{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:3GOV67KQDJBWQ3CTG2K2X24VYZ","short_pith_number":"pith:3GOV67KQ","schema_version":"1.0","canonical_sha256":"d99d5f7d501a43686c533695abeb95c66d22e92a38b8faf7f5a381ae394cab88","source":{"kind":"arxiv","id":"1406.2227","version":4},"attestation_state":"computed","paper":{"title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Karen Simonyan, Max Jaderberg","submitted_at":"2014-06-09T15:53:33Z","abstract_excerpt":"In this work we present a framework for the recognition of natural scene text. Our framework does not require any human-labelled data, and performs word recognition on the whole image holistically, departing from the character based recognition systems of the past. The deep neural network models at the centre of this framework are trained solely on data produced by a synthetic text generation engine -- synthetic data that is highly realistic and sufficient to replace real data, giving us infinite amounts of training data. This excess of data exposes new possibilities for word recognition model"},"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":"1406.2227","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-06-09T15:53:33Z","cross_cats_sorted":[],"title_canon_sha256":"00c516f2f0cb267633506ca3bd7ecf7e23f1240b35e9716738ff60a7e72c0a4c","abstract_canon_sha256":"ce2fbdbf7b0959d7bf5872f96ab7d3855578b3cf70a48a4963cdc5ef5994c676"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:31:47.276092Z","signature_b64":"dxBiT+Q9+jkz7ZoRp6/ElIGIDAUDO8wItNtRQ2fYSFVJwBeE5ReG1MqR3Jsz79MrSK9G3Py/30bRg1PE31D7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d99d5f7d501a43686c533695abeb95c66d22e92a38b8faf7f5a381ae394cab88","last_reissued_at":"2026-05-18T02:31:47.275301Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:31:47.275301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Karen Simonyan, Max Jaderberg","submitted_at":"2014-06-09T15:53:33Z","abstract_excerpt":"In this work we present a framework for the recognition of natural scene text. Our framework does not require any human-labelled data, and performs word recognition on the whole image holistically, departing from the character based recognition systems of the past. The deep neural network models at the centre of this framework are trained solely on data produced by a synthetic text generation engine -- synthetic data that is highly realistic and sufficient to replace real data, giving us infinite amounts of training data. This excess of data exposes new possibilities for word recognition model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.2227","kind":"arxiv","version":4},"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":"1406.2227","created_at":"2026-05-18T02:31:47.275476+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.2227v4","created_at":"2026-05-18T02:31:47.275476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.2227","created_at":"2026-05-18T02:31:47.275476+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GOV67KQDJBW","created_at":"2026-05-18T12:28:11.866339+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GOV67KQDJBWQ3CT","created_at":"2026-05-18T12:28:11.866339+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GOV67KQ","created_at":"2026-05-18T12:28:11.866339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"1907.01372","citing_title":"Improving Performance of End-to-End ASR on Numeric Sequences","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"1907.04888","citing_title":"Fully Convolutional Networks for Handwriting Recognition","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09653","citing_title":"GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2410.21169","citing_title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","ref_index":92,"is_internal_anchor":true},{"citing_arxiv_id":"2305.07895","citing_title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","ref_index":112,"is_internal_anchor":true},{"citing_arxiv_id":"2205.14100","citing_title":"GIT: A Generative Image-to-text Transformer for Vision and Language","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04681","citing_title":"Batch Loss Score for Dynamic Data Pruning","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GOV67KQDJBWQ3CTG2K2X24VYZ","json":"https://pith.science/pith/3GOV67KQDJBWQ3CTG2K2X24VYZ.json","graph_json":"https://pith.science/api/pith-number/3GOV67KQDJBWQ3CTG2K2X24VYZ/graph.json","events_json":"https://pith.science/api/pith-number/3GOV67KQDJBWQ3CTG2K2X24VYZ/events.json","paper":"https://pith.science/paper/3GOV67KQ"},"agent_actions":{"view_html":"https://pith.science/pith/3GOV67KQDJBWQ3CTG2K2X24VYZ","download_json":"https://pith.science/pith/3GOV67KQDJBWQ3CTG2K2X24VYZ.json","view_paper":"https://pith.science/paper/3GOV67KQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.2227&json=true","fetch_graph":"https://pith.science/api/pith-number/3GOV67KQDJBWQ3CTG2K2X24VYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3GOV67KQDJBWQ3CTG2K2X24VYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GOV67KQDJBWQ3CTG2K2X24VYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GOV67KQDJBWQ3CTG2K2X24VYZ/action/storage_attestation","attest_author":"https://pith.science/pith/3GOV67KQDJBWQ3CTG2K2X24VYZ/action/author_attestation","sign_citation":"https://pith.science/pith/3GOV67KQDJBWQ3CTG2K2X24VYZ/action/citation_signature","submit_replication":"https://pith.science/pith/3GOV67KQDJBWQ3CTG2K2X24VYZ/action/replication_record"}},"created_at":"2026-05-18T02:31:47.275476+00:00","updated_at":"2026-05-18T02:31:47.275476+00:00"}