{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7HRRZJLMPRQ4JHAF6DF3KZHWWS","short_pith_number":"pith:7HRRZJLM","schema_version":"1.0","canonical_sha256":"f9e31ca56c7c61c49c05f0cbb564f6b4a2e824ad40af13fa9c9416639958796b","source":{"kind":"arxiv","id":"1908.07836","version":1},"attestation_state":"computed","paper":{"title":"PubLayNet: largest dataset ever for document layout analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonio Jimeno Yepes, Jianbin Tang, Xu Zhong","submitted_at":"2019-08-16T00:40:08Z","abstract_excerpt":"Recognizing the layout of unstructured digital documents is an important step when parsing the documents into structured machine-readable format for downstream applications. Deep neural networks that are developed for computer vision have been proven to be an effective method to analyze layout of document images. However, document layout datasets that are currently publicly available are several magnitudes smaller than established computing vision datasets. Models have to be trained by transfer learning from a base model that is pre-trained on a traditional computer vision dataset. In this pap"},"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":"1908.07836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-16T00:40:08Z","cross_cats_sorted":[],"title_canon_sha256":"94dae323df3132a93f3521c92740adffa572806ba573ee31c4078624eaf12aa6","abstract_canon_sha256":"0dd734c897f16b04b7ee69ec4de432c48b5535f2ff11fd6a4a78dfe8d1ad6ac2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:01.572699Z","signature_b64":"UUrEKI0OPAib1UeSbHSeNyvAikuJfotUhNX6zXLlBKKx0O3D5ZJc15egMRouk0dtCrqnDiJLNvaeq7kYKJjRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9e31ca56c7c61c49c05f0cbb564f6b4a2e824ad40af13fa9c9416639958796b","last_reissued_at":"2026-07-04T23:59:01.572327Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:01.572327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PubLayNet: largest dataset ever for document layout analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonio Jimeno Yepes, Jianbin Tang, Xu Zhong","submitted_at":"2019-08-16T00:40:08Z","abstract_excerpt":"Recognizing the layout of unstructured digital documents is an important step when parsing the documents into structured machine-readable format for downstream applications. Deep neural networks that are developed for computer vision have been proven to be an effective method to analyze layout of document images. However, document layout datasets that are currently publicly available are several magnitudes smaller than established computing vision datasets. Models have to be trained by transfer learning from a base model that is pre-trained on a traditional computer vision dataset. In this pap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07836","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/1908.07836/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":"1908.07836","created_at":"2026-07-04T23:59:01.572388+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.07836v1","created_at":"2026-07-04T23:59:01.572388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07836","created_at":"2026-07-04T23:59:01.572388+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HRRZJLMPRQ4","created_at":"2026-07-04T23:59:01.572388+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HRRZJLMPRQ4JHAF","created_at":"2026-07-04T23:59:01.572388+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HRRZJLM","created_at":"2026-07-04T23:59:01.572388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23344","citing_title":"RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03266","citing_title":"ReforMe: Re-Shaping Documents with Contextual Prompting and Layout-Aware Propagation","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28796","citing_title":"Structure-Preserving Document Translation via Multi-Stage LLM Pipeline: A Case Study in Marathi","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11042","citing_title":"Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08115","citing_title":"Revise: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategy","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS","json":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS.json","graph_json":"https://pith.science/api/pith-number/7HRRZJLMPRQ4JHAF6DF3KZHWWS/graph.json","events_json":"https://pith.science/api/pith-number/7HRRZJLMPRQ4JHAF6DF3KZHWWS/events.json","paper":"https://pith.science/paper/7HRRZJLM"},"agent_actions":{"view_html":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS","download_json":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS.json","view_paper":"https://pith.science/paper/7HRRZJLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.07836&json=true","fetch_graph":"https://pith.science/api/pith-number/7HRRZJLMPRQ4JHAF6DF3KZHWWS/graph.json","fetch_events":"https://pith.science/api/pith-number/7HRRZJLMPRQ4JHAF6DF3KZHWWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS/action/storage_attestation","attest_author":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS/action/author_attestation","sign_citation":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS/action/citation_signature","submit_replication":"https://pith.science/pith/7HRRZJLMPRQ4JHAF6DF3KZHWWS/action/replication_record"}},"created_at":"2026-07-04T23:59:01.572388+00:00","updated_at":"2026-07-04T23:59:01.572388+00:00"}