{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UHK7I6WWMCYC6PYWQ4DHDMFDXQ","short_pith_number":"pith:UHK7I6WW","schema_version":"1.0","canonical_sha256":"a1d5f47ad660b02f3f16870671b0a3bc394026b3c8a058440cd4abd3a012110d","source":{"kind":"arxiv","id":"1809.08675","version":2},"attestation_state":"computed","paper":{"title":"Learning to Read by Spelling: Towards Unsupervised Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Ankush Gupta","submitted_at":"2018-09-23T20:53:41Z","abstract_excerpt":"This work presents a method for visual text recognition without using any paired supervisory data. We formulate the text recognition task as one of aligning the conditional distribution of strings predicted from given text images, with lexically valid strings sampled from target corpora. This enables fully automated, and unsupervised learning from just line-level text-images, and unpaired text-string samples, obviating the need for large aligned datasets. We present detailed analysis for various aspects of the proposed method, namely - (1) impact of the length of training sequences on converge"},"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":"1809.08675","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-23T20:53:41Z","cross_cats_sorted":[],"title_canon_sha256":"93778aa3d7010e56394f1dbd1cc791ac17aa6f7842d67fd169dea26e1bb7fba1","abstract_canon_sha256":"49fe02772ca01bf24669d9359ed12285f308f2e9eb77f682cf51e62378ff576d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:47.517785Z","signature_b64":"3e4x3vCnoxrviuMWNMAg3Uo/e4ora5HHjnAKnjqeCgBWE56xhV5QTOlnf920SoWQDukd56vlcrOPFwQcrXLUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1d5f47ad660b02f3f16870671b0a3bc394026b3c8a058440cd4abd3a012110d","last_reissued_at":"2026-05-17T23:58:47.517337Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:47.517337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Read by Spelling: Towards Unsupervised Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Ankush Gupta","submitted_at":"2018-09-23T20:53:41Z","abstract_excerpt":"This work presents a method for visual text recognition without using any paired supervisory data. We formulate the text recognition task as one of aligning the conditional distribution of strings predicted from given text images, with lexically valid strings sampled from target corpora. This enables fully automated, and unsupervised learning from just line-level text-images, and unpaired text-string samples, obviating the need for large aligned datasets. We present detailed analysis for various aspects of the proposed method, namely - (1) impact of the length of training sequences on converge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.08675","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":""},"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":"1809.08675","created_at":"2026-05-17T23:58:47.517412+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.08675v2","created_at":"2026-05-17T23:58:47.517412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.08675","created_at":"2026-05-17T23:58:47.517412+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHK7I6WWMCYC","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHK7I6WWMCYC6PYW","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHK7I6WW","created_at":"2026-05-18T12:32:56.356000+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/UHK7I6WWMCYC6PYWQ4DHDMFDXQ","json":"https://pith.science/pith/UHK7I6WWMCYC6PYWQ4DHDMFDXQ.json","graph_json":"https://pith.science/api/pith-number/UHK7I6WWMCYC6PYWQ4DHDMFDXQ/graph.json","events_json":"https://pith.science/api/pith-number/UHK7I6WWMCYC6PYWQ4DHDMFDXQ/events.json","paper":"https://pith.science/paper/UHK7I6WW"},"agent_actions":{"view_html":"https://pith.science/pith/UHK7I6WWMCYC6PYWQ4DHDMFDXQ","download_json":"https://pith.science/pith/UHK7I6WWMCYC6PYWQ4DHDMFDXQ.json","view_paper":"https://pith.science/paper/UHK7I6WW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.08675&json=true","fetch_graph":"https://pith.science/api/pith-number/UHK7I6WWMCYC6PYWQ4DHDMFDXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UHK7I6WWMCYC6PYWQ4DHDMFDXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHK7I6WWMCYC6PYWQ4DHDMFDXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHK7I6WWMCYC6PYWQ4DHDMFDXQ/action/storage_attestation","attest_author":"https://pith.science/pith/UHK7I6WWMCYC6PYWQ4DHDMFDXQ/action/author_attestation","sign_citation":"https://pith.science/pith/UHK7I6WWMCYC6PYWQ4DHDMFDXQ/action/citation_signature","submit_replication":"https://pith.science/pith/UHK7I6WWMCYC6PYWQ4DHDMFDXQ/action/replication_record"}},"created_at":"2026-05-17T23:58:47.517412+00:00","updated_at":"2026-05-17T23:58:47.517412+00:00"}