{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JMACG4LQAAOTCTZGQD7IZJOM2X","short_pith_number":"pith:JMACG4LQ","schema_version":"1.0","canonical_sha256":"4b00237170001d314f2680fe8ca5ccd5dfd89ba70c3ee2df6b740715c0da845f","source":{"kind":"arxiv","id":"2211.03256","version":2},"attestation_state":"computed","paper":{"title":"On Web-based Visual Corpus Construction for Visual Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Donghyun Kim, Geewook Kim, Moonbin Yim, Teakgyu Hong, Yoonsik Kim","submitted_at":"2022-11-07T01:24:43Z","abstract_excerpt":"In recent years, research on visual document understanding (VDU) has grown significantly, with a particular emphasis on the development of self-supervised learning methods. However, one of the significant challenges faced in this field is the limited availability of publicly accessible visual corpora or extensive collections of images with detailed text annotations, particularly for non-Latin or resource-scarce languages. To address this challenge, we propose Web-based Visual Corpus Builder (Webvicob), a dataset generator engine capable of constructing large-scale, multilingual visual corpora "},"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":"2211.03256","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-07T01:24:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9243ce386020584db2b31cb870e9104460af03de64daaa4a348124b8e7adf4ca","abstract_canon_sha256":"aa20a9f7fa3d7eb07de430d8d5a80430a93c3a436c600eb022abeadf3cb1f78d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:05.200535Z","signature_b64":"rlz1pM1nHDC08gl/johIfS0b868C3zLKN85p+ZgKOhilpT4K6gFAkMWGF1NCODZiC5iWbwhL95Xal8fK/sGOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b00237170001d314f2680fe8ca5ccd5dfd89ba70c3ee2df6b740715c0da845f","last_reissued_at":"2026-07-05T06:06:05.200132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:05.200132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Web-based Visual Corpus Construction for Visual Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Donghyun Kim, Geewook Kim, Moonbin Yim, Teakgyu Hong, Yoonsik Kim","submitted_at":"2022-11-07T01:24:43Z","abstract_excerpt":"In recent years, research on visual document understanding (VDU) has grown significantly, with a particular emphasis on the development of self-supervised learning methods. However, one of the significant challenges faced in this field is the limited availability of publicly accessible visual corpora or extensive collections of images with detailed text annotations, particularly for non-Latin or resource-scarce languages. To address this challenge, we propose Web-based Visual Corpus Builder (Webvicob), a dataset generator engine capable of constructing large-scale, multilingual visual corpora "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03256","kind":"arxiv","version":2},"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/2211.03256/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":"2211.03256","created_at":"2026-07-05T06:06:05.200191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.03256v2","created_at":"2026-07-05T06:06:05.200191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03256","created_at":"2026-07-05T06:06:05.200191+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMACG4LQAAOT","created_at":"2026-07-05T06:06:05.200191+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMACG4LQAAOTCTZG","created_at":"2026-07-05T06:06:05.200191+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMACG4LQ","created_at":"2026-07-05T06:06:05.200191+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/JMACG4LQAAOTCTZGQD7IZJOM2X","json":"https://pith.science/pith/JMACG4LQAAOTCTZGQD7IZJOM2X.json","graph_json":"https://pith.science/api/pith-number/JMACG4LQAAOTCTZGQD7IZJOM2X/graph.json","events_json":"https://pith.science/api/pith-number/JMACG4LQAAOTCTZGQD7IZJOM2X/events.json","paper":"https://pith.science/paper/JMACG4LQ"},"agent_actions":{"view_html":"https://pith.science/pith/JMACG4LQAAOTCTZGQD7IZJOM2X","download_json":"https://pith.science/pith/JMACG4LQAAOTCTZGQD7IZJOM2X.json","view_paper":"https://pith.science/paper/JMACG4LQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.03256&json=true","fetch_graph":"https://pith.science/api/pith-number/JMACG4LQAAOTCTZGQD7IZJOM2X/graph.json","fetch_events":"https://pith.science/api/pith-number/JMACG4LQAAOTCTZGQD7IZJOM2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMACG4LQAAOTCTZGQD7IZJOM2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMACG4LQAAOTCTZGQD7IZJOM2X/action/storage_attestation","attest_author":"https://pith.science/pith/JMACG4LQAAOTCTZGQD7IZJOM2X/action/author_attestation","sign_citation":"https://pith.science/pith/JMACG4LQAAOTCTZGQD7IZJOM2X/action/citation_signature","submit_replication":"https://pith.science/pith/JMACG4LQAAOTCTZGQD7IZJOM2X/action/replication_record"}},"created_at":"2026-07-05T06:06:05.200191+00:00","updated_at":"2026-07-05T06:06:05.200191+00:00"}