{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BRBG3Z43APBZ6OIMESZVLQRXYY","short_pith_number":"pith:BRBG3Z43","schema_version":"1.0","canonical_sha256":"0c426de79b03c39f390c24b355c237c6132817f1b2fd4c592bf22f4e0dc0ccce","source":{"kind":"arxiv","id":"2105.05300","version":2},"attestation_state":"computed","paper":{"title":"One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alicia Forn\\'es, Ali Furkan Biten, Dimosthenis Karatzas, Josep Llad\\'os, Lluis Gomez, Mohamed Ali Souibgui, Sounak Dey, Yousri Kessentini","submitted_at":"2021-05-11T18:53:01Z","abstract_excerpt":"Low resource Handwritten Text Recognition (HTR) is a hard problem due to the scarce annotated data and the very limited linguistic information (dictionaries and language models). For example, in the case of historical ciphered manuscripts, which are usually written with invented alphabets to hide the message contents. Thus, in this paper we address this problem through a data generation technique based on Bayesian Program Learning (BPL). Contrary to traditional generation approaches, which require a huge amount of annotated images, our method is able to generate human-like handwriting using on"},"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":"2105.05300","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-11T18:53:01Z","cross_cats_sorted":[],"title_canon_sha256":"f61ebd396fc3b8cb580ece6cb47902d6e9de59a22a8fa0c2f2318027d8ceb9c0","abstract_canon_sha256":"3b5895fcee1abbfc172b073588be08f3fe7b35db79f83b55056ec58412cbaec0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:02.060865Z","signature_b64":"pVrHuRzwncn10VwJiKJer5E1P97uveVbaUc3iJa6KKcQaJEv2aI20tOPGNQLknvLFvZirvXfexUM5F9c35FTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c426de79b03c39f390c24b355c237c6132817f1b2fd4c592bf22f4e0dc0ccce","last_reissued_at":"2026-07-05T03:20:02.060055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:02.060055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alicia Forn\\'es, Ali Furkan Biten, Dimosthenis Karatzas, Josep Llad\\'os, Lluis Gomez, Mohamed Ali Souibgui, Sounak Dey, Yousri Kessentini","submitted_at":"2021-05-11T18:53:01Z","abstract_excerpt":"Low resource Handwritten Text Recognition (HTR) is a hard problem due to the scarce annotated data and the very limited linguistic information (dictionaries and language models). For example, in the case of historical ciphered manuscripts, which are usually written with invented alphabets to hide the message contents. Thus, in this paper we address this problem through a data generation technique based on Bayesian Program Learning (BPL). Contrary to traditional generation approaches, which require a huge amount of annotated images, our method is able to generate human-like handwriting using on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.05300","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/2105.05300/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":"2105.05300","created_at":"2026-07-05T03:20:02.060450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.05300v2","created_at":"2026-07-05T03:20:02.060450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.05300","created_at":"2026-07-05T03:20:02.060450+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRBG3Z43APBZ","created_at":"2026-07-05T03:20:02.060450+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRBG3Z43APBZ6OIM","created_at":"2026-07-05T03:20:02.060450+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRBG3Z43","created_at":"2026-07-05T03:20:02.060450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06275","citing_title":"Advancing Offline Handwritten Text Recognition: A Systematic Review of Data Augmentation and Generation Techniques","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRBG3Z43APBZ6OIMESZVLQRXYY","json":"https://pith.science/pith/BRBG3Z43APBZ6OIMESZVLQRXYY.json","graph_json":"https://pith.science/api/pith-number/BRBG3Z43APBZ6OIMESZVLQRXYY/graph.json","events_json":"https://pith.science/api/pith-number/BRBG3Z43APBZ6OIMESZVLQRXYY/events.json","paper":"https://pith.science/paper/BRBG3Z43"},"agent_actions":{"view_html":"https://pith.science/pith/BRBG3Z43APBZ6OIMESZVLQRXYY","download_json":"https://pith.science/pith/BRBG3Z43APBZ6OIMESZVLQRXYY.json","view_paper":"https://pith.science/paper/BRBG3Z43","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.05300&json=true","fetch_graph":"https://pith.science/api/pith-number/BRBG3Z43APBZ6OIMESZVLQRXYY/graph.json","fetch_events":"https://pith.science/api/pith-number/BRBG3Z43APBZ6OIMESZVLQRXYY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRBG3Z43APBZ6OIMESZVLQRXYY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRBG3Z43APBZ6OIMESZVLQRXYY/action/storage_attestation","attest_author":"https://pith.science/pith/BRBG3Z43APBZ6OIMESZVLQRXYY/action/author_attestation","sign_citation":"https://pith.science/pith/BRBG3Z43APBZ6OIMESZVLQRXYY/action/citation_signature","submit_replication":"https://pith.science/pith/BRBG3Z43APBZ6OIMESZVLQRXYY/action/replication_record"}},"created_at":"2026-07-05T03:20:02.060450+00:00","updated_at":"2026-07-05T03:20:02.060450+00:00"}