{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SIS7PJ2OBNRER5VDWW7APUIZNE","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":"7e2ad6d08c78e1245d927d309bd4502c7844a603900586bb0dd83d44c7525ef6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-27T13:03:17Z","title_canon_sha256":"954b82cb6fbecfeaa1f926623738eca6928c7738df2e614e0e8baefe022c8357"},"schema_version":"1.0","source":{"id":"2103.14899","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.14899","created_at":"2026-07-05T03:07:47Z"},{"alias_kind":"arxiv_version","alias_value":"2103.14899v2","created_at":"2026-07-05T03:07:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14899","created_at":"2026-07-05T03:07:47Z"},{"alias_kind":"pith_short_12","alias_value":"SIS7PJ2OBNRE","created_at":"2026-07-05T03:07:47Z"},{"alias_kind":"pith_short_16","alias_value":"SIS7PJ2OBNRER5VD","created_at":"2026-07-05T03:07:47Z"},{"alias_kind":"pith_short_8","alias_value":"SIS7PJ2O","created_at":"2026-07-05T03:07:47Z"}],"graph_snapshots":[{"event_id":"sha256:ee25dd6e6dfe59d417b361908be6256de80da0b4dc6ff4c3b2613d285b1b8ea8","target":"graph","created_at":"2026-07-05T03:07:47Z","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/2103.14899/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in transformer models for image classification. To this end, we propose a dual-branch transformer to combine image patches (i.e., tokens in a transformer) of different sizes to produce stronger image features. Our approach processes small-patch and large-patch tokens with two separate branches of different computational complexity and these tokens are then fuse","authors_text":"Chun-Fu Chen, Quanfu Fan, Rameswar Panda","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-27T13:03:17Z","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14899","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":"sha256:29c52ba54e47fea8592f399a9958462e79dfa8f1d1408154239694348ad21d16","target":"record","created_at":"2026-07-05T03:07:47Z","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":"7e2ad6d08c78e1245d927d309bd4502c7844a603900586bb0dd83d44c7525ef6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-27T13:03:17Z","title_canon_sha256":"954b82cb6fbecfeaa1f926623738eca6928c7738df2e614e0e8baefe022c8357"},"schema_version":"1.0","source":{"id":"2103.14899","kind":"arxiv","version":2}},"canonical_sha256":"9225f7a74e0b6248f6a3b5be07d119693cab369287e17277e42694b38422fc29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9225f7a74e0b6248f6a3b5be07d119693cab369287e17277e42694b38422fc29","first_computed_at":"2026-07-05T03:07:47.858842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:07:47.858842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GXfR/hxfsugAf1EBXQ3R2zbsa3k1YdWoV/hvdfBua4mk/6Ab8ykdWtILchojf/25YRAJDXhiajsbFVdfDAgDCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:07:47.859261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.14899","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29c52ba54e47fea8592f399a9958462e79dfa8f1d1408154239694348ad21d16","sha256:ee25dd6e6dfe59d417b361908be6256de80da0b4dc6ff4c3b2613d285b1b8ea8"],"state_sha256":"760e1ba84972a4599962b2b1e74810f666c12e70d3620b63674df622ca76c169"}