{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HJYWEOO3LGJF2NK26ECSYYRSRW","short_pith_number":"pith:HJYWEOO3","schema_version":"1.0","canonical_sha256":"3a716239db59925d355af1052c62328d92133f2c8cd0be96e9c1c77a5b046015","source":{"kind":"arxiv","id":"2606.29213","version":1},"attestation_state":"computed","paper":{"title":"Can OCR-VLMs Read Devanagari? A Stress-Test Benchmark and Post-Correction Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Aditya Pratap Singh","submitted_at":"2026-06-28T05:46:05Z","abstract_excerpt":"OCR systems, ranging from classical engines to specialised OCR vision-language models (OCR-VLMs) and frontier multimodal LLMs, report strong results on English and Chinese document benchmarks, yet their behaviour on Indic scripts is largely uncharacterised. We benchmark ten systems on Devanagari (Hindi): classical EasyOCR; open VLMs (Qwen2.5-VL-3B, Qwen3-VL-8B, olmOCR-7B); specialised OCR-VLMs (DeepSeek-OCR, Unlimited-OCR); and frontier closed models (Gemini 2.5 Flash, Claude Opus 4.7, GPT-5.5, Mistral OCR), across four synthetic degradation conditions and 300 real printed scans. We report fou"},"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":"2606.29213","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-28T05:46:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"0733e890b922ed32064614c287e2ae9c20a9bdc4047c6b1ba07e5d9fc501fa1f","abstract_canon_sha256":"840d2f1f0995e75f3a8c1a0b7ce3ca47e05d2aa3aee141e2780f00c81a7f5595"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:57.464400Z","signature_b64":"7ASE+9zibkqx9ZoC1knfxznEo33kbPJtaFXFZ4yS83tCzk0IxjtRQD0+fxK97nGZiV+Q8KDX6RwdYarAPatdDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a716239db59925d355af1052c62328d92133f2c8cd0be96e9c1c77a5b046015","last_reissued_at":"2026-06-30T01:17:57.463943Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:57.463943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can OCR-VLMs Read Devanagari? A Stress-Test Benchmark and Post-Correction Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Aditya Pratap Singh","submitted_at":"2026-06-28T05:46:05Z","abstract_excerpt":"OCR systems, ranging from classical engines to specialised OCR vision-language models (OCR-VLMs) and frontier multimodal LLMs, report strong results on English and Chinese document benchmarks, yet their behaviour on Indic scripts is largely uncharacterised. We benchmark ten systems on Devanagari (Hindi): classical EasyOCR; open VLMs (Qwen2.5-VL-3B, Qwen3-VL-8B, olmOCR-7B); specialised OCR-VLMs (DeepSeek-OCR, Unlimited-OCR); and frontier closed models (Gemini 2.5 Flash, Claude Opus 4.7, GPT-5.5, Mistral OCR), across four synthetic degradation conditions and 300 real printed scans. We report fou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29213","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/2606.29213/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":"2606.29213","created_at":"2026-06-30T01:17:57.464013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29213v1","created_at":"2026-06-30T01:17:57.464013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29213","created_at":"2026-06-30T01:17:57.464013+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJYWEOO3LGJF","created_at":"2026-06-30T01:17:57.464013+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJYWEOO3LGJF2NK2","created_at":"2026-06-30T01:17:57.464013+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJYWEOO3","created_at":"2026-06-30T01:17:57.464013+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/HJYWEOO3LGJF2NK26ECSYYRSRW","json":"https://pith.science/pith/HJYWEOO3LGJF2NK26ECSYYRSRW.json","graph_json":"https://pith.science/api/pith-number/HJYWEOO3LGJF2NK26ECSYYRSRW/graph.json","events_json":"https://pith.science/api/pith-number/HJYWEOO3LGJF2NK26ECSYYRSRW/events.json","paper":"https://pith.science/paper/HJYWEOO3"},"agent_actions":{"view_html":"https://pith.science/pith/HJYWEOO3LGJF2NK26ECSYYRSRW","download_json":"https://pith.science/pith/HJYWEOO3LGJF2NK26ECSYYRSRW.json","view_paper":"https://pith.science/paper/HJYWEOO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29213&json=true","fetch_graph":"https://pith.science/api/pith-number/HJYWEOO3LGJF2NK26ECSYYRSRW/graph.json","fetch_events":"https://pith.science/api/pith-number/HJYWEOO3LGJF2NK26ECSYYRSRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJYWEOO3LGJF2NK26ECSYYRSRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJYWEOO3LGJF2NK26ECSYYRSRW/action/storage_attestation","attest_author":"https://pith.science/pith/HJYWEOO3LGJF2NK26ECSYYRSRW/action/author_attestation","sign_citation":"https://pith.science/pith/HJYWEOO3LGJF2NK26ECSYYRSRW/action/citation_signature","submit_replication":"https://pith.science/pith/HJYWEOO3LGJF2NK26ECSYYRSRW/action/replication_record"}},"created_at":"2026-06-30T01:17:57.464013+00:00","updated_at":"2026-06-30T01:17:57.464013+00:00"}