{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ESZSFUHMON74AQMA64247T35HG","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":"0ca762d3566f5db6800675190ee110df25d6590beddddf17efea48d33bccaaac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-27T03:24:03Z","title_canon_sha256":"c65ca3179194e1e52b17176f97e048f66a230d927153aa6266b26470a0ad795e"},"schema_version":"1.0","source":{"id":"2112.13492","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.13492","created_at":"2026-07-05T03:43:53Z"},{"alias_kind":"arxiv_version","alias_value":"2112.13492v1","created_at":"2026-07-05T03:43:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13492","created_at":"2026-07-05T03:43:53Z"},{"alias_kind":"pith_short_12","alias_value":"ESZSFUHMON74","created_at":"2026-07-05T03:43:53Z"},{"alias_kind":"pith_short_16","alias_value":"ESZSFUHMON74AQMA","created_at":"2026-07-05T03:43:53Z"},{"alias_kind":"pith_short_8","alias_value":"ESZSFUHM","created_at":"2026-07-05T03:43:53Z"}],"graph_snapshots":[{"event_id":"sha256:20a6e57c87d6d9746c0b1b4bf93a5e6a41d767e8fea6755c68e65c55e0e738b2","target":"graph","created_at":"2026-07-05T03:43:53Z","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/2112.13492/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, the Vision Transformer (ViT), which applied the transformer structure to the image classification task, has outperformed convolutional neural networks. However, the high performance of the ViT results from pre-training using a large-size dataset such as JFT-300M, and its dependence on a large dataset is interpreted as due to low locality inductive bias. This paper proposes Shifted Patch Tokenization (SPT) and Locality Self-Attention (LSA), which effectively solve the lack of locality inductive bias and enable it to learn from scratch even on small-size datasets. Moreover, SPT and LSA","authors_text":"Byung Cheol Song, Seung Hoon Lee, Seunghyun Lee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-27T03:24:03Z","title":"Vision Transformer for Small-Size Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13492","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":"sha256:33ae5720ab8acc122ee4b43a32a3d6233a5e35d000ad449884e92d0722778663","target":"record","created_at":"2026-07-05T03:43:53Z","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":"0ca762d3566f5db6800675190ee110df25d6590beddddf17efea48d33bccaaac","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-27T03:24:03Z","title_canon_sha256":"c65ca3179194e1e52b17176f97e048f66a230d927153aa6266b26470a0ad795e"},"schema_version":"1.0","source":{"id":"2112.13492","kind":"arxiv","version":1}},"canonical_sha256":"24b322d0ec737fc04180f735cfcf7d398ef905fe321568ebc7f19728bf1fa8b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24b322d0ec737fc04180f735cfcf7d398ef905fe321568ebc7f19728bf1fa8b7","first_computed_at":"2026-07-05T03:43:53.991577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:43:53.991577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wjN4kh6Ozot8ebrquxHp6L/qMp0pbqyVTTmUOsaYr+Vtq6ndmRhfpXDQ53hKTdn8DcKdv1LudC5AnlGiRqjTDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:43:53.992046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.13492","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33ae5720ab8acc122ee4b43a32a3d6233a5e35d000ad449884e92d0722778663","sha256:20a6e57c87d6d9746c0b1b4bf93a5e6a41d767e8fea6755c68e65c55e0e738b2"],"state_sha256":"794d617f78e94ba3092095ea0c29e5979798431f42e1cef6bec8d27a5cbc8ba3"}