{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RNT7SGTSF7EU2XB6UAXQNEMZQA","short_pith_number":"pith:RNT7SGTS","schema_version":"1.0","canonical_sha256":"8b67f91a722fc94d5c3ea02f069199802287b0d8b8eb1fa2b29e6e42ef8c8002","source":{"kind":"arxiv","id":"2112.07395","version":1},"attestation_state":"computed","paper":{"title":"Handwritten text generation and strikethrough characters augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Shonenkov, Andrey Chertok, Denis Dimitrov, Denis Karachev, Mark Potanin, Max Novopoltsev","submitted_at":"2021-12-14T13:41:10Z","abstract_excerpt":"We introduce two data augmentation techniques, which, used with a Resnet-BiLSTM-CTC network, significantly reduce Word Error Rate (WER) and Character Error Rate (CER) beyond best-reported results on handwriting text recognition (HTR) tasks. We apply a novel augmentation that simulates strikethrough text (HandWritten Blots) and a handwritten text generation method based on printed text (StackMix), which proved to be very effective in HTR tasks. StackMix uses weakly-supervised framework to get character boundaries. Because these data augmentation techniques are independent of the network used, t"},"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":"2112.07395","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T13:41:10Z","cross_cats_sorted":[],"title_canon_sha256":"9febb01de6cd2f15791f3175d352e35dcd989a16a48debd1bd5619eea7c821cc","abstract_canon_sha256":"1c8df22318aa76f048b0d4a33bdfffc750cc2a81eb095e089f77688097c31e9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:40:57.589485Z","signature_b64":"4VGxsBqq8aa+u1a44ThRapWSh5zTOcCONWJhBXrNLsdmdMNyHiBkeynaM5+OHEfmFwgQ86Ykai1XLsq0QoFGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b67f91a722fc94d5c3ea02f069199802287b0d8b8eb1fa2b29e6e42ef8c8002","last_reissued_at":"2026-07-05T03:40:57.589044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:40:57.589044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Handwritten text generation and strikethrough characters augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Shonenkov, Andrey Chertok, Denis Dimitrov, Denis Karachev, Mark Potanin, Max Novopoltsev","submitted_at":"2021-12-14T13:41:10Z","abstract_excerpt":"We introduce two data augmentation techniques, which, used with a Resnet-BiLSTM-CTC network, significantly reduce Word Error Rate (WER) and Character Error Rate (CER) beyond best-reported results on handwriting text recognition (HTR) tasks. We apply a novel augmentation that simulates strikethrough text (HandWritten Blots) and a handwritten text generation method based on printed text (StackMix), which proved to be very effective in HTR tasks. StackMix uses weakly-supervised framework to get character boundaries. Because these data augmentation techniques are independent of the network used, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07395","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/2112.07395/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":"2112.07395","created_at":"2026-07-05T03:40:57.589098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.07395v1","created_at":"2026-07-05T03:40:57.589098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07395","created_at":"2026-07-05T03:40:57.589098+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNT7SGTSF7EU","created_at":"2026-07-05T03:40:57.589098+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNT7SGTSF7EU2XB6","created_at":"2026-07-05T03:40:57.589098+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNT7SGTS","created_at":"2026-07-05T03:40:57.589098+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/RNT7SGTSF7EU2XB6UAXQNEMZQA","json":"https://pith.science/pith/RNT7SGTSF7EU2XB6UAXQNEMZQA.json","graph_json":"https://pith.science/api/pith-number/RNT7SGTSF7EU2XB6UAXQNEMZQA/graph.json","events_json":"https://pith.science/api/pith-number/RNT7SGTSF7EU2XB6UAXQNEMZQA/events.json","paper":"https://pith.science/paper/RNT7SGTS"},"agent_actions":{"view_html":"https://pith.science/pith/RNT7SGTSF7EU2XB6UAXQNEMZQA","download_json":"https://pith.science/pith/RNT7SGTSF7EU2XB6UAXQNEMZQA.json","view_paper":"https://pith.science/paper/RNT7SGTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.07395&json=true","fetch_graph":"https://pith.science/api/pith-number/RNT7SGTSF7EU2XB6UAXQNEMZQA/graph.json","fetch_events":"https://pith.science/api/pith-number/RNT7SGTSF7EU2XB6UAXQNEMZQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNT7SGTSF7EU2XB6UAXQNEMZQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNT7SGTSF7EU2XB6UAXQNEMZQA/action/storage_attestation","attest_author":"https://pith.science/pith/RNT7SGTSF7EU2XB6UAXQNEMZQA/action/author_attestation","sign_citation":"https://pith.science/pith/RNT7SGTSF7EU2XB6UAXQNEMZQA/action/citation_signature","submit_replication":"https://pith.science/pith/RNT7SGTSF7EU2XB6UAXQNEMZQA/action/replication_record"}},"created_at":"2026-07-05T03:40:57.589098+00:00","updated_at":"2026-07-05T03:40:57.589098+00:00"}