{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7K3P3POGXIJOLX4TEFIJU5ZJXL","short_pith_number":"pith:7K3P3POG","schema_version":"1.0","canonical_sha256":"fab6fdbdc6ba12e5df9321509a7729bafcff830bd0ec742b1757f5b4e606f6c9","source":{"kind":"arxiv","id":"1803.00085","version":1},"attestation_state":"computed","paper":{"title":"Chinese Text in the Wild","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-Jun Li, Kun Xu, Shi-Min Hu, Tai-Ling Yuan, Zhe Zhu","submitted_at":"2018-02-28T21:03:58Z","abstract_excerpt":"We introduce Chinese Text in the Wild, a very large dataset of Chinese text in street view images. While optical character recognition (OCR) in document images is well studied and many commercial tools are available, detection and recognition of text in natural images is still a challenging problem, especially for more complicated character sets such as Chinese text. Lack of training data has always been a problem, especially for deep learning methods which require massive training data.\n  In this paper we provide details of a newly created dataset of Chinese text with about 1 million Chinese "},"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":"1803.00085","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2018-02-28T21:03:58Z","cross_cats_sorted":[],"title_canon_sha256":"981d5bc750aa7fc89a103c42af1633809fde477f7c3d3e06e4b3ec8fce9f63aa","abstract_canon_sha256":"f42ebe92a87b01f8d3d13ae3addd8b52b182386f4fbe7cd3de0a40ecd8ee82ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:13.401383Z","signature_b64":"fdhgoIHJurhp57grgQaOeFdahF+beyq1GRhRg+XEo7sx0HwmsTnIIO0xWdwhZP9dsrf4RO0/y9niq+alB3TUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fab6fdbdc6ba12e5df9321509a7729bafcff830bd0ec742b1757f5b4e606f6c9","last_reissued_at":"2026-05-18T00:22:13.400733Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:13.400733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chinese Text in the Wild","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng-Jun Li, Kun Xu, Shi-Min Hu, Tai-Ling Yuan, Zhe Zhu","submitted_at":"2018-02-28T21:03:58Z","abstract_excerpt":"We introduce Chinese Text in the Wild, a very large dataset of Chinese text in street view images. While optical character recognition (OCR) in document images is well studied and many commercial tools are available, detection and recognition of text in natural images is still a challenging problem, especially for more complicated character sets such as Chinese text. Lack of training data has always been a problem, especially for deep learning methods which require massive training data.\n  In this paper we provide details of a newly created dataset of Chinese text with about 1 million Chinese "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00085","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":""},"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":"1803.00085","created_at":"2026-05-18T00:22:13.400838+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.00085v1","created_at":"2026-05-18T00:22:13.400838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00085","created_at":"2026-05-18T00:22:13.400838+00:00"},{"alias_kind":"pith_short_12","alias_value":"7K3P3POGXIJO","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7K3P3POGXIJOLX4T","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7K3P3POG","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24837","citing_title":"Zero-Shot Chinese Character Recognition with Hierarchical Multi-Granularity Image-Text Aligning","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7K3P3POGXIJOLX4TEFIJU5ZJXL","json":"https://pith.science/pith/7K3P3POGXIJOLX4TEFIJU5ZJXL.json","graph_json":"https://pith.science/api/pith-number/7K3P3POGXIJOLX4TEFIJU5ZJXL/graph.json","events_json":"https://pith.science/api/pith-number/7K3P3POGXIJOLX4TEFIJU5ZJXL/events.json","paper":"https://pith.science/paper/7K3P3POG"},"agent_actions":{"view_html":"https://pith.science/pith/7K3P3POGXIJOLX4TEFIJU5ZJXL","download_json":"https://pith.science/pith/7K3P3POGXIJOLX4TEFIJU5ZJXL.json","view_paper":"https://pith.science/paper/7K3P3POG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.00085&json=true","fetch_graph":"https://pith.science/api/pith-number/7K3P3POGXIJOLX4TEFIJU5ZJXL/graph.json","fetch_events":"https://pith.science/api/pith-number/7K3P3POGXIJOLX4TEFIJU5ZJXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7K3P3POGXIJOLX4TEFIJU5ZJXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7K3P3POGXIJOLX4TEFIJU5ZJXL/action/storage_attestation","attest_author":"https://pith.science/pith/7K3P3POGXIJOLX4TEFIJU5ZJXL/action/author_attestation","sign_citation":"https://pith.science/pith/7K3P3POGXIJOLX4TEFIJU5ZJXL/action/citation_signature","submit_replication":"https://pith.science/pith/7K3P3POGXIJOLX4TEFIJU5ZJXL/action/replication_record"}},"created_at":"2026-05-18T00:22:13.400838+00:00","updated_at":"2026-05-18T00:22:13.400838+00:00"}