{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AP7RABF2AESQOG322QPYQER6SU","short_pith_number":"pith:AP7RABF2","schema_version":"1.0","canonical_sha256":"03ff1004ba0125071b7ad41f88123e9514cbfd04ee11fc2b59dad7ab2f9ff8b7","source":{"kind":"arxiv","id":"2209.08569","version":1},"attestation_state":"computed","paper":{"title":"ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bin Luo, Dianhai Yu, Qianglong Chen, Qiming Peng, Shikun Feng, Weichong Yin, Wenjin Wang, Yinxu Pan, Yin Zhang, Yu Sun, Zhengjie Huang","submitted_at":"2022-09-18T13:46:56Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.08569","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-18T13:46:56Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"58da9db0d382a88bb473d7dfd148be16e396c0a41e1af726bab78d5b2eecdf95","abstract_canon_sha256":"723b4ed37d3fc5d6a2adb333f9c17ffd4a9f68d054e20ba843125846d4f078d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:43.121142Z","signature_b64":"I2eDJBJCsEZeC5iYHlLPKacZWEtfEO+O2YZC/wzMG5M5q4uaqhn4d399DXC/0S1/ibTMhH/qHVU/72uCNRBODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03ff1004ba0125071b7ad41f88123e9514cbfd04ee11fc2b59dad7ab2f9ff8b7","last_reissued_at":"2026-07-05T04:58:43.120763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:43.120763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bin Luo, Dianhai Yu, Qianglong Chen, Qiming Peng, Shikun Feng, Weichong Yin, Wenjin Wang, Yinxu Pan, Yin Zhang, Yu Sun, Zhengjie Huang","submitted_at":"2022-09-18T13:46:56Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08569","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.08569/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.08569","created_at":"2026-07-05T04:58:43.120818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.08569v1","created_at":"2026-07-05T04:58:43.120818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08569","created_at":"2026-07-05T04:58:43.120818+00:00"},{"alias_kind":"pith_short_12","alias_value":"AP7RABF2AESQ","created_at":"2026-07-05T04:58:43.120818+00:00"},{"alias_kind":"pith_short_16","alias_value":"AP7RABF2AESQOG32","created_at":"2026-07-05T04:58:43.120818+00:00"},{"alias_kind":"pith_short_8","alias_value":"AP7RABF2","created_at":"2026-07-05T04:58:43.120818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AP7RABF2AESQOG322QPYQER6SU","json":"https://pith.science/pith/AP7RABF2AESQOG322QPYQER6SU.json","graph_json":"https://pith.science/api/pith-number/AP7RABF2AESQOG322QPYQER6SU/graph.json","events_json":"https://pith.science/api/pith-number/AP7RABF2AESQOG322QPYQER6SU/events.json","paper":"https://pith.science/paper/AP7RABF2"},"agent_actions":{"view_html":"https://pith.science/pith/AP7RABF2AESQOG322QPYQER6SU","download_json":"https://pith.science/pith/AP7RABF2AESQOG322QPYQER6SU.json","view_paper":"https://pith.science/paper/AP7RABF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.08569&json=true","fetch_graph":"https://pith.science/api/pith-number/AP7RABF2AESQOG322QPYQER6SU/graph.json","fetch_events":"https://pith.science/api/pith-number/AP7RABF2AESQOG322QPYQER6SU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AP7RABF2AESQOG322QPYQER6SU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AP7RABF2AESQOG322QPYQER6SU/action/storage_attestation","attest_author":"https://pith.science/pith/AP7RABF2AESQOG322QPYQER6SU/action/author_attestation","sign_citation":"https://pith.science/pith/AP7RABF2AESQOG322QPYQER6SU/action/citation_signature","submit_replication":"https://pith.science/pith/AP7RABF2AESQOG322QPYQER6SU/action/replication_record"}},"created_at":"2026-07-05T04:58:43.120818+00:00","updated_at":"2026-07-05T04:58:43.120818+00:00"}