{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6KGKVHRQDGBACZODKCXEEZ2QNM","short_pith_number":"pith:6KGKVHRQ","schema_version":"1.0","canonical_sha256":"f28caa9e3019820165c350ae4267506b10af99836cd9a991e7753efdd895bca5","source":{"kind":"arxiv","id":"2303.10757","version":1},"attestation_state":"computed","paper":{"title":"Multiscale Audio Spectrogram Transformer for Efficient Audio Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Mohamed Omar, Wentao Zhu","submitted_at":"2023-03-19T20:21:29Z","abstract_excerpt":"Audio event has a hierarchical architecture in both time and frequency and can be grouped together to construct more abstract semantic audio classes. In this work, we develop a multiscale audio spectrogram Transformer (MAST) that employs hierarchical representation learning for efficient audio classification. Specifically, MAST employs one-dimensional (and two-dimensional) pooling operators along the time (and frequency domains) in different stages, and progressively reduces the number of tokens and increases the feature dimensions. MAST significantly outperforms AST~\\cite{gong2021ast} by 22.2"},"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":"2303.10757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-03-19T20:21:29Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"2834a70cd8140adc0a6d96be4a5357906b2def5df15993e7573d842edda301e9","abstract_canon_sha256":"52b72638a91789489c7104266ae5b559fbaa0dfb1dc6eb2922b5a2e4e68b6fa1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:36.354150Z","signature_b64":"W7iyUYqT8KuLtdnc80Q1necbtzcvsg+CWj7RAqc9qFeLqdvBwj4xHMXUS6j8eLKj9qRt6KfA8AfeE+47ncbiDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f28caa9e3019820165c350ae4267506b10af99836cd9a991e7753efdd895bca5","last_reissued_at":"2026-07-05T05:52:36.353795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:36.353795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiscale Audio Spectrogram Transformer for Efficient Audio Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Mohamed Omar, Wentao Zhu","submitted_at":"2023-03-19T20:21:29Z","abstract_excerpt":"Audio event has a hierarchical architecture in both time and frequency and can be grouped together to construct more abstract semantic audio classes. In this work, we develop a multiscale audio spectrogram Transformer (MAST) that employs hierarchical representation learning for efficient audio classification. Specifically, MAST employs one-dimensional (and two-dimensional) pooling operators along the time (and frequency domains) in different stages, and progressively reduces the number of tokens and increases the feature dimensions. MAST significantly outperforms AST~\\cite{gong2021ast} by 22.2"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10757","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/2303.10757/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":"2303.10757","created_at":"2026-07-05T05:52:36.353858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.10757v1","created_at":"2026-07-05T05:52:36.353858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10757","created_at":"2026-07-05T05:52:36.353858+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KGKVHRQDGBA","created_at":"2026-07-05T05:52:36.353858+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KGKVHRQDGBACZOD","created_at":"2026-07-05T05:52:36.353858+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KGKVHRQ","created_at":"2026-07-05T05:52:36.353858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19409","citing_title":"Modality Agnostic Efficient Long Range Encoder","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6KGKVHRQDGBACZODKCXEEZ2QNM","json":"https://pith.science/pith/6KGKVHRQDGBACZODKCXEEZ2QNM.json","graph_json":"https://pith.science/api/pith-number/6KGKVHRQDGBACZODKCXEEZ2QNM/graph.json","events_json":"https://pith.science/api/pith-number/6KGKVHRQDGBACZODKCXEEZ2QNM/events.json","paper":"https://pith.science/paper/6KGKVHRQ"},"agent_actions":{"view_html":"https://pith.science/pith/6KGKVHRQDGBACZODKCXEEZ2QNM","download_json":"https://pith.science/pith/6KGKVHRQDGBACZODKCXEEZ2QNM.json","view_paper":"https://pith.science/paper/6KGKVHRQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.10757&json=true","fetch_graph":"https://pith.science/api/pith-number/6KGKVHRQDGBACZODKCXEEZ2QNM/graph.json","fetch_events":"https://pith.science/api/pith-number/6KGKVHRQDGBACZODKCXEEZ2QNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KGKVHRQDGBACZODKCXEEZ2QNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KGKVHRQDGBACZODKCXEEZ2QNM/action/storage_attestation","attest_author":"https://pith.science/pith/6KGKVHRQDGBACZODKCXEEZ2QNM/action/author_attestation","sign_citation":"https://pith.science/pith/6KGKVHRQDGBACZODKCXEEZ2QNM/action/citation_signature","submit_replication":"https://pith.science/pith/6KGKVHRQDGBACZODKCXEEZ2QNM/action/replication_record"}},"created_at":"2026-07-05T05:52:36.353858+00:00","updated_at":"2026-07-05T05:52:36.353858+00:00"}