{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QBPOW2PROLIJBQRTSKPE73BRPS","short_pith_number":"pith:QBPOW2PR","schema_version":"1.0","canonical_sha256":"805eeb69f172d090c233929e4fec317c8b6d4a6adeafc18571588f47eca900c1","source":{"kind":"arxiv","id":"2009.00678","version":1},"attestation_state":"computed","paper":{"title":"Text and Style Conditioned GAN for Generation of Offline Handwriting Lines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Davis, Brian Price, Bryan Morse, Chris Tensmeyer, Curtis Wigington, Rajiv Jain","submitted_at":"2020-09-01T20:19:42Z","abstract_excerpt":"This paper presents a GAN for generating images of handwritten lines conditioned on arbitrary text and latent style vectors. Unlike prior work, which produce stroke points or single-word images, this model generates entire lines of offline handwriting. The model produces variable-sized images by using style vectors to determine character widths. A generator network is trained with GAN and autoencoder techniques to learn style, and uses a pre-trained handwriting recognition network to induce legibility. A study using human evaluators demonstrates that the model produces images that appear to be"},"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":"2009.00678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-09-01T20:19:42Z","cross_cats_sorted":[],"title_canon_sha256":"2361596fbc7895053a7f37666be8c4c9d8734b46e46236e23c4d327377f8d1e6","abstract_canon_sha256":"a8ce8128271686dc91b7fc5739baba71c970fc28dafa48cc7e7833e875292ee8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:32:25.862368Z","signature_b64":"DZn4p/hDYElkSeVjQ9ueqf7EeuTL9h1eKbX/SZCRSgJyfkpemQ/GI0jtVZdv3jmhZE93G7DGyzE6adWc3wTFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"805eeb69f172d090c233929e4fec317c8b6d4a6adeafc18571588f47eca900c1","last_reissued_at":"2026-07-05T01:32:25.861922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:32:25.861922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text and Style Conditioned GAN for Generation of Offline Handwriting Lines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Davis, Brian Price, Bryan Morse, Chris Tensmeyer, Curtis Wigington, Rajiv Jain","submitted_at":"2020-09-01T20:19:42Z","abstract_excerpt":"This paper presents a GAN for generating images of handwritten lines conditioned on arbitrary text and latent style vectors. Unlike prior work, which produce stroke points or single-word images, this model generates entire lines of offline handwriting. The model produces variable-sized images by using style vectors to determine character widths. A generator network is trained with GAN and autoencoder techniques to learn style, and uses a pre-trained handwriting recognition network to induce legibility. A study using human evaluators demonstrates that the model produces images that appear to be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.00678","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/2009.00678/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":"2009.00678","created_at":"2026-07-05T01:32:25.861982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.00678v1","created_at":"2026-07-05T01:32:25.861982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.00678","created_at":"2026-07-05T01:32:25.861982+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBPOW2PROLIJ","created_at":"2026-07-05T01:32:25.861982+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBPOW2PROLIJBQRT","created_at":"2026-07-05T01:32:25.861982+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBPOW2PR","created_at":"2026-07-05T01:32:25.861982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.13285","citing_title":"SkyReels-Text: Fine-Grained Font-Controllable Text Editing for Poster Design","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QBPOW2PROLIJBQRTSKPE73BRPS","json":"https://pith.science/pith/QBPOW2PROLIJBQRTSKPE73BRPS.json","graph_json":"https://pith.science/api/pith-number/QBPOW2PROLIJBQRTSKPE73BRPS/graph.json","events_json":"https://pith.science/api/pith-number/QBPOW2PROLIJBQRTSKPE73BRPS/events.json","paper":"https://pith.science/paper/QBPOW2PR"},"agent_actions":{"view_html":"https://pith.science/pith/QBPOW2PROLIJBQRTSKPE73BRPS","download_json":"https://pith.science/pith/QBPOW2PROLIJBQRTSKPE73BRPS.json","view_paper":"https://pith.science/paper/QBPOW2PR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.00678&json=true","fetch_graph":"https://pith.science/api/pith-number/QBPOW2PROLIJBQRTSKPE73BRPS/graph.json","fetch_events":"https://pith.science/api/pith-number/QBPOW2PROLIJBQRTSKPE73BRPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBPOW2PROLIJBQRTSKPE73BRPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBPOW2PROLIJBQRTSKPE73BRPS/action/storage_attestation","attest_author":"https://pith.science/pith/QBPOW2PROLIJBQRTSKPE73BRPS/action/author_attestation","sign_citation":"https://pith.science/pith/QBPOW2PROLIJBQRTSKPE73BRPS/action/citation_signature","submit_replication":"https://pith.science/pith/QBPOW2PROLIJBQRTSKPE73BRPS/action/replication_record"}},"created_at":"2026-07-05T01:32:25.861982+00:00","updated_at":"2026-07-05T01:32:25.861982+00:00"}