{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7IU22GAJHCQSCFBUDETJM7UL2S","short_pith_number":"pith:7IU22GAJ","schema_version":"1.0","canonical_sha256":"fa29ad180938a12114341926967e8bd4a7376e1abf07c5cdf1d00f8df201f947","source":{"kind":"arxiv","id":"2208.06079","version":2},"attestation_state":"computed","paper":{"title":"Character decomposition to resolve class imbalance problem in Hangul OCR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Geonuk Kim, Jaemin Son, Jaesik Min, Kanghyu Lee","submitted_at":"2022-08-12T01:35:17Z","abstract_excerpt":"We present a novel approach to OCR(Optical Character Recognition) of Korean character, Hangul. As a phonogram, Hangul can represent 11,172 different characters with only 52 graphemes, by describing each character with a combination of the graphemes. As the total number of the characters could overwhelm the capacity of a neural network, the existing OCR encoding methods pre-define a smaller set of characters that are frequently used. This design choice naturally compromises the performance on long-tailed characters in the distribution. In this work, we demonstrate that grapheme encoding is not "},"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":"2208.06079","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-12T01:35:17Z","cross_cats_sorted":[],"title_canon_sha256":"c8b8078ae3208f222a919e28fe05b25d6adb3c768993af37e3a4c2f11fefcdd9","abstract_canon_sha256":"9920346543d591d02f7d274f3627e566ba02b0644b3803838174d61802e43d32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:40.402137Z","signature_b64":"z/NfGkP3lfH8k/II3al+aStPxVyjbPcXXVV7BE/k0fYLfSCuR9pxUg1FibGvxSCr7OmSB861kFv03UdN1YfUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa29ad180938a12114341926967e8bd4a7376e1abf07c5cdf1d00f8df201f947","last_reissued_at":"2026-07-05T05:01:40.401645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:40.401645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Character decomposition to resolve class imbalance problem in Hangul OCR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Geonuk Kim, Jaemin Son, Jaesik Min, Kanghyu Lee","submitted_at":"2022-08-12T01:35:17Z","abstract_excerpt":"We present a novel approach to OCR(Optical Character Recognition) of Korean character, Hangul. As a phonogram, Hangul can represent 11,172 different characters with only 52 graphemes, by describing each character with a combination of the graphemes. As the total number of the characters could overwhelm the capacity of a neural network, the existing OCR encoding methods pre-define a smaller set of characters that are frequently used. This design choice naturally compromises the performance on long-tailed characters in the distribution. In this work, we demonstrate that grapheme encoding is not "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06079","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/2208.06079/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":"2208.06079","created_at":"2026-07-05T05:01:40.401706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.06079v2","created_at":"2026-07-05T05:01:40.401706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06079","created_at":"2026-07-05T05:01:40.401706+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IU22GAJHCQS","created_at":"2026-07-05T05:01:40.401706+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IU22GAJHCQSCFBU","created_at":"2026-07-05T05:01:40.401706+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IU22GAJ","created_at":"2026-07-05T05:01:40.401706+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/7IU22GAJHCQSCFBUDETJM7UL2S","json":"https://pith.science/pith/7IU22GAJHCQSCFBUDETJM7UL2S.json","graph_json":"https://pith.science/api/pith-number/7IU22GAJHCQSCFBUDETJM7UL2S/graph.json","events_json":"https://pith.science/api/pith-number/7IU22GAJHCQSCFBUDETJM7UL2S/events.json","paper":"https://pith.science/paper/7IU22GAJ"},"agent_actions":{"view_html":"https://pith.science/pith/7IU22GAJHCQSCFBUDETJM7UL2S","download_json":"https://pith.science/pith/7IU22GAJHCQSCFBUDETJM7UL2S.json","view_paper":"https://pith.science/paper/7IU22GAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.06079&json=true","fetch_graph":"https://pith.science/api/pith-number/7IU22GAJHCQSCFBUDETJM7UL2S/graph.json","fetch_events":"https://pith.science/api/pith-number/7IU22GAJHCQSCFBUDETJM7UL2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IU22GAJHCQSCFBUDETJM7UL2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IU22GAJHCQSCFBUDETJM7UL2S/action/storage_attestation","attest_author":"https://pith.science/pith/7IU22GAJHCQSCFBUDETJM7UL2S/action/author_attestation","sign_citation":"https://pith.science/pith/7IU22GAJHCQSCFBUDETJM7UL2S/action/citation_signature","submit_replication":"https://pith.science/pith/7IU22GAJHCQSCFBUDETJM7UL2S/action/replication_record"}},"created_at":"2026-07-05T05:01:40.401706+00:00","updated_at":"2026-07-05T05:01:40.401706+00:00"}