{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GCBLWQKOQ5CCUHK7XPBD4BA4ID","short_pith_number":"pith:GCBLWQKO","schema_version":"1.0","canonical_sha256":"3082bb414e87442a1d5fbbc23e041c40faa3b2b37b58c34ed9efa95fd46b1787","source":{"kind":"arxiv","id":"2608.03884","version":1},"attestation_state":"computed","paper":{"title":"BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Eshat Tanzeem, Mir Md Inzamam, Sadab Shiper, Tawsif Tashwar Dipto","submitted_at":"2026-08-04T16:20:53Z","abstract_excerpt":"In-the-wild Bengali scene text recognition is largely unmeasured: existing resources target handwritten documents or constrained sign-board parsing, report only aggregate edit-distance metrics, and evaluate either conventional OCR or VLMs, never both on the same in-the-wild data. To address this gap, we introduce BANGLAWILD, a benchmark of 2,535 Bengali scene text images, each paired with a verbatim gold transcription, two categorical axes, four diagnostic attributes, and an orthographically standard form where the in-image text deviates from canonical spelling. We evaluate fifteen VLMs and th"},"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":"2608.03884","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T16:20:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b9f29d2676d1a37ed74d43bf25e3526a8dc6d4839b89973e68fad562cf5dea07","abstract_canon_sha256":"22b39955b4b700fc587c4a1dd67d8f42d231d14e9b0a5687b3f766f310696d9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:19.141796Z","signature_b64":"7nNeQ0Jtfu68vRNXTimWkpKnZHwzm5nhF3LN3v7MQpwrcvhJmjTKzUNfg5dC6LghTDfJ7z6YXkGBE8YdTF1iDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3082bb414e87442a1d5fbbc23e041c40faa3b2b37b58c34ed9efa95fd46b1787","last_reissued_at":"2026-08-05T01:37:19.140373Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:19.140373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Eshat Tanzeem, Mir Md Inzamam, Sadab Shiper, Tawsif Tashwar Dipto","submitted_at":"2026-08-04T16:20:53Z","abstract_excerpt":"In-the-wild Bengali scene text recognition is largely unmeasured: existing resources target handwritten documents or constrained sign-board parsing, report only aggregate edit-distance metrics, and evaluate either conventional OCR or VLMs, never both on the same in-the-wild data. To address this gap, we introduce BANGLAWILD, a benchmark of 2,535 Bengali scene text images, each paired with a verbatim gold transcription, two categorical axes, four diagnostic attributes, and an orthographically standard form where the in-image text deviates from canonical spelling. We evaluate fifteen VLMs and th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03884","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/2608.03884/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":"2608.03884","created_at":"2026-08-05T01:37:19.140849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03884v1","created_at":"2026-08-05T01:37:19.140849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03884","created_at":"2026-08-05T01:37:19.140849+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCBLWQKOQ5CC","created_at":"2026-08-05T01:37:19.140849+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCBLWQKOQ5CCUHK7","created_at":"2026-08-05T01:37:19.140849+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCBLWQKO","created_at":"2026-08-05T01:37:19.140849+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/GCBLWQKOQ5CCUHK7XPBD4BA4ID","json":"https://pith.science/pith/GCBLWQKOQ5CCUHK7XPBD4BA4ID.json","graph_json":"https://pith.science/api/pith-number/GCBLWQKOQ5CCUHK7XPBD4BA4ID/graph.json","events_json":"https://pith.science/api/pith-number/GCBLWQKOQ5CCUHK7XPBD4BA4ID/events.json","paper":"https://pith.science/paper/GCBLWQKO"},"agent_actions":{"view_html":"https://pith.science/pith/GCBLWQKOQ5CCUHK7XPBD4BA4ID","download_json":"https://pith.science/pith/GCBLWQKOQ5CCUHK7XPBD4BA4ID.json","view_paper":"https://pith.science/paper/GCBLWQKO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03884&json=true","fetch_graph":"https://pith.science/api/pith-number/GCBLWQKOQ5CCUHK7XPBD4BA4ID/graph.json","fetch_events":"https://pith.science/api/pith-number/GCBLWQKOQ5CCUHK7XPBD4BA4ID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCBLWQKOQ5CCUHK7XPBD4BA4ID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCBLWQKOQ5CCUHK7XPBD4BA4ID/action/storage_attestation","attest_author":"https://pith.science/pith/GCBLWQKOQ5CCUHK7XPBD4BA4ID/action/author_attestation","sign_citation":"https://pith.science/pith/GCBLWQKOQ5CCUHK7XPBD4BA4ID/action/citation_signature","submit_replication":"https://pith.science/pith/GCBLWQKOQ5CCUHK7XPBD4BA4ID/action/replication_record"}},"created_at":"2026-08-05T01:37:19.140849+00:00","updated_at":"2026-08-05T01:37:19.140849+00:00"}