{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5VGHJETJJO7IXLYDPBCZC3JMRF","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":"17865445fcdc26ef1bf18c2815f17f121b39afcaf06508cdec8ab71117b77691","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-01T08:27:19Z","title_canon_sha256":"6a10620bd80e1aab1b0a8b4cac21631e828037d1f99b88be7fa0823c2f3347c2"},"schema_version":"1.0","source":{"id":"2206.00311","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00311","created_at":"2026-07-05T06:58:53Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00311v3","created_at":"2026-07-05T06:58:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00311","created_at":"2026-07-05T06:58:53Z"},{"alias_kind":"pith_short_12","alias_value":"5VGHJETJJO7I","created_at":"2026-07-05T06:58:53Z"},{"alias_kind":"pith_short_16","alias_value":"5VGHJETJJO7IXLYD","created_at":"2026-07-05T06:58:53Z"},{"alias_kind":"pith_short_8","alias_value":"5VGHJETJ","created_at":"2026-07-05T06:58:53Z"}],"graph_snapshots":[{"event_id":"sha256:8ed1dbd65d5154e5400b70e249737a04f7771d40dcf8857dcc9d3f3b924fe118","target":"graph","created_at":"2026-07-05T06:58:53Z","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/2206.00311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text images contain both visual and linguistic information. However, existing pre-training techniques for text recognition mainly focus on either visual representation learning or linguistic knowledge learning. In this paper, we propose a novel approach MaskOCR to unify vision and language pre-training in the classical encoder-decoder recognition framework. We adopt the masked image modeling approach to pre-train the feature encoder using a large set of unlabeled real text images, which allows us to learn strong visual representations. In contrast to introducing linguistic knowledge with an ad","authors_text":"Chengquan Zhang, Errui Ding, Jingdong Wang, Junyu Han, Kun Yao, Liang Wu, Meina Qiao, Pengyuan Lyu, Shanshan Liu, Yangliu Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-01T08:27:19Z","title":"MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00311","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":"sha256:834be41025df4ead4d4c6798c0c037ab7303efda76f449813dfad1fffe63dc25","target":"record","created_at":"2026-07-05T06:58:53Z","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":"17865445fcdc26ef1bf18c2815f17f121b39afcaf06508cdec8ab71117b77691","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-01T08:27:19Z","title_canon_sha256":"6a10620bd80e1aab1b0a8b4cac21631e828037d1f99b88be7fa0823c2f3347c2"},"schema_version":"1.0","source":{"id":"2206.00311","kind":"arxiv","version":3}},"canonical_sha256":"ed4c7492694bbe8baf037845916d2c8944355a6688946d0f1708b262174947e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed4c7492694bbe8baf037845916d2c8944355a6688946d0f1708b262174947e1","first_computed_at":"2026-07-05T06:58:53.006609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:53.006609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CE5t307Tod4uKTMOu7cbCMeZa7vgd0pnUhwe3SmnDtb0URwSmOozbewKbqwsNOQc/0GpoUJSp+d/vPhaKyteCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:53.007145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.00311","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:834be41025df4ead4d4c6798c0c037ab7303efda76f449813dfad1fffe63dc25","sha256:8ed1dbd65d5154e5400b70e249737a04f7771d40dcf8857dcc9d3f3b924fe118"],"state_sha256":"6e80890c8b5ba34596d0ff9b9b03672442baa3ea63a315c82f159899ab08563b"}