{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QTO67RIBQBE2EB3SN2F2ZOUF6A","short_pith_number":"pith:QTO67RIB","schema_version":"1.0","canonical_sha256":"84ddefc5018049a207726e8bacba85f03a0cc52fc7ddad2f960370ad1661bffc","source":{"kind":"arxiv","id":"2202.00874","version":1},"attestation_state":"computed","paper":{"title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bilei Zhu, Ke Chen, Shlomo Dubnov, Taylor Berg-Kirkpatrick, Xingjian Du, Zejun Ma","submitted_at":"2022-02-02T04:49:14Z","abstract_excerpt":"Audio classification is an important task of mapping audio samples into their corresponding labels. Recently, the transformer model with self-attention mechanisms has been adopted in this field. However, existing audio transformers require large GPU memories and long training time, meanwhile relying on pretrained vision models to achieve high performance, which limits the model's scalability in audio tasks. To combat these problems, we introduce HTS-AT: an audio transformer with a hierarchical structure to reduce the model size and training time. It is further combined with a token-semantic mo"},"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":"2202.00874","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-02-02T04:49:14Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG","eess.AS"],"title_canon_sha256":"295b725eb094a2afd79c2639d61c025ff9dc9ae9dcf5bb9d94df69bec49af756","abstract_canon_sha256":"6ed0563d0380281ec3330eade0ffb871bc23e72a10efefefc120543a2bb1defe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:53:28.520409Z","signature_b64":"iMNNoPRsGaG9gL2EYlVBYW6LkG3nM+4xnmG86Xwl06WtfjU/yTluVFyJka+8/SHTSbF6LjN+RFA3FTrwbp/eDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84ddefc5018049a207726e8bacba85f03a0cc52fc7ddad2f960370ad1661bffc","last_reissued_at":"2026-07-05T03:53:28.519828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:53:28.519828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bilei Zhu, Ke Chen, Shlomo Dubnov, Taylor Berg-Kirkpatrick, Xingjian Du, Zejun Ma","submitted_at":"2022-02-02T04:49:14Z","abstract_excerpt":"Audio classification is an important task of mapping audio samples into their corresponding labels. Recently, the transformer model with self-attention mechanisms has been adopted in this field. However, existing audio transformers require large GPU memories and long training time, meanwhile relying on pretrained vision models to achieve high performance, which limits the model's scalability in audio tasks. To combat these problems, we introduce HTS-AT: an audio transformer with a hierarchical structure to reduce the model size and training time. It is further combined with a token-semantic mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00874","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/2202.00874/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":"2202.00874","created_at":"2026-07-05T03:53:28.519895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.00874v1","created_at":"2026-07-05T03:53:28.519895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00874","created_at":"2026-07-05T03:53:28.519895+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTO67RIBQBE2","created_at":"2026-07-05T03:53:28.519895+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTO67RIBQBE2EB3S","created_at":"2026-07-05T03:53:28.519895+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTO67RIB","created_at":"2026-07-05T03:53:28.519895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06929","citing_title":"MADB: A Large-Scale Music Aesthetics Dataset with Professional and Multi-Dimensional Annotations","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19632","citing_title":"Executable Boundary Contracts for Sound Event Traces","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01929","citing_title":"Woosh: A Sound Effects Foundation Model","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTO67RIBQBE2EB3SN2F2ZOUF6A","json":"https://pith.science/pith/QTO67RIBQBE2EB3SN2F2ZOUF6A.json","graph_json":"https://pith.science/api/pith-number/QTO67RIBQBE2EB3SN2F2ZOUF6A/graph.json","events_json":"https://pith.science/api/pith-number/QTO67RIBQBE2EB3SN2F2ZOUF6A/events.json","paper":"https://pith.science/paper/QTO67RIB"},"agent_actions":{"view_html":"https://pith.science/pith/QTO67RIBQBE2EB3SN2F2ZOUF6A","download_json":"https://pith.science/pith/QTO67RIBQBE2EB3SN2F2ZOUF6A.json","view_paper":"https://pith.science/paper/QTO67RIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.00874&json=true","fetch_graph":"https://pith.science/api/pith-number/QTO67RIBQBE2EB3SN2F2ZOUF6A/graph.json","fetch_events":"https://pith.science/api/pith-number/QTO67RIBQBE2EB3SN2F2ZOUF6A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTO67RIBQBE2EB3SN2F2ZOUF6A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTO67RIBQBE2EB3SN2F2ZOUF6A/action/storage_attestation","attest_author":"https://pith.science/pith/QTO67RIBQBE2EB3SN2F2ZOUF6A/action/author_attestation","sign_citation":"https://pith.science/pith/QTO67RIBQBE2EB3SN2F2ZOUF6A/action/citation_signature","submit_replication":"https://pith.science/pith/QTO67RIBQBE2EB3SN2F2ZOUF6A/action/replication_record"}},"created_at":"2026-07-05T03:53:28.519895+00:00","updated_at":"2026-07-05T03:53:28.519895+00:00"}