{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DRRLDFPJGQZYCYBSL7XKMCJ4XB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ee7c8d6ae3ee102c9330e0c4949d11bcb417fba6674fbd1df1794cf88aa62b55","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-13T12:27:17Z","title_canon_sha256":"b48d425b1a024cfabe160f9be88b849132cb435fccdce3596b0c8c77c60fcf5c"},"schema_version":"1.0","source":{"id":"2304.06446","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.06446","created_at":"2026-07-05T06:01:19Z"},{"alias_kind":"arxiv_version","alias_value":"2304.06446v2","created_at":"2026-07-05T06:01:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06446","created_at":"2026-07-05T06:01:19Z"},{"alias_kind":"pith_short_12","alias_value":"DRRLDFPJGQZY","created_at":"2026-07-05T06:01:19Z"},{"alias_kind":"pith_short_16","alias_value":"DRRLDFPJGQZYCYBS","created_at":"2026-07-05T06:01:19Z"},{"alias_kind":"pith_short_8","alias_value":"DRRLDFPJ","created_at":"2026-07-05T06:01:19Z"}],"graph_snapshots":[{"event_id":"sha256:141843a69ffc56b72bd081424b335d4c9f498b09f0f7f6df6cef665253da6346","target":"graph","created_at":"2026-07-05T06:01:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2304.06446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Badri N. Patro, Vijay Srinivas Agneeswaran, Vinay P. Namboodiri","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-13T12:27:17Z","title":"SpectFormer: Frequency and Attention is what you need in a Vision Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06446","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1c5e4a6c09c04ecd08af72681b960fb280244d78215f79fb30ecd42312e7d370","target":"record","created_at":"2026-07-05T06:01:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ee7c8d6ae3ee102c9330e0c4949d11bcb417fba6674fbd1df1794cf88aa62b55","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-13T12:27:17Z","title_canon_sha256":"b48d425b1a024cfabe160f9be88b849132cb435fccdce3596b0c8c77c60fcf5c"},"schema_version":"1.0","source":{"id":"2304.06446","kind":"arxiv","version":2}},"canonical_sha256":"1c62b195e934338160325feea6093cb87ccbda6a7b7300e7ed95a070d8837b82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c62b195e934338160325feea6093cb87ccbda6a7b7300e7ed95a070d8837b82","first_computed_at":"2026-07-05T06:01:19.123607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:01:19.123607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"97FI4SuNP/82GOkY0O+EbE0fBQoQk0mi774jUIi4RNuFjF/XpBue31llZVhOfpREg2oC2N4W+cWTfdYnpe9rDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:01:19.124052Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.06446","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c5e4a6c09c04ecd08af72681b960fb280244d78215f79fb30ecd42312e7d370","sha256:141843a69ffc56b72bd081424b335d4c9f498b09f0f7f6df6cef665253da6346"],"state_sha256":"e32d7090a8acf34325609c796798fc40fb70beecb8e19ef592732f80991bdd92"}