{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DVPSGXRBDDTEALQU5DVQORML44","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":"e6ca30caa93694bceb74200c26de4f221363c4309f01af8b97df4f2752b25c98","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-11T16:03:51Z","title_canon_sha256":"0894cb6369ad480231249c41a0e34ed684f3c1da9ac7dc02b44f7dc0220606bb"},"schema_version":"1.0","source":{"id":"2207.04978","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.04978","created_at":"2026-07-05T04:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"2207.04978v1","created_at":"2026-07-05T04:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04978","created_at":"2026-07-05T04:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"DVPSGXRBDDTE","created_at":"2026-07-05T04:39:05Z"},{"alias_kind":"pith_short_16","alias_value":"DVPSGXRBDDTEALQU","created_at":"2026-07-05T04:39:05Z"},{"alias_kind":"pith_short_8","alias_value":"DVPSGXRB","created_at":"2026-07-05T04:39:05Z"}],"graph_snapshots":[{"event_id":"sha256:ec1f04e18335f2f01b5496999c99b9c03d85a0129b85c2a988f78321f7e1a828","target":"graph","created_at":"2026-07-05T04:39:05Z","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/2207.04978/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks, while the self-attention computation in Transformer scales quadratically w.r.t. the input patch number. Thus, existing solutions commonly employ down-sampling operations (e.g., average pooling) over keys/values to dramatically reduce the computational cost. In this work, we argue that such over-aggressive down-sampling design is not invertible and inevitably causes information dropping especially for high-frequency components in objects (e.g., texture details). Motivated by the wavelet theory, we","authors_text":"Chong-Wah Ngo, Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-11T16:03:51Z","title":"Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04978","kind":"arxiv","version":1},"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":"sha256:10ce5cfee0e3ce535b11d7e2b152a728e38d50725d189edb5fa927d469eae39b","target":"record","created_at":"2026-07-05T04:39:05Z","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":"e6ca30caa93694bceb74200c26de4f221363c4309f01af8b97df4f2752b25c98","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-11T16:03:51Z","title_canon_sha256":"0894cb6369ad480231249c41a0e34ed684f3c1da9ac7dc02b44f7dc0220606bb"},"schema_version":"1.0","source":{"id":"2207.04978","kind":"arxiv","version":1}},"canonical_sha256":"1d5f235e2118e6402e14e8eb07458be702e4326e8b630f83671de96cb3e42b6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d5f235e2118e6402e14e8eb07458be702e4326e8b630f83671de96cb3e42b6c","first_computed_at":"2026-07-05T04:39:05.697898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:39:05.697898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DvQrdeEdaoZDaJthG/8gDD0rEgYq9baV3hn7YhK7CmyYdjlpDEu/n+54yHa4xcsjZ1Xz+vH/2XpGQwGoeUmhAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:39:05.698728Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.04978","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10ce5cfee0e3ce535b11d7e2b152a728e38d50725d189edb5fa927d469eae39b","sha256:ec1f04e18335f2f01b5496999c99b9c03d85a0129b85c2a988f78321f7e1a828"],"state_sha256":"c439b4f7e9b25905bcdd62cfe012301f7e1543c3b142ae04b7c502aed8bd6af3"}