{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XEUGIQTVRADBLDRDUNVDBHH67W","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":"cb0402c4c4c4f391167651798e3f2ded7ba6210dd952587adbd857a6f7d79144","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-14T18:59:52Z","title_canon_sha256":"d4f8edbf7916cec27b9d7be75c95e3e0657bb10f65e0fb81c58b589220537718"},"schema_version":"1.0","source":{"id":"2211.07636","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.07636","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"2211.07636v2","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07636","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"XEUGIQTVRADB","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_16","alias_value":"XEUGIQTVRADBLDRD","created_at":"2026-07-05T05:22:12Z"},{"alias_kind":"pith_short_8","alias_value":"XEUGIQTV","created_at":"2026-07-05T05:22:12Z"}],"graph_snapshots":[{"event_id":"sha256:741e0ee4f5600f01460250192a9f12c12479de0f84a20f4fbce646405c3d407d","target":"graph","created_at":"2026-07-05T05:22:12Z","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/2211.07636/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained to reconstruct the masked out image-text aligned vision features conditioned on visible image patches. Via this pretext task, we can efficiently scale up EVA to one billion parameters, and sets new records on a broad range of representative vision downstream tasks, such as image recognition, video action recognition, object detection, instance segmentation and semantic segmentation without heavy supervised training. Moreo","authors_text":"Binhui Xie, Ledell Wu, Quan Sun, Tiejun Huang, Wen Wang, Xinggang Wang, Xinlong Wang, Yue Cao, Yuxin Fang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-14T18:59:52Z","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07636","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:b6561968d4606828add6bfbda91c6796929e5c4db3b5f165f02f59c27b1e2b25","target":"record","created_at":"2026-07-05T05:22:12Z","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":"cb0402c4c4c4f391167651798e3f2ded7ba6210dd952587adbd857a6f7d79144","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-14T18:59:52Z","title_canon_sha256":"d4f8edbf7916cec27b9d7be75c95e3e0657bb10f65e0fb81c58b589220537718"},"schema_version":"1.0","source":{"id":"2211.07636","kind":"arxiv","version":2}},"canonical_sha256":"b9286442758806158e23a36a309cfefd9eea3161b148ccbd6de3842ab9bffa67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9286442758806158e23a36a309cfefd9eea3161b148ccbd6de3842ab9bffa67","first_computed_at":"2026-07-05T05:22:12.493003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:22:12.493003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UE+XBPOynPI88nFhrWxfrI7CGEFEeFUiFMC8sy33/RkG+4O9lmD/eAJLyfWtfc/qhQMNDGg4CFgXHcUN19qXCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:22:12.493500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.07636","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6561968d4606828add6bfbda91c6796929e5c4db3b5f165f02f59c27b1e2b25","sha256:741e0ee4f5600f01460250192a9f12c12479de0f84a20f4fbce646405c3d407d"],"state_sha256":"8896fb052f32d27efa08f0406daf4ca3baa7a0d94f3585f72b91cf2657d2a356"}