{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MZSMZYZTIE5O2BUG5KVRPHZMXF","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":"1c10d0d91047e498f65901e845219631c9a80cf504ed8bfb71a9e181fe0f9232","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-03-11T14:32:33Z","title_canon_sha256":"8c7e5e176ce539e0649360407fb7660f324097197e3de372c16376c6ef61afe3"},"schema_version":"1.0","source":{"id":"2103.06695","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.06695","created_at":"2026-07-05T02:33:57Z"},{"alias_kind":"arxiv_version","alias_value":"2103.06695v2","created_at":"2026-07-05T02:33:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06695","created_at":"2026-07-05T02:33:57Z"},{"alias_kind":"pith_short_12","alias_value":"MZSMZYZTIE5O","created_at":"2026-07-05T02:33:57Z"},{"alias_kind":"pith_short_16","alias_value":"MZSMZYZTIE5O2BUG","created_at":"2026-07-05T02:33:57Z"},{"alias_kind":"pith_short_8","alias_value":"MZSMZYZT","created_at":"2026-07-05T02:33:57Z"}],"graph_snapshots":[{"event_id":"sha256:0768a3123676fc021cc216a15ea957abf90ed515ed43c3c2bc0a205551ffa3d8","target":"graph","created_at":"2026-07-05T02:33:57Z","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/2103.06695/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inspired by the recent progress in self-supervised learning for computer vision that generates supervision using data augmentations, we explore a new general-purpose audio representation learning approach. We propose learning general-purpose audio representation from a single audio segment without expecting relationships between different time segments of audio samples. To implement this principle, we introduce Bootstrap Your Own Latent (BYOL) for Audio (BYOL-A, pronounced \"viola\"), an audio self-supervised learning method based on BYOL for learning general-purpose audio representation. Unlike","authors_text":"Daiki Takeuchi, Daisuke Niizumi, Kunio Kashino, Noboru Harada, Yasunori Ohishi","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-03-11T14:32:33Z","title":"BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06695","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":"sha256:36bc5d8b73fa4da7658ce533c692186ffce15624a7bb3e81e537f6c3e15a3cc0","target":"record","created_at":"2026-07-05T02:33:57Z","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":"1c10d0d91047e498f65901e845219631c9a80cf504ed8bfb71a9e181fe0f9232","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-03-11T14:32:33Z","title_canon_sha256":"8c7e5e176ce539e0649360407fb7660f324097197e3de372c16376c6ef61afe3"},"schema_version":"1.0","source":{"id":"2103.06695","kind":"arxiv","version":2}},"canonical_sha256":"6664cce333413aed0686eaab179f2cb96819ebcf87fe3bee23e7defce3425c87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6664cce333413aed0686eaab179f2cb96819ebcf87fe3bee23e7defce3425c87","first_computed_at":"2026-07-05T02:33:57.878639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:57.878639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bV7x1eZxacjJcTQd8Cx0KoKxkAKDrBhF2hnm4Mcc+fMjqAjJL2kBVBz0C70IKIUgKNEcJSHlqp4sXsCsoc7kBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:57.879134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.06695","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36bc5d8b73fa4da7658ce533c692186ffce15624a7bb3e81e537f6c3e15a3cc0","sha256:0768a3123676fc021cc216a15ea957abf90ed515ed43c3c2bc0a205551ffa3d8"],"state_sha256":"9d71c7975fbf296291ba269371fe5698f7dc56b75dd1cbc05e3a835d86c3444d"}