{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CYASKRSLAQ5E5TYTLD7P3FBZYM","short_pith_number":"pith:CYASKRSL","schema_version":"1.0","canonical_sha256":"160125464b043a4ecf1358fefd9439c3051bce85fe9b8b69b6208383dff08b18","source":{"kind":"arxiv","id":"2505.00746","version":2},"attestation_state":"computed","paper":{"title":"Entropy Heat-Mapping: Localizing GPT-Based OCR Errors with Sliding-Window Shannon Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexei Kaltchenko","submitted_at":"2025-04-30T09:05:49Z","abstract_excerpt":"Vision-language models such as OpenAI GPT-4o can transcribe mathematical documents directly from images, yet their token-level confidence signals are seldom used to pinpoint local recognition mistakes. We present an entropy-heat-mapping proof-of-concept that turns per-token Shannon entropy into a visual ''uncertainty landscape''. By scanning the entropy sequence with a fixed-length sliding window, we obtain hotspots that are likely to contain OCR errors such as missing symbols, mismatched braces, or garbled prose. Using a small, curated set of scanned research pages rendered at several resolut"},"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":"2505.00746","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-30T09:05:49Z","cross_cats_sorted":[],"title_canon_sha256":"413f33aac7d3b4b03cddd3c0b7a40552ed05edd231c3d263ede0ba0b7ae804c6","abstract_canon_sha256":"03ea36e6089aab5fa47e6a2e51361320f1a9a0bc0bcdd56f360369d7a3640ada"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:47.846647Z","signature_b64":"cgK2DFqeTRcP2iyTjiU/yvM3nbKthCqS/1clYLn9qv8QWHmaHlXj7h8MqnEMs9WTyw+QMHjw+K0gD2rPzIYECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"160125464b043a4ecf1358fefd9439c3051bce85fe9b8b69b6208383dff08b18","last_reissued_at":"2026-07-05T10:58:47.846136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:47.846136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entropy Heat-Mapping: Localizing GPT-Based OCR Errors with Sliding-Window Shannon Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexei Kaltchenko","submitted_at":"2025-04-30T09:05:49Z","abstract_excerpt":"Vision-language models such as OpenAI GPT-4o can transcribe mathematical documents directly from images, yet their token-level confidence signals are seldom used to pinpoint local recognition mistakes. We present an entropy-heat-mapping proof-of-concept that turns per-token Shannon entropy into a visual ''uncertainty landscape''. By scanning the entropy sequence with a fixed-length sliding window, we obtain hotspots that are likely to contain OCR errors such as missing symbols, mismatched braces, or garbled prose. Using a small, curated set of scanned research pages rendered at several resolut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00746","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/2505.00746/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":"2505.00746","created_at":"2026-07-05T10:58:47.846198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00746v2","created_at":"2026-07-05T10:58:47.846198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00746","created_at":"2026-07-05T10:58:47.846198+00:00"},{"alias_kind":"pith_short_12","alias_value":"CYASKRSLAQ5E","created_at":"2026-07-05T10:58:47.846198+00:00"},{"alias_kind":"pith_short_16","alias_value":"CYASKRSLAQ5E5TYT","created_at":"2026-07-05T10:58:47.846198+00:00"},{"alias_kind":"pith_short_8","alias_value":"CYASKRSL","created_at":"2026-07-05T10:58:47.846198+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/CYASKRSLAQ5E5TYTLD7P3FBZYM","json":"https://pith.science/pith/CYASKRSLAQ5E5TYTLD7P3FBZYM.json","graph_json":"https://pith.science/api/pith-number/CYASKRSLAQ5E5TYTLD7P3FBZYM/graph.json","events_json":"https://pith.science/api/pith-number/CYASKRSLAQ5E5TYTLD7P3FBZYM/events.json","paper":"https://pith.science/paper/CYASKRSL"},"agent_actions":{"view_html":"https://pith.science/pith/CYASKRSLAQ5E5TYTLD7P3FBZYM","download_json":"https://pith.science/pith/CYASKRSLAQ5E5TYTLD7P3FBZYM.json","view_paper":"https://pith.science/paper/CYASKRSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00746&json=true","fetch_graph":"https://pith.science/api/pith-number/CYASKRSLAQ5E5TYTLD7P3FBZYM/graph.json","fetch_events":"https://pith.science/api/pith-number/CYASKRSLAQ5E5TYTLD7P3FBZYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CYASKRSLAQ5E5TYTLD7P3FBZYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CYASKRSLAQ5E5TYTLD7P3FBZYM/action/storage_attestation","attest_author":"https://pith.science/pith/CYASKRSLAQ5E5TYTLD7P3FBZYM/action/author_attestation","sign_citation":"https://pith.science/pith/CYASKRSLAQ5E5TYTLD7P3FBZYM/action/citation_signature","submit_replication":"https://pith.science/pith/CYASKRSLAQ5E5TYTLD7P3FBZYM/action/replication_record"}},"created_at":"2026-07-05T10:58:47.846198+00:00","updated_at":"2026-07-05T10:58:47.846198+00:00"}