{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SHJZZE5QZ4LCA2VQP7KYPVOWTP","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":"4236780d6c37e6fffcb8e31fa5ab812d1dc23d86cf89b460537b184567538c55","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-07T14:31:27Z","title_canon_sha256":"0e6a0883150a847f6de14bca94989a5dce439a47d69861f8c6301a322f72b9f3"},"schema_version":"1.0","source":{"id":"2401.03497","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.03497","created_at":"2026-07-05T07:31:09Z"},{"alias_kind":"arxiv_version","alias_value":"2401.03497v1","created_at":"2026-07-05T07:31:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03497","created_at":"2026-07-05T07:31:09Z"},{"alias_kind":"pith_short_12","alias_value":"SHJZZE5QZ4LC","created_at":"2026-07-05T07:31:09Z"},{"alias_kind":"pith_short_16","alias_value":"SHJZZE5QZ4LCA2VQ","created_at":"2026-07-05T07:31:09Z"},{"alias_kind":"pith_short_8","alias_value":"SHJZZE5Q","created_at":"2026-07-05T07:31:09Z"}],"graph_snapshots":[{"event_id":"sha256:f979d0c2eb190070b9179d17116944f975b3b49c21f2bccd01436808abd47546","target":"graph","created_at":"2026-07-05T07:31:09Z","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/2401.03497/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio self-supervised learning (SSL) pre-training, which aims to learn good representations from unlabeled audio, has made remarkable progress. However, the extensive computational demands during pre-training pose a significant barrier to the potential application and optimization of audio SSL models. In this paper, inspired by the success of data2vec 2.0 in image modality and Audio-MAE in audio modality, we introduce Efficient Audio Transformer (EAT) to further improve the effectiveness and efficiency in audio SSL. The proposed EAT adopts the bootstrap self-supervised training paradigm to the","authors_text":"Wenxi Chen, Xie Chen, Yuzhe Liang, Zhisheng Zheng, Ziyang Ma","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-07T14:31:27Z","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03497","kind":"arxiv","version":1},"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":"sha256:759570513ed501cd67aa9e320811361ce3be80d0b9b816702e797d3acd594c22","target":"record","created_at":"2026-07-05T07:31:09Z","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":"4236780d6c37e6fffcb8e31fa5ab812d1dc23d86cf89b460537b184567538c55","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-07T14:31:27Z","title_canon_sha256":"0e6a0883150a847f6de14bca94989a5dce439a47d69861f8c6301a322f72b9f3"},"schema_version":"1.0","source":{"id":"2401.03497","kind":"arxiv","version":1}},"canonical_sha256":"91d39c93b0cf16206ab07fd587d5d69bcc87112df2dd143e1c2422c5ed7d5b0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91d39c93b0cf16206ab07fd587d5d69bcc87112df2dd143e1c2422c5ed7d5b0f","first_computed_at":"2026-07-05T07:31:09.763576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:31:09.763576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"piGihz1zy3JE4YHMPSW4dwOJRSnNNk0OOgMngM31zuj2Lj3eDZKRibMG3WK7Aw1xsjli0dQMe5REtCKxklX7DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:31:09.764201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.03497","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:759570513ed501cd67aa9e320811361ce3be80d0b9b816702e797d3acd594c22","sha256:f979d0c2eb190070b9179d17116944f975b3b49c21f2bccd01436808abd47546"],"state_sha256":"9eae4ee5c727f2a72f479499d9376147793722a3975f39fb07c3e639db79dbcb"}