{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DRRLDFPJGQZYCYBSL7XKMCJ4XB","short_pith_number":"pith:DRRLDFPJ","schema_version":"1.0","canonical_sha256":"1c62b195e934338160325feea6093cb87ccbda6a7b7300e7ed95a070d8837b82","source":{"kind":"arxiv","id":"2304.06446","version":2},"attestation_state":"computed","paper":{"title":"SpectFormer: Frequency and Attention is what you need in a Vision Transformer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Badri N. Patro, Vijay Srinivas Agneeswaran, Vinay P. Namboodiri","submitted_at":"2023-04-13T12:27:17Z","abstract_excerpt":"Vision transformers have been applied successfully for image recognition tasks. There have been either multi-headed self-attention based (ViT \\cite{dosovitskiy2020image}, DeIT, \\cite{touvron2021training}) similar to the original work in textual models or more recently based on spectral layers (Fnet\\cite{lee2021fnet}, GFNet\\cite{rao2021global}, AFNO\\cite{guibas2021efficient}). We hypothesize that both spectral and multi-headed attention plays a major role. We investigate this hypothesis through this work and observe that indeed combining spectral and multi-headed attention layers provides a bet"},"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":"2304.06446","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-13T12:27:17Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"b48d425b1a024cfabe160f9be88b849132cb435fccdce3596b0c8c77c60fcf5c","abstract_canon_sha256":"ee7c8d6ae3ee102c9330e0c4949d11bcb417fba6674fbd1df1794cf88aa62b55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:19.124052Z","signature_b64":"97FI4SuNP/82GOkY0O+EbE0fBQoQk0mi774jUIi4RNuFjF/XpBue31llZVhOfpREg2oC2N4W+cWTfdYnpe9rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c62b195e934338160325feea6093cb87ccbda6a7b7300e7ed95a070d8837b82","last_reissued_at":"2026-07-05T06:01:19.123607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:19.123607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpectFormer: Frequency and Attention is what you need in a Vision Transformer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Badri N. Patro, Vijay Srinivas Agneeswaran, Vinay P. Namboodiri","submitted_at":"2023-04-13T12:27:17Z","abstract_excerpt":"Vision transformers have been applied successfully for image recognition tasks. There have been either multi-headed self-attention based (ViT \\cite{dosovitskiy2020image}, DeIT, \\cite{touvron2021training}) similar to the original work in textual models or more recently based on spectral layers (Fnet\\cite{lee2021fnet}, GFNet\\cite{rao2021global}, AFNO\\cite{guibas2021efficient}). We hypothesize that both spectral and multi-headed attention plays a major role. We investigate this hypothesis through this work and observe that indeed combining spectral and multi-headed attention layers provides a bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06446","kind":"arxiv","version":2},"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/2304.06446/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":"2304.06446","created_at":"2026-07-05T06:01:19.123663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.06446v2","created_at":"2026-07-05T06:01:19.123663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06446","created_at":"2026-07-05T06:01:19.123663+00:00"},{"alias_kind":"pith_short_12","alias_value":"DRRLDFPJGQZY","created_at":"2026-07-05T06:01:19.123663+00:00"},{"alias_kind":"pith_short_16","alias_value":"DRRLDFPJGQZYCYBS","created_at":"2026-07-05T06:01:19.123663+00:00"},{"alias_kind":"pith_short_8","alias_value":"DRRLDFPJ","created_at":"2026-07-05T06:01:19.123663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08181","citing_title":"Text-Guided Multi-Scale Frequency Representation Adaptation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00871","citing_title":"NAKUL-Med: Spectral-Graph State Space Models with Dynamics Kernels for Medical Signals","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19028","citing_title":"Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors","ref_index":269,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14724","citing_title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DRRLDFPJGQZYCYBSL7XKMCJ4XB","json":"https://pith.science/pith/DRRLDFPJGQZYCYBSL7XKMCJ4XB.json","graph_json":"https://pith.science/api/pith-number/DRRLDFPJGQZYCYBSL7XKMCJ4XB/graph.json","events_json":"https://pith.science/api/pith-number/DRRLDFPJGQZYCYBSL7XKMCJ4XB/events.json","paper":"https://pith.science/paper/DRRLDFPJ"},"agent_actions":{"view_html":"https://pith.science/pith/DRRLDFPJGQZYCYBSL7XKMCJ4XB","download_json":"https://pith.science/pith/DRRLDFPJGQZYCYBSL7XKMCJ4XB.json","view_paper":"https://pith.science/paper/DRRLDFPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.06446&json=true","fetch_graph":"https://pith.science/api/pith-number/DRRLDFPJGQZYCYBSL7XKMCJ4XB/graph.json","fetch_events":"https://pith.science/api/pith-number/DRRLDFPJGQZYCYBSL7XKMCJ4XB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DRRLDFPJGQZYCYBSL7XKMCJ4XB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DRRLDFPJGQZYCYBSL7XKMCJ4XB/action/storage_attestation","attest_author":"https://pith.science/pith/DRRLDFPJGQZYCYBSL7XKMCJ4XB/action/author_attestation","sign_citation":"https://pith.science/pith/DRRLDFPJGQZYCYBSL7XKMCJ4XB/action/citation_signature","submit_replication":"https://pith.science/pith/DRRLDFPJGQZYCYBSL7XKMCJ4XB/action/replication_record"}},"created_at":"2026-07-05T06:01:19.123663+00:00","updated_at":"2026-07-05T06:01:19.123663+00:00"}