{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GD3VP3LAA7QZ4AAZPVFI4HQR26","short_pith_number":"pith:GD3VP3LA","schema_version":"1.0","canonical_sha256":"30f757ed6007e19e00197d4a8e1e11d7a85ce4f818247912e909d51e52f55f34","source":{"kind":"arxiv","id":"2306.13236","version":1},"attestation_state":"computed","paper":{"title":"Document Image Cleaning using Budget-Aware Black-Box Approximation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Van Oeveren, Ganesh Tata, Katyani Singh, Nilanjan Ray","submitted_at":"2023-06-22T23:07:31Z","abstract_excerpt":"Recent work has shown that by approximating the behaviour of a non-differentiable black-box function using a neural network, the black-box can be integrated into a differentiable training pipeline for end-to-end training. This methodology is termed \"differentiable bypass,'' and a successful application of this method involves training a document preprocessor to improve the performance of a black-box OCR engine. However, a good approximation of an OCR engine requires querying it for all samples throughout the training process, which can be computationally and financially expensive. Several zero"},"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":"2306.13236","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-22T23:07:31Z","cross_cats_sorted":[],"title_canon_sha256":"6ab886bda48323f59dd599178cd791f17374ed147d1d4d82a4e40ee5498e4285","abstract_canon_sha256":"88d48f586fb370ef8ff37c2de16a484fb87aef01d04f4bc084b233d52dbc57c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:03.011366Z","signature_b64":"yirBEEAAxO/aMIcnjh+AlGkQRkZynw4YrHN/x9cZ4N0Ifkgg2nOMmLSgLeJwlB0c26Wu9nxdUx8VaVgHXYLZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30f757ed6007e19e00197d4a8e1e11d7a85ce4f818247912e909d51e52f55f34","last_reissued_at":"2026-07-05T06:24:03.010999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:03.010999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Document Image Cleaning using Budget-Aware Black-Box Approximation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Van Oeveren, Ganesh Tata, Katyani Singh, Nilanjan Ray","submitted_at":"2023-06-22T23:07:31Z","abstract_excerpt":"Recent work has shown that by approximating the behaviour of a non-differentiable black-box function using a neural network, the black-box can be integrated into a differentiable training pipeline for end-to-end training. This methodology is termed \"differentiable bypass,'' and a successful application of this method involves training a document preprocessor to improve the performance of a black-box OCR engine. However, a good approximation of an OCR engine requires querying it for all samples throughout the training process, which can be computationally and financially expensive. Several zero"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.13236","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/2306.13236/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":"2306.13236","created_at":"2026-07-05T06:24:03.011061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.13236v1","created_at":"2026-07-05T06:24:03.011061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.13236","created_at":"2026-07-05T06:24:03.011061+00:00"},{"alias_kind":"pith_short_12","alias_value":"GD3VP3LAA7QZ","created_at":"2026-07-05T06:24:03.011061+00:00"},{"alias_kind":"pith_short_16","alias_value":"GD3VP3LAA7QZ4AAZ","created_at":"2026-07-05T06:24:03.011061+00:00"},{"alias_kind":"pith_short_8","alias_value":"GD3VP3LA","created_at":"2026-07-05T06:24:03.011061+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/GD3VP3LAA7QZ4AAZPVFI4HQR26","json":"https://pith.science/pith/GD3VP3LAA7QZ4AAZPVFI4HQR26.json","graph_json":"https://pith.science/api/pith-number/GD3VP3LAA7QZ4AAZPVFI4HQR26/graph.json","events_json":"https://pith.science/api/pith-number/GD3VP3LAA7QZ4AAZPVFI4HQR26/events.json","paper":"https://pith.science/paper/GD3VP3LA"},"agent_actions":{"view_html":"https://pith.science/pith/GD3VP3LAA7QZ4AAZPVFI4HQR26","download_json":"https://pith.science/pith/GD3VP3LAA7QZ4AAZPVFI4HQR26.json","view_paper":"https://pith.science/paper/GD3VP3LA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.13236&json=true","fetch_graph":"https://pith.science/api/pith-number/GD3VP3LAA7QZ4AAZPVFI4HQR26/graph.json","fetch_events":"https://pith.science/api/pith-number/GD3VP3LAA7QZ4AAZPVFI4HQR26/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GD3VP3LAA7QZ4AAZPVFI4HQR26/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GD3VP3LAA7QZ4AAZPVFI4HQR26/action/storage_attestation","attest_author":"https://pith.science/pith/GD3VP3LAA7QZ4AAZPVFI4HQR26/action/author_attestation","sign_citation":"https://pith.science/pith/GD3VP3LAA7QZ4AAZPVFI4HQR26/action/citation_signature","submit_replication":"https://pith.science/pith/GD3VP3LAA7QZ4AAZPVFI4HQR26/action/replication_record"}},"created_at":"2026-07-05T06:24:03.011061+00:00","updated_at":"2026-07-05T06:24:03.011061+00:00"}