{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CHNOCESL3X3QDATFQ63FT5IZVV","short_pith_number":"pith:CHNOCESL","schema_version":"1.0","canonical_sha256":"11dae1124bddf701826587b659f519ad7e821909413d81271aa9d9556a4bd5e6","source":{"kind":"arxiv","id":"2607.22200","version":1},"attestation_state":"computed","paper":{"title":"LayoutLite: Token-Level Implicit Layout Analysis for Efficient Document OCR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bicheng Wan, Xudong Liu, Yulin Jin","submitted_at":"2026-07-24T11:13:44Z","abstract_excerpt":"End-to-end OCR systems based on vision-language models have achieved strong performance in complex document OCR, but their efficiency is limited by the large number of visual tokens produced from document images. Many of these tokens correspond to blank margins or visually redundant regions, yet directly applying generic visual token compression methods may remove OCR-critical fine-grained details. In this paper, we propose LayoutLite, a lightweight plug-and-play module for efficient document OCR. Instead of relying on explicit document layout detection, LayoutLite performs implicit layout ana"},"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":"2607.22200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T11:13:44Z","cross_cats_sorted":[],"title_canon_sha256":"b258929730fabd1d49b93e5219b64b8b11db9928867c69da848a7150bb823a37","abstract_canon_sha256":"0d59403e93ddcc959858c577e691ab73e2eb302f9f7206e6c0a54e442e649379"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:53.557071Z","signature_b64":"0DhgH55M1KmcZ0PacLxNuG3cwZetAhSleyG1N8PFh5vrzBELtkkAi3wFroHzjz3Fo1KrAlq7HI3LKSGGBB1RBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11dae1124bddf701826587b659f519ad7e821909413d81271aa9d9556a4bd5e6","last_reissued_at":"2026-07-27T01:20:53.556229Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:53.556229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LayoutLite: Token-Level Implicit Layout Analysis for Efficient Document OCR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bicheng Wan, Xudong Liu, Yulin Jin","submitted_at":"2026-07-24T11:13:44Z","abstract_excerpt":"End-to-end OCR systems based on vision-language models have achieved strong performance in complex document OCR, but their efficiency is limited by the large number of visual tokens produced from document images. Many of these tokens correspond to blank margins or visually redundant regions, yet directly applying generic visual token compression methods may remove OCR-critical fine-grained details. In this paper, we propose LayoutLite, a lightweight plug-and-play module for efficient document OCR. Instead of relying on explicit document layout detection, LayoutLite performs implicit layout ana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22200","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/2607.22200/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":"2607.22200","created_at":"2026-07-27T01:20:53.556667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22200v1","created_at":"2026-07-27T01:20:53.556667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22200","created_at":"2026-07-27T01:20:53.556667+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHNOCESL3X3Q","created_at":"2026-07-27T01:20:53.556667+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHNOCESL3X3QDATF","created_at":"2026-07-27T01:20:53.556667+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHNOCESL","created_at":"2026-07-27T01:20:53.556667+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/CHNOCESL3X3QDATFQ63FT5IZVV","json":"https://pith.science/pith/CHNOCESL3X3QDATFQ63FT5IZVV.json","graph_json":"https://pith.science/api/pith-number/CHNOCESL3X3QDATFQ63FT5IZVV/graph.json","events_json":"https://pith.science/api/pith-number/CHNOCESL3X3QDATFQ63FT5IZVV/events.json","paper":"https://pith.science/paper/CHNOCESL"},"agent_actions":{"view_html":"https://pith.science/pith/CHNOCESL3X3QDATFQ63FT5IZVV","download_json":"https://pith.science/pith/CHNOCESL3X3QDATFQ63FT5IZVV.json","view_paper":"https://pith.science/paper/CHNOCESL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22200&json=true","fetch_graph":"https://pith.science/api/pith-number/CHNOCESL3X3QDATFQ63FT5IZVV/graph.json","fetch_events":"https://pith.science/api/pith-number/CHNOCESL3X3QDATFQ63FT5IZVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHNOCESL3X3QDATFQ63FT5IZVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHNOCESL3X3QDATFQ63FT5IZVV/action/storage_attestation","attest_author":"https://pith.science/pith/CHNOCESL3X3QDATFQ63FT5IZVV/action/author_attestation","sign_citation":"https://pith.science/pith/CHNOCESL3X3QDATFQ63FT5IZVV/action/citation_signature","submit_replication":"https://pith.science/pith/CHNOCESL3X3QDATFQ63FT5IZVV/action/replication_record"}},"created_at":"2026-07-27T01:20:53.556667+00:00","updated_at":"2026-07-27T01:20:53.556667+00:00"}