{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ADJUEHKZLTLOVQDCFEPPX3J3YL","short_pith_number":"pith:ADJUEHKZ","schema_version":"1.0","canonical_sha256":"00d3421d595cd6eac062291efbed3bc2eb437667df5367c298ab9e2eec514bce","source":{"kind":"arxiv","id":"1909.07808","version":2},"attestation_state":"computed","paper":{"title":"Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Errui Ding, Jiaming Liu, Jingtuo Liu, Junyu Han, Wei Liu, Yipeng Sun","submitted_at":"2019-09-17T13:54:24Z","abstract_excerpt":"Most existing text reading benchmarks make it difficult to evaluate the performance of more advanced deep learning models in large vocabularies due to the limited amount of training data. To address this issue, we introduce a new large-scale text reading benchmark dataset named Chinese Street View Text (C-SVT) with 430,000 street view images, which is at least 14 times as large as the existing Chinese text reading benchmarks. To recognize Chinese text in the wild while keeping large-scale datasets labeling cost-effective, we propose to annotate one part of the CSVT dataset (30,000 images) in l"},"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":"1909.07808","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-17T13:54:24Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"46f9270c7bb1e0f75be901816b08d9e37c03e6bfd746d68521e371b4467a6c91","abstract_canon_sha256":"d5bcb1b8748a3352c2e40c39d23fe35f60ed16ec8e4c6ed0a91c0010d9e83dbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:25.480016Z","signature_b64":"rbLk8TM4IvH+qnKoEUXEvAM5HarZfvyuO9M9CT1GXbdC1S+AdiuvqZI2a9QcLzd8dYvnRij06L6AT0An9QuNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00d3421d595cd6eac062291efbed3bc2eb437667df5367c298ab9e2eec514bce","last_reissued_at":"2026-07-05T00:40:25.479571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:25.479571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Errui Ding, Jiaming Liu, Jingtuo Liu, Junyu Han, Wei Liu, Yipeng Sun","submitted_at":"2019-09-17T13:54:24Z","abstract_excerpt":"Most existing text reading benchmarks make it difficult to evaluate the performance of more advanced deep learning models in large vocabularies due to the limited amount of training data. To address this issue, we introduce a new large-scale text reading benchmark dataset named Chinese Street View Text (C-SVT) with 430,000 street view images, which is at least 14 times as large as the existing Chinese text reading benchmarks. To recognize Chinese text in the wild while keeping large-scale datasets labeling cost-effective, we propose to annotate one part of the CSVT dataset (30,000 images) in l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.07808","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/1909.07808/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":"1909.07808","created_at":"2026-07-05T00:40:25.479628+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.07808v2","created_at":"2026-07-05T00:40:25.479628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.07808","created_at":"2026-07-05T00:40:25.479628+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADJUEHKZLTLO","created_at":"2026-07-05T00:40:25.479628+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADJUEHKZLTLOVQDC","created_at":"2026-07-05T00:40:25.479628+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADJUEHKZ","created_at":"2026-07-05T00:40:25.479628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.00321","citing_title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","ref_index":95,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADJUEHKZLTLOVQDCFEPPX3J3YL","json":"https://pith.science/pith/ADJUEHKZLTLOVQDCFEPPX3J3YL.json","graph_json":"https://pith.science/api/pith-number/ADJUEHKZLTLOVQDCFEPPX3J3YL/graph.json","events_json":"https://pith.science/api/pith-number/ADJUEHKZLTLOVQDCFEPPX3J3YL/events.json","paper":"https://pith.science/paper/ADJUEHKZ"},"agent_actions":{"view_html":"https://pith.science/pith/ADJUEHKZLTLOVQDCFEPPX3J3YL","download_json":"https://pith.science/pith/ADJUEHKZLTLOVQDCFEPPX3J3YL.json","view_paper":"https://pith.science/paper/ADJUEHKZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.07808&json=true","fetch_graph":"https://pith.science/api/pith-number/ADJUEHKZLTLOVQDCFEPPX3J3YL/graph.json","fetch_events":"https://pith.science/api/pith-number/ADJUEHKZLTLOVQDCFEPPX3J3YL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADJUEHKZLTLOVQDCFEPPX3J3YL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADJUEHKZLTLOVQDCFEPPX3J3YL/action/storage_attestation","attest_author":"https://pith.science/pith/ADJUEHKZLTLOVQDCFEPPX3J3YL/action/author_attestation","sign_citation":"https://pith.science/pith/ADJUEHKZLTLOVQDCFEPPX3J3YL/action/citation_signature","submit_replication":"https://pith.science/pith/ADJUEHKZLTLOVQDCFEPPX3J3YL/action/replication_record"}},"created_at":"2026-07-05T00:40:25.479628+00:00","updated_at":"2026-07-05T00:40:25.479628+00:00"}