{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:F6PK2UMNFMPZ4GD3AE53WMWS7A","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":"1784e00b219fb130242a044d061b57fd9c7af40369bd66f24ecba22e97702964","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-14T02:21:53Z","title_canon_sha256":"70fd30f28e4fa8c50f400a5c2bd917739ff4707f5baba83230d525f1530210d5"},"schema_version":"1.0","source":{"id":"2309.07391","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07391","created_at":"2026-07-05T08:21:06Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07391v2","created_at":"2026-07-05T08:21:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07391","created_at":"2026-07-05T08:21:06Z"},{"alias_kind":"pith_short_12","alias_value":"F6PK2UMNFMPZ","created_at":"2026-07-05T08:21:06Z"},{"alias_kind":"pith_short_16","alias_value":"F6PK2UMNFMPZ4GD3","created_at":"2026-07-05T08:21:06Z"},{"alias_kind":"pith_short_8","alias_value":"F6PK2UMN","created_at":"2026-07-05T08:21:06Z"}],"graph_snapshots":[{"event_id":"sha256:9bd358dddd0542bdfa67d0f6105fb34754bfa0bd39a611cb18c0c2ee7f341343","target":"graph","created_at":"2026-07-05T08:21:06Z","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/2309.07391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of universal audio representation learning is to obtain foundational models that can be used for a variety of downstream tasks involving speech, music and environmental sounds. To approach this problem, methods inspired by works on self-supervised learning for NLP, like BERT, or computer vision, like masked autoencoders (MAE), are often adapted to the audio domain. In this work, we propose masking representations of the audio signal, and training a MAE to reconstruct the masked segments. The reconstruction is done by predicting the discrete units generated by EnCodec, a neural audio c","authors_text":"Leonardo Pepino, Luciana Ferrer, Pablo Riera","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-14T02:21:53Z","title":"EnCodecMAE: Leveraging neural codecs for universal audio representation learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07391","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:d7e8b459ea8d15fdb8cf1a29ef23f19b027e5046ab163d99054acf8d902a8a76","target":"record","created_at":"2026-07-05T08:21:06Z","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":"1784e00b219fb130242a044d061b57fd9c7af40369bd66f24ecba22e97702964","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-14T02:21:53Z","title_canon_sha256":"70fd30f28e4fa8c50f400a5c2bd917739ff4707f5baba83230d525f1530210d5"},"schema_version":"1.0","source":{"id":"2309.07391","kind":"arxiv","version":2}},"canonical_sha256":"2f9ead518d2b1f9e187b013bbb32d2f8074a00d5c17a1cd72861e25f3b7e465d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f9ead518d2b1f9e187b013bbb32d2f8074a00d5c17a1cd72861e25f3b7e465d","first_computed_at":"2026-07-05T08:21:06.628867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:21:06.628867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dMcxWf1d/wtw3OYnvJOmcDaP7STO8F52MrOeX6StsbwkrP5lOcrEVGQmnpKUcjaSsIu8WDUJNtl3p/TcgsshDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:21:06.629490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.07391","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7e8b459ea8d15fdb8cf1a29ef23f19b027e5046ab163d99054acf8d902a8a76","sha256:9bd358dddd0542bdfa67d0f6105fb34754bfa0bd39a611cb18c0c2ee7f341343"],"state_sha256":"89a7b1af28922d4c493c2a00354aa70966b0ebf8e59dce0aa1ee3912b6600846"}