{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SPPHEK6YVPVN7BOECG5IVNTCBJ","short_pith_number":"pith:SPPHEK6Y","schema_version":"1.0","canonical_sha256":"93de722bd8abeadf85c411ba8ab6620a727e1a5f522d774dd5fc49e91cc5b9f7","source":{"kind":"arxiv","id":"2111.06738","version":1},"attestation_state":"computed","paper":{"title":"Improving Structured Text Recognition with Regular Expression Biasing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoguang Shi, Cha Zhang, Dinei Florencio, Wenfeng Cheng, Yijuan Lu","submitted_at":"2021-11-10T23:12:05Z","abstract_excerpt":"We study the problem of recognizing structured text, i.e. text that follows certain formats, and propose to improve the recognition accuracy of structured text by specifying regular expressions (regexes) for biasing. A biased recognizer recognizes text that matches the specified regexes with significantly improved accuracy, at the cost of a generally small degradation on other text. The biasing is realized by modeling regexes as a Weighted Finite-State Transducer (WFST) and injecting it into the decoder via dynamic replacement. A single hyperparameter controls the biasing strength. The method "},"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":"2111.06738","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-10T23:12:05Z","cross_cats_sorted":[],"title_canon_sha256":"74f369bc5f1b406ddb6b9497a15d5aba3962a3802a6e811bc40847942384d692","abstract_canon_sha256":"d77110fa3df7ed8e95a147df6839c671c48faa28d9b829f989430f811038f8f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:17.181415Z","signature_b64":"VoaY2vSfqLPyvPEfRC0m0EZXAC4ipvzg2NL8DxjMNIwSFTsgMDRgOGs+c5Oub3ln0LfKaQECJYhs6GkDGofrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93de722bd8abeadf85c411ba8ab6620a727e1a5f522d774dd5fc49e91cc5b9f7","last_reissued_at":"2026-07-05T03:31:17.180988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:17.180988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Structured Text Recognition with Regular Expression Biasing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoguang Shi, Cha Zhang, Dinei Florencio, Wenfeng Cheng, Yijuan Lu","submitted_at":"2021-11-10T23:12:05Z","abstract_excerpt":"We study the problem of recognizing structured text, i.e. text that follows certain formats, and propose to improve the recognition accuracy of structured text by specifying regular expressions (regexes) for biasing. A biased recognizer recognizes text that matches the specified regexes with significantly improved accuracy, at the cost of a generally small degradation on other text. The biasing is realized by modeling regexes as a Weighted Finite-State Transducer (WFST) and injecting it into the decoder via dynamic replacement. A single hyperparameter controls the biasing strength. The method "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.06738","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/2111.06738/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":"2111.06738","created_at":"2026-07-05T03:31:17.181044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.06738v1","created_at":"2026-07-05T03:31:17.181044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.06738","created_at":"2026-07-05T03:31:17.181044+00:00"},{"alias_kind":"pith_short_12","alias_value":"SPPHEK6YVPVN","created_at":"2026-07-05T03:31:17.181044+00:00"},{"alias_kind":"pith_short_16","alias_value":"SPPHEK6YVPVN7BOE","created_at":"2026-07-05T03:31:17.181044+00:00"},{"alias_kind":"pith_short_8","alias_value":"SPPHEK6Y","created_at":"2026-07-05T03:31:17.181044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01093","citing_title":"Automated Extraction of Acronym-Expansion Pairs from Scientific Papers","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SPPHEK6YVPVN7BOECG5IVNTCBJ","json":"https://pith.science/pith/SPPHEK6YVPVN7BOECG5IVNTCBJ.json","graph_json":"https://pith.science/api/pith-number/SPPHEK6YVPVN7BOECG5IVNTCBJ/graph.json","events_json":"https://pith.science/api/pith-number/SPPHEK6YVPVN7BOECG5IVNTCBJ/events.json","paper":"https://pith.science/paper/SPPHEK6Y"},"agent_actions":{"view_html":"https://pith.science/pith/SPPHEK6YVPVN7BOECG5IVNTCBJ","download_json":"https://pith.science/pith/SPPHEK6YVPVN7BOECG5IVNTCBJ.json","view_paper":"https://pith.science/paper/SPPHEK6Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.06738&json=true","fetch_graph":"https://pith.science/api/pith-number/SPPHEK6YVPVN7BOECG5IVNTCBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/SPPHEK6YVPVN7BOECG5IVNTCBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SPPHEK6YVPVN7BOECG5IVNTCBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SPPHEK6YVPVN7BOECG5IVNTCBJ/action/storage_attestation","attest_author":"https://pith.science/pith/SPPHEK6YVPVN7BOECG5IVNTCBJ/action/author_attestation","sign_citation":"https://pith.science/pith/SPPHEK6YVPVN7BOECG5IVNTCBJ/action/citation_signature","submit_replication":"https://pith.science/pith/SPPHEK6YVPVN7BOECG5IVNTCBJ/action/replication_record"}},"created_at":"2026-07-05T03:31:17.181044+00:00","updated_at":"2026-07-05T03:31:17.181044+00:00"}