{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XFNECHLW47VJWZMH4TYMKMWQBC","short_pith_number":"pith:XFNECHLW","schema_version":"1.0","canonical_sha256":"b95a411d76e7ea9b6587e4f0c532d00886517fdec2f2a22a4174d0a068993b17","source":{"kind":"arxiv","id":"2411.14962","version":2},"attestation_state":"computed","paper":{"title":"LLM for Barcodes: Generating Diverse Synthetic Data for Identity Documents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CL","authors_text":"Amit Agarwal, Bhargava Kumar, Hitesh Laxmichand Patel, Karan Gupta, Priyaranjan Pattnayak","submitted_at":"2024-11-22T14:21:18Z","abstract_excerpt":"Accurate barcode detection and decoding in Identity documents is crucial for applications like security, healthcare, and education, where reliable data extraction and verification are essential. However, building robust detection models is challenging due to the lack of diverse, realistic datasets an issue often tied to privacy concerns and the wide variety of document formats. Traditional tools like Faker rely on predefined templates, making them less effective for capturing the complexity of real-world identity documents. In this paper, we introduce a new approach to synthetic data generatio"},"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":"2411.14962","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-22T14:21:18Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"d9163cb9fbd2d152c2bfad3a0f9d8caee085dae06bed9185878e99c2d7ce9f90","abstract_canon_sha256":"1200146afdfab1a21e5b1fb1c09f09c48025eab1bedc5a06050934f25721904c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:28.979889Z","signature_b64":"m+yCVm6Yo2L+QQQsLFzTWls1KRFjnQquNCC+foPmt2Vk0FOth4NsaFa22JXQoujTl3Yy3G0dSf814O0g7ITzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b95a411d76e7ea9b6587e4f0c532d00886517fdec2f2a22a4174d0a068993b17","last_reissued_at":"2026-07-05T09:53:28.979415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:28.979415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM for Barcodes: Generating Diverse Synthetic Data for Identity Documents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.CL","authors_text":"Amit Agarwal, Bhargava Kumar, Hitesh Laxmichand Patel, Karan Gupta, Priyaranjan Pattnayak","submitted_at":"2024-11-22T14:21:18Z","abstract_excerpt":"Accurate barcode detection and decoding in Identity documents is crucial for applications like security, healthcare, and education, where reliable data extraction and verification are essential. However, building robust detection models is challenging due to the lack of diverse, realistic datasets an issue often tied to privacy concerns and the wide variety of document formats. Traditional tools like Faker rely on predefined templates, making them less effective for capturing the complexity of real-world identity documents. In this paper, we introduce a new approach to synthetic data generatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14962","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/2411.14962/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":"2411.14962","created_at":"2026-07-05T09:53:28.979474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14962v2","created_at":"2026-07-05T09:53:28.979474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14962","created_at":"2026-07-05T09:53:28.979474+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFNECHLW47VJ","created_at":"2026-07-05T09:53:28.979474+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFNECHLW47VJWZMH","created_at":"2026-07-05T09:53:28.979474+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFNECHLW","created_at":"2026-07-05T09:53:28.979474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02097","citing_title":"Hybrid AI for Responsive Multi-Turn Online Conversations with Novel Dynamic Routing and Feedback Adaptation","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFNECHLW47VJWZMH4TYMKMWQBC","json":"https://pith.science/pith/XFNECHLW47VJWZMH4TYMKMWQBC.json","graph_json":"https://pith.science/api/pith-number/XFNECHLW47VJWZMH4TYMKMWQBC/graph.json","events_json":"https://pith.science/api/pith-number/XFNECHLW47VJWZMH4TYMKMWQBC/events.json","paper":"https://pith.science/paper/XFNECHLW"},"agent_actions":{"view_html":"https://pith.science/pith/XFNECHLW47VJWZMH4TYMKMWQBC","download_json":"https://pith.science/pith/XFNECHLW47VJWZMH4TYMKMWQBC.json","view_paper":"https://pith.science/paper/XFNECHLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14962&json=true","fetch_graph":"https://pith.science/api/pith-number/XFNECHLW47VJWZMH4TYMKMWQBC/graph.json","fetch_events":"https://pith.science/api/pith-number/XFNECHLW47VJWZMH4TYMKMWQBC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFNECHLW47VJWZMH4TYMKMWQBC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFNECHLW47VJWZMH4TYMKMWQBC/action/storage_attestation","attest_author":"https://pith.science/pith/XFNECHLW47VJWZMH4TYMKMWQBC/action/author_attestation","sign_citation":"https://pith.science/pith/XFNECHLW47VJWZMH4TYMKMWQBC/action/citation_signature","submit_replication":"https://pith.science/pith/XFNECHLW47VJWZMH4TYMKMWQBC/action/replication_record"}},"created_at":"2026-07-05T09:53:28.979474+00:00","updated_at":"2026-07-05T09:53:28.979474+00:00"}