bcd137313832d54b1df4","source":{"kind":"arxiv","id":"2309.05767","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05767","created_at":"2026-07-05T07:42:19Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05767v2","created_at":"2026-07-05T07:42:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05767","created_at":"2026-07-05T07:42:19Z"},{"alias_kind":"pith_short_12","alias_value":"NYGTGKWJUFP6","created_at":"2026-07-05T07:42:19Z"},{"alias_kind":"pith_short_16","alias_value":"NYGTGKWJUFP65BDQ","created_at":"2026-07-05T07:42:19Z"},{"alias_kind":"pith_short_8","alias_value":"NYGTGKWJ","created_at":"2026-07-05T07:42:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NYGTGKWJUFP65BDQY6YHKTY5W2","target":"record","payload":{"canonical_record":{"source":{"id":"2309.05767","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-11T18:50:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"ee7d57de3024bc1cecd0c9b76ac708393c6a75576eacd9f12408bc43c4eeef51","abstract_canon_sha256":"ca298ebc5ad1f3447a9e1f4f866dc63f669548ba233306e1132c3b0c2d44537f"},"schema_version":"1.0"},"canonical_sha256":"6e0d332ac9a15fee8470c7b0754f1db686a0ce56b5f6bcd137313832d54b1df4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:19.878337Z","signature_b64":"Fes+hPAlBzEkCekyMKPMz1KTy7fpOARLNIlKgrvXBpcFvzSp6vqSd4Ry4VNwFiMDu182Em3qoGLjkJm+8oAeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e0d332ac9a15fee8470c7b0754f1db686a0ce56b5f6bcd137313832d54b1df4","last_reissued_at":"2026-07-05T07:42:19.877846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:19.877846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.05767","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":"2026-07-05T07:42:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y/QL6bfTteGf0QXc2FjcZndm9/YaEBVjBEaLid1s8w0HhU9VdisYxheirItREDQ/wn0NOXdh244r1NRodqlZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:57:55.430512Z"},"content_sha256":"a85285b427c61d996606e2acc99a4b9901750a0b7da3f12040c84a69ee80aebb","schema_version":"1.0","event_id":"sha256:a85285b427c61d996606e2acc99a4b9901750a0b7da3f12040c84a69ee80aebb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NYGTGKWJUFP65BDQY6YHKTY5W2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural Language Supervision for General-Purpose Audio Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Benjamin Elizalde, Huaming Wang, Soham Deshmukh","submitted_at":"2023-09-11T18:50:21Z","abstract_excerpt":"Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds, music, and speech. Although models have achieved remarkable performance, there is still a performance gap with task-specific models. In this paper, we propose a Contrastive Language-Audio Pretraining model that is pretrained with a diverse collection of 4.6M audio-text pairs employing two innovative encoders for Zero-Shot inference. To learn audio represent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05767","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/2309.05767/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":"2026-07-05T07:42:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3397EDzuo8Ys8d1qvznc0TfczHFppbfVdaI1zYR5w4b2yFB8XgfUE6FfG6iEXwU5e2LPsOiMt0VreFZE7onHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:57:55.431149Z"},"content_sha256":"457c032517d0bc32cf5933e86f5ae9daf17955d2a39959775aa176a723458228","schema_version":"1.0","event_id":"sha256:457c032517d0bc32cf5933e86f5ae9daf17955d2a39959775aa176a723458228"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NYGTGKWJUFP65BDQY6YHKTY5W2/bundle.json","state_url":"https://pith.science/pith/NYGTGKWJUFP65BDQY6YHKTY5W2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NYGTGKWJUFP65BDQY6YHKTY5W2/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":"2026-08-10T09:57:55Z","links":{"resolver":"https://pith.science/pith/NYGTGKWJUFP65BDQY6YHKTY5W2","bundle":"https://pith.science/pith/NYGTGKWJUFP65BDQY6YHKTY5W2/bundle.json","state":"https://pith.science/pith/NYGTGKWJUFP65BDQY6YHKTY5W2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NYGTGKWJUFP65BDQY6YHKTY5W2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NYGTGKWJUFP65BDQY6YHKTY5W2","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":"ca298ebc5ad1f3447a9e1f4f866dc63f669548ba233306e1132c3b0c2d44537f","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-11T18:50:21Z","title_canon_sha256":"ee7d57de3024bc1cecd0c9b76ac708393c6a75576eacd9f12408bc43c4eeef51"},"schema_version":"1.0","source":{"id":"2309.05767","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05767","created_at":"2026-07-05T07:42:19Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05767v2","created_at":"2026-07-05T07:42:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05767","created_at":"2026-07-05T07:42:19Z"},{"alias_kind":"pith_short_12","alias_value":"NYGTGKWJUFP6","created_at":"2026-07-05T07:42:19Z"},{"alias_kind":"pith_short_16","alias_value":"NYGTGKWJUFP65BDQ","created_at":"2026-07-05T07:42:19Z"},{"alias_kind":"pith_short_8","alias_value":"NYGTGKWJ","created_at":"2026-07-05T07:42:19Z"}],"graph_snapshots":[{"event_id":"sha256:457c032517d0bc32cf5933e86f5ae9daf17955d2a39959775aa176a723458228","target":"graph","created_at":"2026-07-05T07:42:19Z","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/2309.05767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds, music, and speech. Although models have achieved remarkable performance, there is still a performance gap with task-specific models. In this paper, we propose a Contrastive Language-Audio Pretraining model that is pretrained with a diverse collection of 4.6M audio-text pairs employing two innovative encoders for Zero-Shot inference. To learn audio represent","authors_text":"Benjamin Elizalde, Huaming Wang, Soham Deshmukh","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-11T18:50:21Z","title":"Natural Language Supervision for General-Purpose Audio Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05767","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:a85285b427c61d996606e2acc99a4b9901750a0b7da3f12040c84a69ee80aebb","target":"record","created_at":"2026-07-05T07:42:19Z","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":"ca298ebc5ad1f3447a9e1f4f866dc63f669548ba233306e1132c3b0c2d44537f","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-11T18:50:21Z","title_canon_sha256":"ee7d57de3024bc1cecd0c9b76ac708393c6a75576eacd9f12408bc43c4eeef51"},"schema_version":"1.0","source":{"id":"2309.05767","kind":"arxiv","version":2}},"canonical_sha256":"6e0d332ac9a15fee8470c7b0754f1db686a0ce56b5f6bcd137313832d54b1df4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e0d332ac9a15fee8470c7b0754f1db686a0ce56b5f6bcd137313832d54b1df4","first_computed_at":"2026-07-05T07:42:19.877846Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:19.877846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fes+hPAlBzEkCekyMKPMz1KTy7fpOARLNIlKgrvXBpcFvzSp6vqSd4Ry4VNwFiMDu182Em3qoGLjkJm+8oAeAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:19.878337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.05767","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a85285b427c61d996606e2acc99a4b9901750a0b7da3f12040c84a69ee80aebb","sha256:457c032517d0bc32cf5933e86f5ae9daf17955d2a39959775aa176a723458228"],"state_sha256":"60d84cd9c9287dadbca7db363e059487d07defc1a65519353e309274750fc2a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"itl2g2x3wGQ9mBqTRIuSaTuRXDHxp4Pqd2el6kGY3NlE3XdB+cioQMkPB9ST3MVoy1WSibRsSx/hlvfVlOylAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:57:55.435416Z","bundle_sha256":"664390e385389e805b2ad2c79fe1357251ae76d90517bc03a303a68b7febba85"}}