{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:STSLD23MXZO2LIWFPGUZ2QXH3V","short_pith_number":"pith:STSLD23M","schema_version":"1.0","canonical_sha256":"94e4b1eb6cbe5da5a2c579a99d42e7dd7c2070ee55c596de6392931684e4a605","source":{"kind":"arxiv","id":"2406.03344","version":1},"attestation_state":"computed","paper":{"title":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Arda Senocak, Jiu Feng, Joon Son Chung, Mehmet Hamza Erol","submitted_at":"2024-06-05T15:00:59Z","abstract_excerpt":"Transformers have rapidly become the preferred choice for audio classification, surpassing methods based on CNNs. However, Audio Spectrogram Transformers (ASTs) exhibit quadratic scaling due to self-attention. The removal of this quadratic self-attention cost presents an appealing direction. Recently, state space models (SSMs), such as Mamba, have demonstrated potential in language and vision tasks in this regard. In this study, we explore whether reliance on self-attention is necessary for audio classification tasks. By introducing Audio Mamba (AuM), the first self-attention-free, purely SSM-"},"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":"2406.03344","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-05T15:00:59Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"9e6c72502a3a56058fa6a43c6c2d021388ebaadff84a408921df1be0b10fe4b1","abstract_canon_sha256":"dd02f13c753bd14804ca7f512fb27bfad7f7f5faaaa3021699bafd7f0141d06b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:55.136782Z","signature_b64":"1bcvQBizrOCt+rqDcQTYBDEqBuo+ER+tuoi3bKiaS29ErxNa+mlAjiiCo5zmHOhZXusCi2ph+FP7XYO3qFHIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94e4b1eb6cbe5da5a2c579a99d42e7dd7c2070ee55c596de6392931684e4a605","last_reissued_at":"2026-07-05T08:27:55.136334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:55.136334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Arda Senocak, Jiu Feng, Joon Son Chung, Mehmet Hamza Erol","submitted_at":"2024-06-05T15:00:59Z","abstract_excerpt":"Transformers have rapidly become the preferred choice for audio classification, surpassing methods based on CNNs. However, Audio Spectrogram Transformers (ASTs) exhibit quadratic scaling due to self-attention. The removal of this quadratic self-attention cost presents an appealing direction. Recently, state space models (SSMs), such as Mamba, have demonstrated potential in language and vision tasks in this regard. In this study, we explore whether reliance on self-attention is necessary for audio classification tasks. By introducing Audio Mamba (AuM), the first self-attention-free, purely SSM-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03344","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/2406.03344/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":"2406.03344","created_at":"2026-07-05T08:27:55.136397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03344v1","created_at":"2026-07-05T08:27:55.136397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03344","created_at":"2026-07-05T08:27:55.136397+00:00"},{"alias_kind":"pith_short_12","alias_value":"STSLD23MXZO2","created_at":"2026-07-05T08:27:55.136397+00:00"},{"alias_kind":"pith_short_16","alias_value":"STSLD23MXZO2LIWF","created_at":"2026-07-05T08:27:55.136397+00:00"},{"alias_kind":"pith_short_8","alias_value":"STSLD23M","created_at":"2026-07-05T08:27:55.136397+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19105","citing_title":"Latent Mamba Operator for Partial Differential Equations","ref_index":2018,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STSLD23MXZO2LIWFPGUZ2QXH3V","json":"https://pith.science/pith/STSLD23MXZO2LIWFPGUZ2QXH3V.json","graph_json":"https://pith.science/api/pith-number/STSLD23MXZO2LIWFPGUZ2QXH3V/graph.json","events_json":"https://pith.science/api/pith-number/STSLD23MXZO2LIWFPGUZ2QXH3V/events.json","paper":"https://pith.science/paper/STSLD23M"},"agent_actions":{"view_html":"https://pith.science/pith/STSLD23MXZO2LIWFPGUZ2QXH3V","download_json":"https://pith.science/pith/STSLD23MXZO2LIWFPGUZ2QXH3V.json","view_paper":"https://pith.science/paper/STSLD23M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03344&json=true","fetch_graph":"https://pith.science/api/pith-number/STSLD23MXZO2LIWFPGUZ2QXH3V/graph.json","fetch_events":"https://pith.science/api/pith-number/STSLD23MXZO2LIWFPGUZ2QXH3V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STSLD23MXZO2LIWFPGUZ2QXH3V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STSLD23MXZO2LIWFPGUZ2QXH3V/action/storage_attestation","attest_author":"https://pith.science/pith/STSLD23MXZO2LIWFPGUZ2QXH3V/action/author_attestation","sign_citation":"https://pith.science/pith/STSLD23MXZO2LIWFPGUZ2QXH3V/action/citation_signature","submit_replication":"https://pith.science/pith/STSLD23MXZO2LIWFPGUZ2QXH3V/action/replication_record"}},"created_at":"2026-07-05T08:27:55.136397+00:00","updated_at":"2026-07-05T08:27:55.136397+00:00"}