{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:S45OEBDEW56FEEPVSZUMFS62P7","short_pith_number":"pith:S45OEBDE","schema_version":"1.0","canonical_sha256":"973ae20464b77c5211f59668c2cbda7ff7d0717526bde721dd19461b2cca602d","source":{"kind":"arxiv","id":"1903.00277","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Generation of Handwritten Text Images Conditioned on Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bastien Moysset, Eloi Alonso, Ronaldo Messina","submitted_at":"2019-03-01T13:11:44Z","abstract_excerpt":"State-of-the-art offline handwriting text recognition systems tend to use neural networks and therefore require a large amount of annotated data to be trained. In order to partially satisfy this requirement, we propose a system based on Generative Adversarial Networks (GAN) to produce synthetic images of handwritten words. We use bidirectional LSTM recurrent layers to get an embedding of the word to be rendered, and we feed it to the generator network. We also modify the standard GAN by adding an auxiliary network for text recognition. The system is then trained with a balanced combination of "},"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":"1903.00277","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-01T13:11:44Z","cross_cats_sorted":[],"title_canon_sha256":"ec5af3b9652af2e4c905ff98bbcaa5865a73f8379ab9663c215223649ba67de5","abstract_canon_sha256":"643a7c64ba4b8048159192958fe1619ac15b3a9e541157e8ffab7417c9f6f101"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:56.764846Z","signature_b64":"+Bj/IAuYy9Ib7fWh/LzABxX16GXLF2xYB+xDJrYcIVVIOJHdfFlh4UdSMO7FBmC3aHLbrUPBl7saKid7p0DrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"973ae20464b77c5211f59668c2cbda7ff7d0717526bde721dd19461b2cca602d","last_reissued_at":"2026-07-05T01:50:56.764308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:56.764308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Generation of Handwritten Text Images Conditioned on Sequences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bastien Moysset, Eloi Alonso, Ronaldo Messina","submitted_at":"2019-03-01T13:11:44Z","abstract_excerpt":"State-of-the-art offline handwriting text recognition systems tend to use neural networks and therefore require a large amount of annotated data to be trained. In order to partially satisfy this requirement, we propose a system based on Generative Adversarial Networks (GAN) to produce synthetic images of handwritten words. We use bidirectional LSTM recurrent layers to get an embedding of the word to be rendered, and we feed it to the generator network. We also modify the standard GAN by adding an auxiliary network for text recognition. The system is then trained with a balanced combination of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00277","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1903.00277/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":"1903.00277","created_at":"2026-07-05T01:50:56.764386+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.00277v1","created_at":"2026-07-05T01:50:56.764386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00277","created_at":"2026-07-05T01:50:56.764386+00:00"},{"alias_kind":"pith_short_12","alias_value":"S45OEBDEW56F","created_at":"2026-07-05T01:50:56.764386+00:00"},{"alias_kind":"pith_short_16","alias_value":"S45OEBDEW56FEEPV","created_at":"2026-07-05T01:50:56.764386+00:00"},{"alias_kind":"pith_short_8","alias_value":"S45OEBDE","created_at":"2026-07-05T01:50:56.764386+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/S45OEBDEW56FEEPVSZUMFS62P7","json":"https://pith.science/pith/S45OEBDEW56FEEPVSZUMFS62P7.json","graph_json":"https://pith.science/api/pith-number/S45OEBDEW56FEEPVSZUMFS62P7/graph.json","events_json":"https://pith.science/api/pith-number/S45OEBDEW56FEEPVSZUMFS62P7/events.json","paper":"https://pith.science/paper/S45OEBDE"},"agent_actions":{"view_html":"https://pith.science/pith/S45OEBDEW56FEEPVSZUMFS62P7","download_json":"https://pith.science/pith/S45OEBDEW56FEEPVSZUMFS62P7.json","view_paper":"https://pith.science/paper/S45OEBDE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.00277&json=true","fetch_graph":"https://pith.science/api/pith-number/S45OEBDEW56FEEPVSZUMFS62P7/graph.json","fetch_events":"https://pith.science/api/pith-number/S45OEBDEW56FEEPVSZUMFS62P7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S45OEBDEW56FEEPVSZUMFS62P7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S45OEBDEW56FEEPVSZUMFS62P7/action/storage_attestation","attest_author":"https://pith.science/pith/S45OEBDEW56FEEPVSZUMFS62P7/action/author_attestation","sign_citation":"https://pith.science/pith/S45OEBDEW56FEEPVSZUMFS62P7/action/citation_signature","submit_replication":"https://pith.science/pith/S45OEBDEW56FEEPVSZUMFS62P7/action/replication_record"}},"created_at":"2026-07-05T01:50:56.764386+00:00","updated_at":"2026-07-05T01:50:56.764386+00:00"}