{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:SIS7PJ2OBNRER5VDWW7APUIZNE","short_pith_number":"pith:SIS7PJ2O","canonical_record":{"source":{"id":"2103.14899","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-27T13:03:17Z","cross_cats_sorted":[],"title_canon_sha256":"954b82cb6fbecfeaa1f926623738eca6928c7738df2e614e0e8baefe022c8357","abstract_canon_sha256":"7e2ad6d08c78e1245d927d309bd4502c7844a603900586bb0dd83d44c7525ef6"},"schema_version":"1.0"},"canonical_sha256":"9225f7a74e0b6248f6a3b5be07d119693cab369287e17277e42694b38422fc29","source":{"kind":"arxiv","id":"2103.14899","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:SIS7PJ2OBNRER5VDWW7APUIZNE","target":"record","payload":{"canonical_record":{"source":{"id":"2103.14899","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-27T13:03:17Z","cross_cats_sorted":[],"title_canon_sha256":"954b82cb6fbecfeaa1f926623738eca6928c7738df2e614e0e8baefe022c8357","abstract_canon_sha256":"7e2ad6d08c78e1245d927d309bd4502c7844a603900586bb0dd83d44c7525ef6"},"schema_version":"1.0"},"canonical_sha256":"9225f7a74e0b6248f6a3b5be07d119693cab369287e17277e42694b38422fc29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:47.859261Z","signature_b64":"GXfR/hxfsugAf1EBXQ3R2zbsa3k1YdWoV/hvdfBua4mk/6Ab8ykdWtILchojf/25YRAJDXhiajsbFVdfDAgDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9225f7a74e0b6248f6a3b5be07d119693cab369287e17277e42694b38422fc29","last_reissued_at":"2026-07-05T03:07:47.858842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:47.858842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.14899","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:07:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nNCU5220eqiSa0obJFM+UnzvIqBEcReTmGxzKPpfe47OhC7P8TmubwS2kmgEdaaaVq5uxc3IMlS+c0ypMxmMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:35:53.869708Z"},"content_sha256":"29c52ba54e47fea8592f399a9958462e79dfa8f1d1408154239694348ad21d16","schema_version":"1.0","event_id":"sha256:29c52ba54e47fea8592f399a9958462e79dfa8f1d1408154239694348ad21d16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:SIS7PJ2OBNRER5VDWW7APUIZNE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun-Fu Chen, Quanfu Fan, Rameswar Panda","submitted_at":"2021-03-27T13:03:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14899","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/2103.14899/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:07:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fx7dFsHVHys6lJSWV6Mh0xPhNX3aSWUvN+KrdLzHuOeIG1xnbjEfKF6aSwdVqKdGp6rJVrfdI70BlGiA2FXlBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:35:53.870306Z"},"content_sha256":"ee25dd6e6dfe59d417b361908be6256de80da0b4dc6ff4c3b2613d285b1b8ea8","schema_version":"1.0","event_id":"sha256:ee25dd6e6dfe59d417b361908be6256de80da0b4dc6ff4c3b2613d285b1b8ea8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE/bundle.json","state_url":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SIS7PJ2OBNRER5VDWW7APUIZNE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T20:35:53Z","links":{"resolver":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE","bundle":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE/bundle.json","state":"https://pith.science/pith/SIS7PJ2OBNRER5VDWW7APUIZNE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SIS7PJ2OBNRER5VDWW7APUIZNE/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"350gOrHc5R6KIcHSIFLugfzA9+NxA1bSifCmxoNtFDVE/KzLi5iWcx7XHl9XdogrdIb1XjZRhaV48rq2F3aZCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T20:35:53.875630Z","bundle_sha256":"8dd2fbe75664c24aee9bbf07d34c3596b76824b5e9c8406313a0aeb8ad5fb194"}}