{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5IA5JMEIIZRAY32S63VOXPUTIY","short_pith_number":"pith:5IA5JMEI","schema_version":"1.0","canonical_sha256":"ea01d4b08846620c6f52f6eaebbe934612ff6b53ff66788ece13c5abc9e1fb48","source":{"kind":"arxiv","id":"2507.11730","version":1},"attestation_state":"computed","paper":{"title":"Seeing the Signs: A Survey of Edge-Deployable OCR Models for Billboard Visibility Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lihang Ying, Maciej Szankin, Vidhyananth Venkatasamy","submitted_at":"2025-07-15T20:58:24Z","abstract_excerpt":"Outdoor advertisements remain a critical medium for modern marketing, yet accurately verifying billboard text visibility under real-world conditions is still challenging. Traditional Optical Character Recognition (OCR) pipelines excel at cropped text recognition but often struggle with complex outdoor scenes, varying fonts, and weather-induced visual noise. Recently, multimodal Vision-Language Models (VLMs) have emerged as promising alternatives, offering end-to-end scene understanding with no explicit detection step. This work systematically benchmarks representative VLMs - including Qwen 2.5"},"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":"2507.11730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-15T20:58:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2da49ee633f03aec3d4e3a31023d85daca423dc4fcd50c8e7dde2d10b2aecb2","abstract_canon_sha256":"256cafcc6e98720353ccada52f39338e2378925247ce03b61e29b6debe2887af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:49.499367Z","signature_b64":"ajID9IOFz89GgR00/GH1H+rEg5RDvWhI8DfPJzZ8yBpeXG7GbRLGuktf6L3+2rPC0dNOJYuHzl3XDw+p2pGyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea01d4b08846620c6f52f6eaebbe934612ff6b53ff66788ece13c5abc9e1fb48","last_reissued_at":"2026-07-05T11:37:49.498806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:49.498806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing the Signs: A Survey of Edge-Deployable OCR Models for Billboard Visibility Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Lihang Ying, Maciej Szankin, Vidhyananth Venkatasamy","submitted_at":"2025-07-15T20:58:24Z","abstract_excerpt":"Outdoor advertisements remain a critical medium for modern marketing, yet accurately verifying billboard text visibility under real-world conditions is still challenging. Traditional Optical Character Recognition (OCR) pipelines excel at cropped text recognition but often struggle with complex outdoor scenes, varying fonts, and weather-induced visual noise. Recently, multimodal Vision-Language Models (VLMs) have emerged as promising alternatives, offering end-to-end scene understanding with no explicit detection step. This work systematically benchmarks representative VLMs - including Qwen 2.5"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11730","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/2507.11730/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":"2507.11730","created_at":"2026-07-05T11:37:49.498869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.11730v1","created_at":"2026-07-05T11:37:49.498869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11730","created_at":"2026-07-05T11:37:49.498869+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IA5JMEIIZRA","created_at":"2026-07-05T11:37:49.498869+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IA5JMEIIZRAY32S","created_at":"2026-07-05T11:37:49.498869+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IA5JMEI","created_at":"2026-07-05T11:37:49.498869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03884","citing_title":"BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language Models","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IA5JMEIIZRAY32S63VOXPUTIY","json":"https://pith.science/pith/5IA5JMEIIZRAY32S63VOXPUTIY.json","graph_json":"https://pith.science/api/pith-number/5IA5JMEIIZRAY32S63VOXPUTIY/graph.json","events_json":"https://pith.science/api/pith-number/5IA5JMEIIZRAY32S63VOXPUTIY/events.json","paper":"https://pith.science/paper/5IA5JMEI"},"agent_actions":{"view_html":"https://pith.science/pith/5IA5JMEIIZRAY32S63VOXPUTIY","download_json":"https://pith.science/pith/5IA5JMEIIZRAY32S63VOXPUTIY.json","view_paper":"https://pith.science/paper/5IA5JMEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.11730&json=true","fetch_graph":"https://pith.science/api/pith-number/5IA5JMEIIZRAY32S63VOXPUTIY/graph.json","fetch_events":"https://pith.science/api/pith-number/5IA5JMEIIZRAY32S63VOXPUTIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IA5JMEIIZRAY32S63VOXPUTIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IA5JMEIIZRAY32S63VOXPUTIY/action/storage_attestation","attest_author":"https://pith.science/pith/5IA5JMEIIZRAY32S63VOXPUTIY/action/author_attestation","sign_citation":"https://pith.science/pith/5IA5JMEIIZRAY32S63VOXPUTIY/action/citation_signature","submit_replication":"https://pith.science/pith/5IA5JMEIIZRAY32S63VOXPUTIY/action/replication_record"}},"created_at":"2026-07-05T11:37:49.498869+00:00","updated_at":"2026-07-05T11:37:49.498869+00:00"}