{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:AP7RABF2AESQOG322QPYQER6SU","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":"723b4ed37d3fc5d6a2adb333f9c17ffd4a9f68d054e20ba843125846d4f078d2","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-18T13:46:56Z","title_canon_sha256":"58da9db0d382a88bb473d7dfd148be16e396c0a41e1af726bab78d5b2eecdf95"},"schema_version":"1.0","source":{"id":"2209.08569","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.08569","created_at":"2026-07-05T04:58:43Z"},{"alias_kind":"arxiv_version","alias_value":"2209.08569v1","created_at":"2026-07-05T04:58:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08569","created_at":"2026-07-05T04:58:43Z"},{"alias_kind":"pith_short_12","alias_value":"AP7RABF2AESQ","created_at":"2026-07-05T04:58:43Z"},{"alias_kind":"pith_short_16","alias_value":"AP7RABF2AESQOG32","created_at":"2026-07-05T04:58:43Z"},{"alias_kind":"pith_short_8","alias_value":"AP7RABF2","created_at":"2026-07-05T04:58:43Z"}],"graph_snapshots":[{"event_id":"sha256:12d50d000386eafbe9b2aedd30e4685e3c44e248bd85fa810171ce0acc9509a8","target":"graph","created_at":"2026-07-05T04:58:43Z","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/2209.08569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent efforts of multimodal Transformers have improved Visually Rich Document Understanding (VrDU) tasks via incorporating visual and textual information. However, existing approaches mainly focus on fine-grained elements such as words and document image patches, making it hard for them to learn from coarse-grained elements, including natural lexical units like phrases and salient visual regions like prominent image regions. In this paper, we attach more importance to coarse-grained elements containing high-density information and consistent semantics, which are valuable for document understa","authors_text":"Bin Luo, Dianhai Yu, Qianglong Chen, Qiming Peng, Shikun Feng, Weichong Yin, Wenjin Wang, Yinxu Pan, Yin Zhang, Yu Sun, Zhengjie Huang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-18T13:46:56Z","title":"ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08569","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":"sha256:33484f19b7ab4ab67920ea899ccd2b3896e2acf73298e799cc0652ec521fccd2","target":"record","created_at":"2026-07-05T04:58:43Z","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":"723b4ed37d3fc5d6a2adb333f9c17ffd4a9f68d054e20ba843125846d4f078d2","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-18T13:46:56Z","title_canon_sha256":"58da9db0d382a88bb473d7dfd148be16e396c0a41e1af726bab78d5b2eecdf95"},"schema_version":"1.0","source":{"id":"2209.08569","kind":"arxiv","version":1}},"canonical_sha256":"03ff1004ba0125071b7ad41f88123e9514cbfd04ee11fc2b59dad7ab2f9ff8b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03ff1004ba0125071b7ad41f88123e9514cbfd04ee11fc2b59dad7ab2f9ff8b7","first_computed_at":"2026-07-05T04:58:43.120763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:58:43.120763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I2eDJBJCsEZeC5iYHlLPKacZWEtfEO+O2YZC/wzMG5M5q4uaqhn4d399DXC/0S1/ibTMhH/qHVU/72uCNRBODA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:58:43.121142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.08569","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33484f19b7ab4ab67920ea899ccd2b3896e2acf73298e799cc0652ec521fccd2","sha256:12d50d000386eafbe9b2aedd30e4685e3c44e248bd85fa810171ce0acc9509a8"],"state_sha256":"97d3dbd328edd34d83d23695efb19b33b9e36ed310115093e247014c31feb8dd"}