{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SHJZZE5QZ4LCA2VQP7KYPVOWTP","short_pith_number":"pith:SHJZZE5Q","schema_version":"1.0","canonical_sha256":"91d39c93b0cf16206ab07fd587d5d69bcc87112df2dd143e1c2422c5ed7d5b0f","source":{"kind":"arxiv","id":"2401.03497","version":1},"attestation_state":"computed","paper":{"title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Wenxi Chen, Xie Chen, Yuzhe Liang, Zhisheng Zheng, Ziyang Ma","submitted_at":"2024-01-07T14:31:27Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.03497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-07T14:31:27Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"0e6a0883150a847f6de14bca94989a5dce439a47d69861f8c6301a322f72b9f3","abstract_canon_sha256":"4236780d6c37e6fffcb8e31fa5ab812d1dc23d86cf89b460537b184567538c55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:09.764201Z","signature_b64":"piGihz1zy3JE4YHMPSW4dwOJRSnNNk0OOgMngM31zuj2Lj3eDZKRibMG3WK7Aw1xsjli0dQMe5REtCKxklX7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91d39c93b0cf16206ab07fd587d5d69bcc87112df2dd143e1c2422c5ed7d5b0f","last_reissued_at":"2026-07-05T07:31:09.763576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:09.763576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Wenxi Chen, Xie Chen, Yuzhe Liang, Zhisheng Zheng, Ziyang Ma","submitted_at":"2024-01-07T14:31:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03497","kind":"arxiv","version":1},"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/2401.03497/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.03497","created_at":"2026-07-05T07:31:09.763636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03497v1","created_at":"2026-07-05T07:31:09.763636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03497","created_at":"2026-07-05T07:31:09.763636+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHJZZE5QZ4LC","created_at":"2026-07-05T07:31:09.763636+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHJZZE5QZ4LCA2VQ","created_at":"2026-07-05T07:31:09.763636+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHJZZE5Q","created_at":"2026-07-05T07:31:09.763636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00387","citing_title":"From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18409","citing_title":"EnvTriCascade: An Environment-Aware Tri-Stage Cascaded Framework for ESDD2 2026 Challenge","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SHJZZE5QZ4LCA2VQP7KYPVOWTP","json":"https://pith.science/pith/SHJZZE5QZ4LCA2VQP7KYPVOWTP.json","graph_json":"https://pith.science/api/pith-number/SHJZZE5QZ4LCA2VQP7KYPVOWTP/graph.json","events_json":"https://pith.science/api/pith-number/SHJZZE5QZ4LCA2VQP7KYPVOWTP/events.json","paper":"https://pith.science/paper/SHJZZE5Q"},"agent_actions":{"view_html":"https://pith.science/pith/SHJZZE5QZ4LCA2VQP7KYPVOWTP","download_json":"https://pith.science/pith/SHJZZE5QZ4LCA2VQP7KYPVOWTP.json","view_paper":"https://pith.science/paper/SHJZZE5Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03497&json=true","fetch_graph":"https://pith.science/api/pith-number/SHJZZE5QZ4LCA2VQP7KYPVOWTP/graph.json","fetch_events":"https://pith.science/api/pith-number/SHJZZE5QZ4LCA2VQP7KYPVOWTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHJZZE5QZ4LCA2VQP7KYPVOWTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHJZZE5QZ4LCA2VQP7KYPVOWTP/action/storage_attestation","attest_author":"https://pith.science/pith/SHJZZE5QZ4LCA2VQP7KYPVOWTP/action/author_attestation","sign_citation":"https://pith.science/pith/SHJZZE5QZ4LCA2VQP7KYPVOWTP/action/citation_signature","submit_replication":"https://pith.science/pith/SHJZZE5QZ4LCA2VQP7KYPVOWTP/action/replication_record"}},"created_at":"2026-07-05T07:31:09.763636+00:00","updated_at":"2026-07-05T07:31:09.763636+00:00"}