{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HTZQOELVOSNJBDPC5OTKYED5DK","short_pith_number":"pith:HTZQOELV","canonical_record":{"source":{"id":"2101.11986","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-28T13:25:28Z","cross_cats_sorted":[],"title_canon_sha256":"55c68d805b902c41e21c3892a3e2758c24c55ef8746a44ccbf7ca44a79c7c4bf","abstract_canon_sha256":"87c9e82a18927b12d398c3b1566aa012714b7b67e86d4d3ace1927944b98f786"},"schema_version":"1.0"},"canonical_sha256":"3cf3071175749a908de2eba6ac107d1a80a68ac0d465da493a115a297a53bf9f","source":{"kind":"arxiv","id":"2101.11986","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.11986","created_at":"2026-07-05T03:36:01Z"},{"alias_kind":"arxiv_version","alias_value":"2101.11986v3","created_at":"2026-07-05T03:36:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11986","created_at":"2026-07-05T03:36:01Z"},{"alias_kind":"pith_short_12","alias_value":"HTZQOELVOSNJ","created_at":"2026-07-05T03:36:01Z"},{"alias_kind":"pith_short_16","alias_value":"HTZQOELVOSNJBDPC","created_at":"2026-07-05T03:36:01Z"},{"alias_kind":"pith_short_8","alias_value":"HTZQOELV","created_at":"2026-07-05T03:36:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HTZQOELVOSNJBDPC5OTKYED5DK","target":"record","payload":{"canonical_record":{"source":{"id":"2101.11986","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-28T13:25:28Z","cross_cats_sorted":[],"title_canon_sha256":"55c68d805b902c41e21c3892a3e2758c24c55ef8746a44ccbf7ca44a79c7c4bf","abstract_canon_sha256":"87c9e82a18927b12d398c3b1566aa012714b7b67e86d4d3ace1927944b98f786"},"schema_version":"1.0"},"canonical_sha256":"3cf3071175749a908de2eba6ac107d1a80a68ac0d465da493a115a297a53bf9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:01.142613Z","signature_b64":"H5DnWY1b84TnR2zNVp4yWHPxXFbz9/tJBWKL9H5ZqdNBNX+B1MVEy5u7+k6TvqvXJH9pxo6ZoihQ89vZVEvUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cf3071175749a908de2eba6ac107d1a80a68ac0d465da493a115a297a53bf9f","last_reissued_at":"2026-07-05T03:36:01.142123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:01.142123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.11986","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:36:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JRo58/66eB4b7DXe4gEN4ccZEziZjJVRshWQc84Cdmi9ptrSWmd+BsyXo0ebOqPy8Hvedyv0Wcrzq9lv88q/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:56:09.985785Z"},"content_sha256":"4545cc533496dfddf94574c37432d8cc6d20b3f8498459f0553150156d74990e","schema_version":"1.0","event_id":"sha256:4545cc533496dfddf94574c37432d8cc6d20b3f8498459f0553150156d74990e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HTZQOELVOSNJBDPC5OTKYED5DK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Francis EH Tay, Jiashi Feng, Li Yuan, Shuicheng Yan, Tao Wang, Weihao Yu, Yujun Shi, Yunpeng Chen, Zihang Jiang","submitted_at":"2021-01-28T13:25:28Z","abstract_excerpt":"Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed length and then applies multiple Transformer layers to model their global relation for classification. However, ViT achieves inferior performance to CNNs when trained from scratch on a midsize dataset like ImageNet. We find it is because: 1) the simple tokenization of input images fails to model the important local structure such as edges and lines among neig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11986","kind":"arxiv","version":3},"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/2101.11986/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":"2026-07-05T03:36:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NXDS3x6z/oiiUzYmIZ5AI8yZEu0kghj1cZX0StiD9r0RNo33gUNkYCrSPNikt8mg0VinzQc71nj/7YzBJD7ODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:56:09.986578Z"},"content_sha256":"26e9789df9f0c61ab368fb74957b50508dd50e9b3bb644d6ded6111d201f3962","schema_version":"1.0","event_id":"sha256:26e9789df9f0c61ab368fb74957b50508dd50e9b3bb644d6ded6111d201f3962"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HTZQOELVOSNJBDPC5OTKYED5DK/bundle.json","state_url":"https://pith.science/pith/HTZQOELVOSNJBDPC5OTKYED5DK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HTZQOELVOSNJBDPC5OTKYED5DK/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":"2026-08-19T23:56:09Z","links":{"resolver":"https://pith.science/pith/HTZQOELVOSNJBDPC5OTKYED5DK","bundle":"https://pith.science/pith/HTZQOELVOSNJBDPC5OTKYED5DK/bundle.json","state":"https://pith.science/pith/HTZQOELVOSNJBDPC5OTKYED5DK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HTZQOELVOSNJBDPC5OTKYED5DK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HTZQOELVOSNJBDPC5OTKYED5DK","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":"87c9e82a18927b12d398c3b1566aa012714b7b67e86d4d3ace1927944b98f786","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-28T13:25:28Z","title_canon_sha256":"55c68d805b902c41e21c3892a3e2758c24c55ef8746a44ccbf7ca44a79c7c4bf"},"schema_version":"1.0","source":{"id":"2101.11986","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.11986","created_at":"2026-07-05T03:36:01Z"},{"alias_kind":"arxiv_version","alias_value":"2101.11986v3","created_at":"2026-07-05T03:36:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11986","created_at":"2026-07-05T03:36:01Z"},{"alias_kind":"pith_short_12","alias_value":"HTZQOELVOSNJ","created_at":"2026-07-05T03:36:01Z"},{"alias_kind":"pith_short_16","alias_value":"HTZQOELVOSNJBDPC","created_at":"2026-07-05T03:36:01Z"},{"alias_kind":"pith_short_8","alias_value":"HTZQOELV","created_at":"2026-07-05T03:36:01Z"}],"graph_snapshots":[{"event_id":"sha256:26e9789df9f0c61ab368fb74957b50508dd50e9b3bb644d6ded6111d201f3962","target":"graph","created_at":"2026-07-05T03:36:01Z","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/2101.11986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed length and then applies multiple Transformer layers to model their global relation for classification. However, ViT achieves inferior performance to CNNs when trained from scratch on a midsize dataset like ImageNet. We find it is because: 1) the simple tokenization of input images fails to model the important local structure such as edges and lines among neig","authors_text":"Francis EH Tay, Jiashi Feng, Li Yuan, Shuicheng Yan, Tao Wang, Weihao Yu, Yujun Shi, Yunpeng Chen, Zihang Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-28T13:25:28Z","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11986","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":"sha256:4545cc533496dfddf94574c37432d8cc6d20b3f8498459f0553150156d74990e","target":"record","created_at":"2026-07-05T03:36:01Z","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":"87c9e82a18927b12d398c3b1566aa012714b7b67e86d4d3ace1927944b98f786","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-28T13:25:28Z","title_canon_sha256":"55c68d805b902c41e21c3892a3e2758c24c55ef8746a44ccbf7ca44a79c7c4bf"},"schema_version":"1.0","source":{"id":"2101.11986","kind":"arxiv","version":3}},"canonical_sha256":"3cf3071175749a908de2eba6ac107d1a80a68ac0d465da493a115a297a53bf9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cf3071175749a908de2eba6ac107d1a80a68ac0d465da493a115a297a53bf9f","first_computed_at":"2026-07-05T03:36:01.142123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:36:01.142123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H5DnWY1b84TnR2zNVp4yWHPxXFbz9/tJBWKL9H5ZqdNBNX+B1MVEy5u7+k6TvqvXJH9pxo6ZoihQ89vZVEvUDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:36:01.142613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.11986","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4545cc533496dfddf94574c37432d8cc6d20b3f8498459f0553150156d74990e","sha256:26e9789df9f0c61ab368fb74957b50508dd50e9b3bb644d6ded6111d201f3962"],"state_sha256":"37c6611f548b608043a5a539cf505eb0180fc3df8e6c9ec0947ddebfa72c6246"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uryTgIcWCVdmfD7o5K+lhEoIP+r0swZrNXc3mrh+WDZ4+1KiBYvKcqyiqxXX5bIuqN1R0XpmJSyQQWAxqYGxCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:56:09.994267Z","bundle_sha256":"3c6676c9861e20165fb6ef6741ed00941141f2f2197b4d2ff21949c02580225f"}}