{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YTGA3MKNZH2KP5EDQT37HWHEE2","short_pith_number":"pith:YTGA3MKN","schema_version":"1.0","canonical_sha256":"c4cc0db14dc9f4a7f48384f7f3d8e4269933f9accb4d6365660bd37b58fa82a5","source":{"kind":"arxiv","id":"2411.15858","version":2},"attestation_state":"computed","paper":{"title":"SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caiyan Jia, Hongtao Xie, Yongkun Du, Yu-Gang Jiang, Zhineng Chen","submitted_at":"2024-11-24T14:21:35Z","abstract_excerpt":"Connectionist temporal classification (CTC)-based scene text recognition (STR) methods, e.g., SVTR, are widely employed in OCR applications, mainly due to their simple architecture, which only contains a visual model and a CTC-aligned linear classifier, and therefore fast inference. However, they generally exhibit worse accuracy than encoder-decoder-based methods (EDTRs) due to struggling with text irregularity and linguistic missing. To address these challenges, we propose SVTRv2, a CTC model endowed with the ability to handle text irregularities and model linguistic context. First, a multi-s"},"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":"2411.15858","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-24T14:21:35Z","cross_cats_sorted":[],"title_canon_sha256":"46a1d2baeab6d05a3f6f7d381b39d8f93d619b58ae6fe468b75fb208c3575a64","abstract_canon_sha256":"96184b8b71bb47101b0ac7ffab9ad08e69d4a0a0afc18dfbde23f42cec28d2d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:12.450654Z","signature_b64":"QVMutqnEUXLuzWsaXWPNHaYV0M+3305NGrJPj+hMC1TXXpJW9tb7xEB9A+j0WULjexai43j2k4uufAqsuDYnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4cc0db14dc9f4a7f48384f7f3d8e4269933f9accb4d6365660bd37b58fa82a5","last_reissued_at":"2026-07-05T11:37:12.450031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:12.450031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caiyan Jia, Hongtao Xie, Yongkun Du, Yu-Gang Jiang, Zhineng Chen","submitted_at":"2024-11-24T14:21:35Z","abstract_excerpt":"Connectionist temporal classification (CTC)-based scene text recognition (STR) methods, e.g., SVTR, are widely employed in OCR applications, mainly due to their simple architecture, which only contains a visual model and a CTC-aligned linear classifier, and therefore fast inference. However, they generally exhibit worse accuracy than encoder-decoder-based methods (EDTRs) due to struggling with text irregularity and linguistic missing. To address these challenges, we propose SVTRv2, a CTC model endowed with the ability to handle text irregularities and model linguistic context. First, a multi-s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15858","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/2411.15858/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":"2411.15858","created_at":"2026-07-05T11:37:12.450102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15858v2","created_at":"2026-07-05T11:37:12.450102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15858","created_at":"2026-07-05T11:37:12.450102+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTGA3MKNZH2K","created_at":"2026-07-05T11:37:12.450102+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTGA3MKNZH2KP5ED","created_at":"2026-07-05T11:37:12.450102+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTGA3MKN","created_at":"2026-07-05T11:37:12.450102+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11730","citing_title":"Seeing the Signs: A Survey of Edge-Deployable OCR Models for Billboard Visibility Analysis","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTGA3MKNZH2KP5EDQT37HWHEE2","json":"https://pith.science/pith/YTGA3MKNZH2KP5EDQT37HWHEE2.json","graph_json":"https://pith.science/api/pith-number/YTGA3MKNZH2KP5EDQT37HWHEE2/graph.json","events_json":"https://pith.science/api/pith-number/YTGA3MKNZH2KP5EDQT37HWHEE2/events.json","paper":"https://pith.science/paper/YTGA3MKN"},"agent_actions":{"view_html":"https://pith.science/pith/YTGA3MKNZH2KP5EDQT37HWHEE2","download_json":"https://pith.science/pith/YTGA3MKNZH2KP5EDQT37HWHEE2.json","view_paper":"https://pith.science/paper/YTGA3MKN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15858&json=true","fetch_graph":"https://pith.science/api/pith-number/YTGA3MKNZH2KP5EDQT37HWHEE2/graph.json","fetch_events":"https://pith.science/api/pith-number/YTGA3MKNZH2KP5EDQT37HWHEE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTGA3MKNZH2KP5EDQT37HWHEE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTGA3MKNZH2KP5EDQT37HWHEE2/action/storage_attestation","attest_author":"https://pith.science/pith/YTGA3MKNZH2KP5EDQT37HWHEE2/action/author_attestation","sign_citation":"https://pith.science/pith/YTGA3MKNZH2KP5EDQT37HWHEE2/action/citation_signature","submit_replication":"https://pith.science/pith/YTGA3MKNZH2KP5EDQT37HWHEE2/action/replication_record"}},"created_at":"2026-07-05T11:37:12.450102+00:00","updated_at":"2026-07-05T11:37:12.450102+00:00"}