{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ILQFW4FZRQSCGEXHSDLVGNBAPA","short_pith_number":"pith:ILQFW4FZ","canonical_record":{"source":{"id":"2103.06508","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-03-11T07:13:05Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"27a83da293bde57be4f344c2e6d12112585e45bc10c7ea22c17c99abaae9554e","abstract_canon_sha256":"4dc44d5b2b0f13f5b6fb289a28229b167e93beb79c3282299cb774ddaa511c41"},"schema_version":"1.0"},"canonical_sha256":"42e05b70b98c242312e790d753342078069785e00b6b70430f5dc9f903324305","source":{"kind":"arxiv","id":"2103.06508","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.06508","created_at":"2026-07-05T02:26:03Z"},{"alias_kind":"arxiv_version","alias_value":"2103.06508v3","created_at":"2026-07-05T02:26:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06508","created_at":"2026-07-05T02:26:03Z"},{"alias_kind":"pith_short_12","alias_value":"ILQFW4FZRQSC","created_at":"2026-07-05T02:26:03Z"},{"alias_kind":"pith_short_16","alias_value":"ILQFW4FZRQSCGEXH","created_at":"2026-07-05T02:26:03Z"},{"alias_kind":"pith_short_8","alias_value":"ILQFW4FZ","created_at":"2026-07-05T02:26:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ILQFW4FZRQSCGEXHSDLVGNBAPA","target":"record","payload":{"canonical_record":{"source":{"id":"2103.06508","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-03-11T07:13:05Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"27a83da293bde57be4f344c2e6d12112585e45bc10c7ea22c17c99abaae9554e","abstract_canon_sha256":"4dc44d5b2b0f13f5b6fb289a28229b167e93beb79c3282299cb774ddaa511c41"},"schema_version":"1.0"},"canonical_sha256":"42e05b70b98c242312e790d753342078069785e00b6b70430f5dc9f903324305","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:03.487285Z","signature_b64":"L+ETSq3EasF9/GOFm4hslyExEHtEtLeMiullnHdgjO3n7gjIJlrHycbuGQj3btMWIAEVbZvkYUvWSXo4e0FHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42e05b70b98c242312e790d753342078069785e00b6b70430f5dc9f903324305","last_reissued_at":"2026-07-05T02:26:03.486892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:03.486892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.06508","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:26:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v7W17s53jjktUxqbYxdRpO239PbsLVVMHDitL1XRu99IMKdWqPGiVgywMzrAqz7iGm5Gp1tm988bg127buQIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:52:30.224770Z"},"content_sha256":"bff55bd116228ce40be6c9d77c99cdaf5d29d58d820baefa5d610d7e199939c9","schema_version":"1.0","event_id":"sha256:bff55bd116228ce40be6c9d77c99cdaf5d29d58d820baefa5d610d7e199939c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ILQFW4FZRQSCGEXHSDLVGNBAPA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Format Contrastive Learning of Audio Representations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aaron van den Oord, Luyu Wang","submitted_at":"2021-03-11T07:13:05Z","abstract_excerpt":"Recent advances suggest the advantage of multi-modal training in comparison with single-modal methods. In contrast to this view, in our work we find that similar gain can be obtained from training with different formats of a single modality. In particular, we investigate the use of the contrastive learning framework to learn audio representations by maximizing the agreement between the raw audio and its spectral representation. We find a significant gain using this multi-format strategy against the single-format counterparts. Moreover, on the downstream AudioSet and ESC-50 classification task,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06508","kind":"arxiv","version":3},"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/2103.06508/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":"2026-07-05T02:26:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KbZWCU8MUJxZ/cDCMHHf6NkOwEvxTINJqVqmBQCcpYic6A7VKsZWlP2/W13+zc8n4cITdUTna3xDrX0LuUhsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:52:30.225331Z"},"content_sha256":"537f4a04c646a0a147640271f684e3842a1d6b405e9ac0c31da3b73fde4e7202","schema_version":"1.0","event_id":"sha256:537f4a04c646a0a147640271f684e3842a1d6b405e9ac0c31da3b73fde4e7202"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ILQFW4FZRQSCGEXHSDLVGNBAPA/bundle.json","state_url":"https://pith.science/pith/ILQFW4FZRQSCGEXHSDLVGNBAPA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ILQFW4FZRQSCGEXHSDLVGNBAPA/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":"2026-08-07T12:52:30Z","links":{"resolver":"https://pith.science/pith/ILQFW4FZRQSCGEXHSDLVGNBAPA","bundle":"https://pith.science/pith/ILQFW4FZRQSCGEXHSDLVGNBAPA/bundle.json","state":"https://pith.science/pith/ILQFW4FZRQSCGEXHSDLVGNBAPA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ILQFW4FZRQSCGEXHSDLVGNBAPA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ILQFW4FZRQSCGEXHSDLVGNBAPA","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":"4dc44d5b2b0f13f5b6fb289a28229b167e93beb79c3282299cb774ddaa511c41","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-03-11T07:13:05Z","title_canon_sha256":"27a83da293bde57be4f344c2e6d12112585e45bc10c7ea22c17c99abaae9554e"},"schema_version":"1.0","source":{"id":"2103.06508","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.06508","created_at":"2026-07-05T02:26:03Z"},{"alias_kind":"arxiv_version","alias_value":"2103.06508v3","created_at":"2026-07-05T02:26:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06508","created_at":"2026-07-05T02:26:03Z"},{"alias_kind":"pith_short_12","alias_value":"ILQFW4FZRQSC","created_at":"2026-07-05T02:26:03Z"},{"alias_kind":"pith_short_16","alias_value":"ILQFW4FZRQSCGEXH","created_at":"2026-07-05T02:26:03Z"},{"alias_kind":"pith_short_8","alias_value":"ILQFW4FZ","created_at":"2026-07-05T02:26:03Z"}],"graph_snapshots":[{"event_id":"sha256:537f4a04c646a0a147640271f684e3842a1d6b405e9ac0c31da3b73fde4e7202","target":"graph","created_at":"2026-07-05T02:26:03Z","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/2103.06508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances suggest the advantage of multi-modal training in comparison with single-modal methods. In contrast to this view, in our work we find that similar gain can be obtained from training with different formats of a single modality. In particular, we investigate the use of the contrastive learning framework to learn audio representations by maximizing the agreement between the raw audio and its spectral representation. We find a significant gain using this multi-format strategy against the single-format counterparts. Moreover, on the downstream AudioSet and ESC-50 classification task,","authors_text":"Aaron van den Oord, Luyu Wang","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-03-11T07:13:05Z","title":"Multi-Format Contrastive Learning of Audio Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06508","kind":"arxiv","version":3},"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:bff55bd116228ce40be6c9d77c99cdaf5d29d58d820baefa5d610d7e199939c9","target":"record","created_at":"2026-07-05T02:26:03Z","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":"4dc44d5b2b0f13f5b6fb289a28229b167e93beb79c3282299cb774ddaa511c41","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-03-11T07:13:05Z","title_canon_sha256":"27a83da293bde57be4f344c2e6d12112585e45bc10c7ea22c17c99abaae9554e"},"schema_version":"1.0","source":{"id":"2103.06508","kind":"arxiv","version":3}},"canonical_sha256":"42e05b70b98c242312e790d753342078069785e00b6b70430f5dc9f903324305","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42e05b70b98c242312e790d753342078069785e00b6b70430f5dc9f903324305","first_computed_at":"2026-07-05T02:26:03.486892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:03.486892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L+ETSq3EasF9/GOFm4hslyExEHtEtLeMiullnHdgjO3n7gjIJlrHycbuGQj3btMWIAEVbZvkYUvWSXo4e0FHDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:03.487285Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.06508","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bff55bd116228ce40be6c9d77c99cdaf5d29d58d820baefa5d610d7e199939c9","sha256:537f4a04c646a0a147640271f684e3842a1d6b405e9ac0c31da3b73fde4e7202"],"state_sha256":"8af37c9f5daed26bb860f76cb47981d3d93084beb32d8b9553f4b52410cf8168"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DTUnqmg9bfLC9dAQRkslacAK3fRXyhzxAPjlPmdA3FIcrHpGHP3yZJ10sFGFP6a70l+mPcDlt3nc8LdEHh3ODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:52:30.229892Z","bundle_sha256":"f60188ec3fccfd140270a186a0b855091060b243b2e97abbe78e83d7baaae7b8"}}