{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UUGBJ4ILREBRUPPMWRWEWSHYJA","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":"fd8f57a83a0eb1a2db59a98dfed28cf1153bb2e88803f9fe49a7b60477f54e9b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T07:32:51Z","title_canon_sha256":"1562cfc3c8db87a76837e86ff464b1d9fd1b0e5c6c2f5291a3177b766cf98015"},"schema_version":"1.0","source":{"id":"2303.00289","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00289","created_at":"2026-07-05T05:47:07Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00289v1","created_at":"2026-07-05T05:47:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00289","created_at":"2026-07-05T05:47:07Z"},{"alias_kind":"pith_short_12","alias_value":"UUGBJ4ILREBR","created_at":"2026-07-05T05:47:07Z"},{"alias_kind":"pith_short_16","alias_value":"UUGBJ4ILREBRUPPM","created_at":"2026-07-05T05:47:07Z"},{"alias_kind":"pith_short_8","alias_value":"UUGBJ4IL","created_at":"2026-07-05T05:47:07Z"}],"graph_snapshots":[{"event_id":"sha256:c20ae00fa4565ba1f6c3c655e6199a185f81fffa40dfe17f61a3673930669f11","target":"graph","created_at":"2026-07-05T05:47:07Z","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/2303.00289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present StrucTexTv2, an effective document image pre-training framework, by performing masked visual-textual prediction. It consists of two self-supervised pre-training tasks: masked image modeling and masked language modeling, based on text region-level image masking. The proposed method randomly masks some image regions according to the bounding box coordinates of text words. The objectives of our pre-training tasks are reconstructing the pixels of masked image regions and the corresponding masked tokens simultaneously. Hence the pre-trained encoder can capture more textual","authors_text":"Chengquan Zhang, Errui Ding, Jingdong Wang, Junyu Han, Kun Yao, Xiameng Qin, Xiaoqiang Zhang, Yuechen Yu, Yulin Li, Zengyuan Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T07:32:51Z","title":"StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00289","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":"sha256:543216f9b1e81cd953a65d750fad8450178de5157de61e5c1c58ab09a50792cc","target":"record","created_at":"2026-07-05T05:47:07Z","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":"fd8f57a83a0eb1a2db59a98dfed28cf1153bb2e88803f9fe49a7b60477f54e9b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T07:32:51Z","title_canon_sha256":"1562cfc3c8db87a76837e86ff464b1d9fd1b0e5c6c2f5291a3177b766cf98015"},"schema_version":"1.0","source":{"id":"2303.00289","kind":"arxiv","version":1}},"canonical_sha256":"a50c14f10b89031a3decb46c4b48f8480b2e83d661bb02e1c0ac53c66c9422c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a50c14f10b89031a3decb46c4b48f8480b2e83d661bb02e1c0ac53c66c9422c7","first_computed_at":"2026-07-05T05:47:07.591484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:07.591484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g/smLKNi4XI9Pv1o/CKKVUGUYAQLcQ3dk++tXVzUyF9sg8RsrrPpKNbjbS3sTAkGvjtU7sue6g/RpB6mjwiSBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:07.591848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.00289","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:543216f9b1e81cd953a65d750fad8450178de5157de61e5c1c58ab09a50792cc","sha256:c20ae00fa4565ba1f6c3c655e6199a185f81fffa40dfe17f61a3673930669f11"],"state_sha256":"17151164f12dcf31adb1898b8c4a4f8187d7be9754cb7da02d2c7886f0c4c2de"}