{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YFTXXA2EXCGY2PIX4XJXZAMUVZ","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":"4869fd8004d69ca227b1d0861ec6c401b4e90c8ce794a8917ec78d736e49fcf0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-03T05:16:51Z","title_canon_sha256":"078f853a3aa758f98a73248281b9dd1bc275a2e4653188dd051cf818dadbc604"},"schema_version":"1.0","source":{"id":"2204.00993","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.00993","created_at":"2026-07-05T04:44:00Z"},{"alias_kind":"arxiv_version","alias_value":"2204.00993v3","created_at":"2026-07-05T04:44:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00993","created_at":"2026-07-05T04:44:00Z"},{"alias_kind":"pith_short_12","alias_value":"YFTXXA2EXCGY","created_at":"2026-07-05T04:44:00Z"},{"alias_kind":"pith_short_16","alias_value":"YFTXXA2EXCGY2PIX","created_at":"2026-07-05T04:44:00Z"},{"alias_kind":"pith_short_8","alias_value":"YFTXXA2E","created_at":"2026-07-05T04:44:00Z"}],"graph_snapshots":[{"event_id":"sha256:d257bea2c2fda75f9f719974c8265d765570dc31907368d437deb8c50081aa39","target":"graph","created_at":"2026-07-05T04:44:00Z","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/2204.00993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The transformer models have shown promising effectiveness in dealing with various vision tasks. However, compared with training Convolutional Neural Network (CNN) models, training Vision Transformer (ViT) models is more difficult and relies on the large-scale training set. To explain this observation we make a hypothesis that \\textit{ViT models are less effective in capturing the high-frequency components of images than CNN models}, and verify it by a frequency analysis. Inspired by this finding, we first investigate the effects of existing techniques for improving ViT models from a new freque","authors_text":"Jiawang Bai, Li Yuan, Shuicheng Yan, Shu-Tao Xia, Wei Liu, ZhiFeng Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-03T05:16:51Z","title":"Improving Vision Transformers by Revisiting High-frequency Components"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00993","kind":"arxiv","version":3},"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:e1be706187bc31efa5d7b903aff60817bde2d874a068d9c9c2aee7781e1d4760","target":"record","created_at":"2026-07-05T04:44:00Z","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":"4869fd8004d69ca227b1d0861ec6c401b4e90c8ce794a8917ec78d736e49fcf0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-03T05:16:51Z","title_canon_sha256":"078f853a3aa758f98a73248281b9dd1bc275a2e4653188dd051cf818dadbc604"},"schema_version":"1.0","source":{"id":"2204.00993","kind":"arxiv","version":3}},"canonical_sha256":"c1677b8344b88d8d3d17e5d37c8194ae543df2c7c357b46621501f44afd5827a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1677b8344b88d8d3d17e5d37c8194ae543df2c7c357b46621501f44afd5827a","first_computed_at":"2026-07-05T04:44:00.838478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:44:00.838478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AzfKfUfT83dMpT8uWibvlXGbn2QvMXYJ0zW0DvnGY0mMA37mSfgQbTRq5wfdVOo72ts9c0ArW8WLYZS5rFrnDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:44:00.838903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.00993","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1be706187bc31efa5d7b903aff60817bde2d874a068d9c9c2aee7781e1d4760","sha256:d257bea2c2fda75f9f719974c8265d765570dc31907368d437deb8c50081aa39"],"state_sha256":"f40977750c65da549d154ac44b0333af1d59e4597d6b57d7211c2d564fc82041"}