{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WYYAZ2VJTXVDUKLN2JEMIIDGLK","short_pith_number":"pith:WYYAZ2VJ","schema_version":"1.0","canonical_sha256":"b6300ceaa99dea3a296dd248c420665a9fb1241c542edefe7b611e261535a718","source":{"kind":"arxiv","id":"2203.09581","version":3},"attestation_state":"computed","paper":{"title":"SepTr: Separable Transformer for Audio Spectrogram Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Nicolae-Catalin Ristea, Radu Tudor Ionescu","submitted_at":"2022-03-17T19:48:43Z","abstract_excerpt":"Following the successful application of vision transformers in multiple computer vision tasks, these models have drawn the attention of the signal processing community. This is because signals are often represented as spectrograms (e.g. through Discrete Fourier Transform) which can be directly provided as input to vision transformers. However, naively applying transformers to spectrograms is suboptimal. Since the axes represent distinct dimensions, i.e. frequency and time, we argue that a better approach is to separate the attention dedicated to each axis. To this end, we propose the Separable"},"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":"2203.09581","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-17T19:48:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"14eadba479d2a9e1f5469997c827793a04c05cec21730ac6771e1a476ffcda35","abstract_canon_sha256":"828cd93991907445c0935456b5325c9323210975122c9a246547651a208565b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:32.954705Z","signature_b64":"0+wXXHvcX0KTwvjx1ydMdMRpzZumMsIKRCFcUM0iNUhQnNh5p/reAtpaTtklyrMzYOzfLVokiOeUu+2MDLJgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6300ceaa99dea3a296dd248c420665a9fb1241c542edefe7b611e261535a718","last_reissued_at":"2026-07-05T04:33:32.954210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:32.954210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SepTr: Separable Transformer for Audio Spectrogram Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Nicolae-Catalin Ristea, Radu Tudor Ionescu","submitted_at":"2022-03-17T19:48:43Z","abstract_excerpt":"Following the successful application of vision transformers in multiple computer vision tasks, these models have drawn the attention of the signal processing community. This is because signals are often represented as spectrograms (e.g. through Discrete Fourier Transform) which can be directly provided as input to vision transformers. However, naively applying transformers to spectrograms is suboptimal. Since the axes represent distinct dimensions, i.e. frequency and time, we argue that a better approach is to separate the attention dedicated to each axis. To this end, we propose the Separable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09581","kind":"arxiv","version":3},"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/2203.09581/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":"2203.09581","created_at":"2026-07-05T04:33:32.954267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.09581v3","created_at":"2026-07-05T04:33:32.954267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09581","created_at":"2026-07-05T04:33:32.954267+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYYAZ2VJTXVD","created_at":"2026-07-05T04:33:32.954267+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYYAZ2VJTXVDUKLN","created_at":"2026-07-05T04:33:32.954267+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYYAZ2VJ","created_at":"2026-07-05T04:33:32.954267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WYYAZ2VJTXVDUKLN2JEMIIDGLK","json":"https://pith.science/pith/WYYAZ2VJTXVDUKLN2JEMIIDGLK.json","graph_json":"https://pith.science/api/pith-number/WYYAZ2VJTXVDUKLN2JEMIIDGLK/graph.json","events_json":"https://pith.science/api/pith-number/WYYAZ2VJTXVDUKLN2JEMIIDGLK/events.json","paper":"https://pith.science/paper/WYYAZ2VJ"},"agent_actions":{"view_html":"https://pith.science/pith/WYYAZ2VJTXVDUKLN2JEMIIDGLK","download_json":"https://pith.science/pith/WYYAZ2VJTXVDUKLN2JEMIIDGLK.json","view_paper":"https://pith.science/paper/WYYAZ2VJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.09581&json=true","fetch_graph":"https://pith.science/api/pith-number/WYYAZ2VJTXVDUKLN2JEMIIDGLK/graph.json","fetch_events":"https://pith.science/api/pith-number/WYYAZ2VJTXVDUKLN2JEMIIDGLK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYYAZ2VJTXVDUKLN2JEMIIDGLK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYYAZ2VJTXVDUKLN2JEMIIDGLK/action/storage_attestation","attest_author":"https://pith.science/pith/WYYAZ2VJTXVDUKLN2JEMIIDGLK/action/author_attestation","sign_citation":"https://pith.science/pith/WYYAZ2VJTXVDUKLN2JEMIIDGLK/action/citation_signature","submit_replication":"https://pith.science/pith/WYYAZ2VJTXVDUKLN2JEMIIDGLK/action/replication_record"}},"created_at":"2026-07-05T04:33:32.954267+00:00","updated_at":"2026-07-05T04:33:32.954267+00:00"}