{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4VB2TWEKQZ6ANIT4O2O2FABEGK","short_pith_number":"pith:4VB2TWEK","schema_version":"1.0","canonical_sha256":"e543a9d88a867c06a27c769da2802432896f6d4b17090c368c2874490c49ef92","source":{"kind":"arxiv","id":"2406.06992","version":2},"attestation_state":"computed","paper":{"title":"Scaling up masked audio encoder learning for general audio classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Wang, Heinrich Dinkel, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","submitted_at":"2024-06-11T06:44:54Z","abstract_excerpt":"Despite progress in audio classification, a generalization gap remains between speech and other sound domains, such as environmental sounds and music. Models trained for speech tasks often fail to perform well on environmental or musical audio tasks, and vice versa. While self-supervised (SSL) audio representations offer an alternative, there has been limited exploration of scaling both model and dataset sizes for SSL-based general audio classification. We introduce Dasheng, a simple SSL audio encoder, based on the efficient masked autoencoder framework. Trained with 1.2 billion parameters on "},"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":"2406.06992","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-11T06:44:54Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d965ac78309aa3ec21eec9d81706d663e656969e43a7a34cf0783db9ad35dc32","abstract_canon_sha256":"3f89fa9ccc22fd32d969934dc4af901794bd6d6c28177192077d74dae2848532"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:16.690794Z","signature_b64":"PIGfbwTQD28gFohKs0TKPLaS9qovbWbf1lRIC4GlR+NM4thePk5zN0uvJjSc9gbnFhOEYZB5yp6tJpktW6BbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e543a9d88a867c06a27c769da2802432896f6d4b17090c368c2874490c49ef92","last_reissued_at":"2026-07-05T08:31:16.690228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:16.690228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling up masked audio encoder learning for general audio classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Wang, Heinrich Dinkel, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","submitted_at":"2024-06-11T06:44:54Z","abstract_excerpt":"Despite progress in audio classification, a generalization gap remains between speech and other sound domains, such as environmental sounds and music. Models trained for speech tasks often fail to perform well on environmental or musical audio tasks, and vice versa. While self-supervised (SSL) audio representations offer an alternative, there has been limited exploration of scaling both model and dataset sizes for SSL-based general audio classification. We introduce Dasheng, a simple SSL audio encoder, based on the efficient masked autoencoder framework. Trained with 1.2 billion parameters on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06992","kind":"arxiv","version":2},"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/2406.06992/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":"2406.06992","created_at":"2026-07-05T08:31:16.690295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06992v2","created_at":"2026-07-05T08:31:16.690295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06992","created_at":"2026-07-05T08:31:16.690295+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VB2TWEKQZ6A","created_at":"2026-07-05T08:31:16.690295+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VB2TWEKQZ6ANIT4","created_at":"2026-07-05T08:31:16.690295+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VB2TWEK","created_at":"2026-07-05T08:31:16.690295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21365","citing_title":"LambdaMark: Semantic Audio Watermarking for Robustness and Radioactivity","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00387","citing_title":"From Objectives to Applications: Aligning Architectural Biases in Audio Self-Supervised Learning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30682","citing_title":"ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK","json":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK.json","graph_json":"https://pith.science/api/pith-number/4VB2TWEKQZ6ANIT4O2O2FABEGK/graph.json","events_json":"https://pith.science/api/pith-number/4VB2TWEKQZ6ANIT4O2O2FABEGK/events.json","paper":"https://pith.science/paper/4VB2TWEK"},"agent_actions":{"view_html":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK","download_json":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK.json","view_paper":"https://pith.science/paper/4VB2TWEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06992&json=true","fetch_graph":"https://pith.science/api/pith-number/4VB2TWEKQZ6ANIT4O2O2FABEGK/graph.json","fetch_events":"https://pith.science/api/pith-number/4VB2TWEKQZ6ANIT4O2O2FABEGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK/action/storage_attestation","attest_author":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK/action/author_attestation","sign_citation":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK/action/citation_signature","submit_replication":"https://pith.science/pith/4VB2TWEKQZ6ANIT4O2O2FABEGK/action/replication_record"}},"created_at":"2026-07-05T08:31:16.690295+00:00","updated_at":"2026-07-05T08:31:16.690295+00:00"}