{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZRBJXMXWNK55PD5CY7IECJY6Y6","short_pith_number":"pith:ZRBJXMXW","schema_version":"1.0","canonical_sha256":"cc429bb2f66abbd78fa2c7d041271ec7b1a21c6c1b05db7578aa256447cc50a3","source":{"kind":"arxiv","id":"2108.11667","version":1},"attestation_state":"computed","paper":{"title":"StackMix and Blot Augmentations for Handwritten Text Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Shonenkov, Denis Dimitrov, Denis Karachev, Mark Potanin, Maxim Novopoltsev","submitted_at":"2021-08-26T09:28:22Z","abstract_excerpt":"This paper proposes a handwritten text recognition(HTR) system that outperforms current state-of-the-artmethods. The comparison was carried out on three of themost frequently used in HTR task datasets, namely Ben-tham, IAM, and Saint Gall. In addition, the results on tworecently presented datasets, Peter the Greats manuscriptsand HKR Dataset, are provided.The paper describes the architecture of the neural net-work and two ways of increasing the volume of train-ing data: augmentation that simulates strikethrough text(HandWritten Blots) and a new text generation method(StackMix), which proved to"},"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":"2108.11667","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-26T09:28:22Z","cross_cats_sorted":[],"title_canon_sha256":"c866df1de93aca38c1d8cb8d14e144eff037a679a8a9769d011f497e0358c3bf","abstract_canon_sha256":"59adb31a8347d5cf8464f6ba00e5025132e89e31cc9f7f5198566071ead6fe7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:08.705544Z","signature_b64":"NmmNswE9twj+Qw1wDL35PZMpHFVQbAtMAtslVqe/1je4Tf+dHg6gd7zjTwOUSbDRiQmXmTDW4aZPF5RLRXVyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc429bb2f66abbd78fa2c7d041271ec7b1a21c6c1b05db7578aa256447cc50a3","last_reissued_at":"2026-07-05T03:09:08.705103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:08.705103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StackMix and Blot Augmentations for Handwritten Text Recognition","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Shonenkov, Denis Dimitrov, Denis Karachev, Mark Potanin, Maxim Novopoltsev","submitted_at":"2021-08-26T09:28:22Z","abstract_excerpt":"This paper proposes a handwritten text recognition(HTR) system that outperforms current state-of-the-artmethods. The comparison was carried out on three of themost frequently used in HTR task datasets, namely Ben-tham, IAM, and Saint Gall. In addition, the results on tworecently presented datasets, Peter the Greats manuscriptsand HKR Dataset, are provided.The paper describes the architecture of the neural net-work and two ways of increasing the volume of train-ing data: augmentation that simulates strikethrough text(HandWritten Blots) and a new text generation method(StackMix), which proved to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.11667","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/2108.11667/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":"2108.11667","created_at":"2026-07-05T03:09:08.705160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.11667v1","created_at":"2026-07-05T03:09:08.705160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.11667","created_at":"2026-07-05T03:09:08.705160+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRBJXMXWNK55","created_at":"2026-07-05T03:09:08.705160+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRBJXMXWNK55PD5C","created_at":"2026-07-05T03:09:08.705160+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRBJXMXW","created_at":"2026-07-05T03:09:08.705160+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/ZRBJXMXWNK55PD5CY7IECJY6Y6","json":"https://pith.science/pith/ZRBJXMXWNK55PD5CY7IECJY6Y6.json","graph_json":"https://pith.science/api/pith-number/ZRBJXMXWNK55PD5CY7IECJY6Y6/graph.json","events_json":"https://pith.science/api/pith-number/ZRBJXMXWNK55PD5CY7IECJY6Y6/events.json","paper":"https://pith.science/paper/ZRBJXMXW"},"agent_actions":{"view_html":"https://pith.science/pith/ZRBJXMXWNK55PD5CY7IECJY6Y6","download_json":"https://pith.science/pith/ZRBJXMXWNK55PD5CY7IECJY6Y6.json","view_paper":"https://pith.science/paper/ZRBJXMXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.11667&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRBJXMXWNK55PD5CY7IECJY6Y6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRBJXMXWNK55PD5CY7IECJY6Y6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRBJXMXWNK55PD5CY7IECJY6Y6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRBJXMXWNK55PD5CY7IECJY6Y6/action/storage_attestation","attest_author":"https://pith.science/pith/ZRBJXMXWNK55PD5CY7IECJY6Y6/action/author_attestation","sign_citation":"https://pith.science/pith/ZRBJXMXWNK55PD5CY7IECJY6Y6/action/citation_signature","submit_replication":"https://pith.science/pith/ZRBJXMXWNK55PD5CY7IECJY6Y6/action/replication_record"}},"created_at":"2026-07-05T03:09:08.705160+00:00","updated_at":"2026-07-05T03:09:08.705160+00:00"}