{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZDSP4PGXMMWIU7SSWGO252J6HK","short_pith_number":"pith:ZDSP4PGX","schema_version":"1.0","canonical_sha256":"c8e4fe3cd7632c8a7e52b19daee93e3a9503ccc3ca49aaa7f434624d8605be08","source":{"kind":"arxiv","id":"2307.14008","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Frequency Filters As Efficient Global Token Mixers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Cuiling Lan, Yan Lu, Zheng-Jun Zha, Zhipeng Huang, Zhizheng Zhang","submitted_at":"2023-07-26T07:42:28Z","abstract_excerpt":"Recent vision transformers, large-kernel CNNs and MLPs have attained remarkable successes in broad vision tasks thanks to their effective information fusion in the global scope. However, their efficient deployments, especially on mobile devices, still suffer from noteworthy challenges due to the heavy computational costs of self-attention mechanisms, large kernels, or fully connected layers. In this work, we apply conventional convolution theorem to deep learning for addressing this and reveal that adaptive frequency filters can serve as efficient global token mixers. With this insight, we pro"},"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":"2307.14008","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-26T07:42:28Z","cross_cats_sorted":[],"title_canon_sha256":"c98a11303ac97348380c27198c35ddc4d143f6e0e95c76b0aba97260c4535bf9","abstract_canon_sha256":"2045d887325ee7016ff3693d4fefc66a25da6789e88de01f4f36c9fa9fbae2dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:56.225992Z","signature_b64":"JT9z9qv1UZCPoWC/1I2ULOGVd8dq2TOHulBroR47aRk3Rip7rVfnRhtD9EUmtnLZPbXGV1ceToqaxP6NzFG3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8e4fe3cd7632c8a7e52b19daee93e3a9503ccc3ca49aaa7f434624d8605be08","last_reissued_at":"2026-07-05T06:34:56.225526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:56.225526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Frequency Filters As Efficient Global Token Mixers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baining Guo, Cuiling Lan, Yan Lu, Zheng-Jun Zha, Zhipeng Huang, Zhizheng Zhang","submitted_at":"2023-07-26T07:42:28Z","abstract_excerpt":"Recent vision transformers, large-kernel CNNs and MLPs have attained remarkable successes in broad vision tasks thanks to their effective information fusion in the global scope. However, their efficient deployments, especially on mobile devices, still suffer from noteworthy challenges due to the heavy computational costs of self-attention mechanisms, large kernels, or fully connected layers. In this work, we apply conventional convolution theorem to deep learning for addressing this and reveal that adaptive frequency filters can serve as efficient global token mixers. With this insight, we pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14008","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/2307.14008/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":"2307.14008","created_at":"2026-07-05T06:34:56.225592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.14008v1","created_at":"2026-07-05T06:34:56.225592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14008","created_at":"2026-07-05T06:34:56.225592+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDSP4PGXMMWI","created_at":"2026-07-05T06:34:56.225592+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDSP4PGXMMWIU7SS","created_at":"2026-07-05T06:34:56.225592+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDSP4PGX","created_at":"2026-07-05T06:34:56.225592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.12552","citing_title":"FreqSelect: Frequency-Aware fMRI-to-Image Reconstruction","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZDSP4PGXMMWIU7SSWGO252J6HK","json":"https://pith.science/pith/ZDSP4PGXMMWIU7SSWGO252J6HK.json","graph_json":"https://pith.science/api/pith-number/ZDSP4PGXMMWIU7SSWGO252J6HK/graph.json","events_json":"https://pith.science/api/pith-number/ZDSP4PGXMMWIU7SSWGO252J6HK/events.json","paper":"https://pith.science/paper/ZDSP4PGX"},"agent_actions":{"view_html":"https://pith.science/pith/ZDSP4PGXMMWIU7SSWGO252J6HK","download_json":"https://pith.science/pith/ZDSP4PGXMMWIU7SSWGO252J6HK.json","view_paper":"https://pith.science/paper/ZDSP4PGX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.14008&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDSP4PGXMMWIU7SSWGO252J6HK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDSP4PGXMMWIU7SSWGO252J6HK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDSP4PGXMMWIU7SSWGO252J6HK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDSP4PGXMMWIU7SSWGO252J6HK/action/storage_attestation","attest_author":"https://pith.science/pith/ZDSP4PGXMMWIU7SSWGO252J6HK/action/author_attestation","sign_citation":"https://pith.science/pith/ZDSP4PGXMMWIU7SSWGO252J6HK/action/citation_signature","submit_replication":"https://pith.science/pith/ZDSP4PGXMMWIU7SSWGO252J6HK/action/replication_record"}},"created_at":"2026-07-05T06:34:56.225592+00:00","updated_at":"2026-07-05T06:34:56.225592+00:00"}