{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ODYMEM4B64BSJHUSQ3VRA64N36","short_pith_number":"pith:ODYMEM4B","schema_version":"1.0","canonical_sha256":"70f0c23381f703249e9286eb107b8ddf9d0ae22c2efd895336483fe04f704eb1","source":{"kind":"arxiv","id":"2110.05069","version":3},"attestation_state":"computed","paper":{"title":"Efficient Training of Audio Transformers with Patchout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gerhard Widmer, Hamid Eghbal-zadeh, Jan Schl\\\"uter, Khaled Koutini","submitted_at":"2021-10-11T08:07:50Z","abstract_excerpt":"The great success of transformer-based models in natural language processing (NLP) has led to various attempts at adapting these architectures to other domains such as vision and audio. Recent work has shown that transformers can outperform Convolutional Neural Networks (CNNs) on vision and audio tasks. However, one of the main shortcomings of transformer models, compared to the well-established CNNs, is the computational complexity. In transformers, the compute and memory complexity is known to grow quadratically with the input length. Therefore, there has been extensive work on optimizing tr"},"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":"2110.05069","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-10-11T08:07:50Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"de72afadca9993299095687ca1d79076186542f5560871265d1a3b43fa6492a2","abstract_canon_sha256":"5abf957d536dacb53c8f1c35c80ccffd832a99a4af95a970e259e9d33f61c45c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:35:42.370077Z","signature_b64":"5wuaLall//gi5T8axWwtXvvIppnotMF5/d3gnuTcneWgR6p55rr0ARRzRsSAUNLiQ8TAV9HlWORc18otXRE3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70f0c23381f703249e9286eb107b8ddf9d0ae22c2efd895336483fe04f704eb1","last_reissued_at":"2026-07-05T05:35:42.369581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:35:42.369581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Training of Audio Transformers with Patchout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Gerhard Widmer, Hamid Eghbal-zadeh, Jan Schl\\\"uter, Khaled Koutini","submitted_at":"2021-10-11T08:07:50Z","abstract_excerpt":"The great success of transformer-based models in natural language processing (NLP) has led to various attempts at adapting these architectures to other domains such as vision and audio. Recent work has shown that transformers can outperform Convolutional Neural Networks (CNNs) on vision and audio tasks. However, one of the main shortcomings of transformer models, compared to the well-established CNNs, is the computational complexity. In transformers, the compute and memory complexity is known to grow quadratically with the input length. Therefore, there has been extensive work on optimizing tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05069","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/2110.05069/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":"2110.05069","created_at":"2026-07-05T05:35:42.369648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.05069v3","created_at":"2026-07-05T05:35:42.369648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05069","created_at":"2026-07-05T05:35:42.369648+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODYMEM4B64BS","created_at":"2026-07-05T05:35:42.369648+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODYMEM4B64BSJHUS","created_at":"2026-07-05T05:35:42.369648+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODYMEM4B","created_at":"2026-07-05T05:35:42.369648+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24307","citing_title":"Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23064","citing_title":"STAR-VAE: Structured Topology-Aware Regularization for Audio Reconstruction and Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22717","citing_title":"Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2510.09065","citing_title":"MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02731","citing_title":"Omni2Sound: Towards Unified Video-Text-to-Audio Generation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20981","citing_title":"Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13672","citing_title":"SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07903","citing_title":"BeeVe: Unsupervised Acoustic State Discovery in Honey Bee Buzzing","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15086","citing_title":"ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODYMEM4B64BSJHUSQ3VRA64N36","json":"https://pith.science/pith/ODYMEM4B64BSJHUSQ3VRA64N36.json","graph_json":"https://pith.science/api/pith-number/ODYMEM4B64BSJHUSQ3VRA64N36/graph.json","events_json":"https://pith.science/api/pith-number/ODYMEM4B64BSJHUSQ3VRA64N36/events.json","paper":"https://pith.science/paper/ODYMEM4B"},"agent_actions":{"view_html":"https://pith.science/pith/ODYMEM4B64BSJHUSQ3VRA64N36","download_json":"https://pith.science/pith/ODYMEM4B64BSJHUSQ3VRA64N36.json","view_paper":"https://pith.science/paper/ODYMEM4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.05069&json=true","fetch_graph":"https://pith.science/api/pith-number/ODYMEM4B64BSJHUSQ3VRA64N36/graph.json","fetch_events":"https://pith.science/api/pith-number/ODYMEM4B64BSJHUSQ3VRA64N36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODYMEM4B64BSJHUSQ3VRA64N36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODYMEM4B64BSJHUSQ3VRA64N36/action/storage_attestation","attest_author":"https://pith.science/pith/ODYMEM4B64BSJHUSQ3VRA64N36/action/author_attestation","sign_citation":"https://pith.science/pith/ODYMEM4B64BSJHUSQ3VRA64N36/action/citation_signature","submit_replication":"https://pith.science/pith/ODYMEM4B64BSJHUSQ3VRA64N36/action/replication_record"}},"created_at":"2026-07-05T05:35:42.369648+00:00","updated_at":"2026-07-05T05:35:42.369648+00:00"}