{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WLVSEREGVMXJZE2C5QDSNVMKLX","short_pith_number":"pith:WLVSEREG","schema_version":"1.0","canonical_sha256":"b2eb224486ab2e9c9342ec0726d58a5df2782041018984ad827888740325ff5f","source":{"kind":"arxiv","id":"2312.03568","version":1},"attestation_state":"computed","paper":{"title":"DocBinFormer: A Two-Level Transformer Network for Effective Document Image Binarization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guang-Bin Huang, Ning Wang, Risab Biswas, Swalpa Kumar Roy, Umapada Pal","submitted_at":"2023-12-06T16:01:29Z","abstract_excerpt":"In real life, various degradation scenarios exist that might damage document images, making it harder to recognize and analyze them, thus binarization is a fundamental and crucial step for achieving the most optimal performance in any document analysis task. We propose DocBinFormer (Document Binarization Transformer), a novel two-level vision transformer (TL-ViT) architecture based on vision transformers for effective document image binarization. The presented architecture employs a two-level transformer encoder to effectively capture both global and local feature representation from the input"},"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":"2312.03568","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T16:01:29Z","cross_cats_sorted":[],"title_canon_sha256":"642205dc0b69004d0a441af98fb4480cd6d9dcdd33df58a70791e256bf0bf3d9","abstract_canon_sha256":"7dba737a08c127e3ff7cc0d94154469e85044b6800c016f068960823ff7e7a71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:06.535538Z","signature_b64":"S/fy7gG8BRQPZPD05+odAbdqdOh10vvq0IkkDscA0tVoICoWsK58tYc6+vjrbKpoxYmp0k0khnPYhGP2YvT1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2eb224486ab2e9c9342ec0726d58a5df2782041018984ad827888740325ff5f","last_reissued_at":"2026-07-05T07:21:06.534961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:06.534961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocBinFormer: A Two-Level Transformer Network for Effective Document Image Binarization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guang-Bin Huang, Ning Wang, Risab Biswas, Swalpa Kumar Roy, Umapada Pal","submitted_at":"2023-12-06T16:01:29Z","abstract_excerpt":"In real life, various degradation scenarios exist that might damage document images, making it harder to recognize and analyze them, thus binarization is a fundamental and crucial step for achieving the most optimal performance in any document analysis task. We propose DocBinFormer (Document Binarization Transformer), a novel two-level vision transformer (TL-ViT) architecture based on vision transformers for effective document image binarization. The presented architecture employs a two-level transformer encoder to effectively capture both global and local feature representation from the input"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03568","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/2312.03568/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":"2312.03568","created_at":"2026-07-05T07:21:06.535020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03568v1","created_at":"2026-07-05T07:21:06.535020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03568","created_at":"2026-07-05T07:21:06.535020+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLVSEREGVMXJ","created_at":"2026-07-05T07:21:06.535020+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLVSEREGVMXJZE2C","created_at":"2026-07-05T07:21:06.535020+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLVSEREG","created_at":"2026-07-05T07:21:06.535020+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22625","citing_title":"DR-Mamba: Automatic Inference-Time Domain Adaptation for Document Image Binarization via Sample-Conditioned Detail-Background Suppression","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08781","citing_title":"DeepMine-Mamba: Mitigating Information Dilution in Mamba-Based State Space Models for Document Image Binarization","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WLVSEREGVMXJZE2C5QDSNVMKLX","json":"https://pith.science/pith/WLVSEREGVMXJZE2C5QDSNVMKLX.json","graph_json":"https://pith.science/api/pith-number/WLVSEREGVMXJZE2C5QDSNVMKLX/graph.json","events_json":"https://pith.science/api/pith-number/WLVSEREGVMXJZE2C5QDSNVMKLX/events.json","paper":"https://pith.science/paper/WLVSEREG"},"agent_actions":{"view_html":"https://pith.science/pith/WLVSEREGVMXJZE2C5QDSNVMKLX","download_json":"https://pith.science/pith/WLVSEREGVMXJZE2C5QDSNVMKLX.json","view_paper":"https://pith.science/paper/WLVSEREG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03568&json=true","fetch_graph":"https://pith.science/api/pith-number/WLVSEREGVMXJZE2C5QDSNVMKLX/graph.json","fetch_events":"https://pith.science/api/pith-number/WLVSEREGVMXJZE2C5QDSNVMKLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLVSEREGVMXJZE2C5QDSNVMKLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLVSEREGVMXJZE2C5QDSNVMKLX/action/storage_attestation","attest_author":"https://pith.science/pith/WLVSEREGVMXJZE2C5QDSNVMKLX/action/author_attestation","sign_citation":"https://pith.science/pith/WLVSEREGVMXJZE2C5QDSNVMKLX/action/citation_signature","submit_replication":"https://pith.science/pith/WLVSEREGVMXJZE2C5QDSNVMKLX/action/replication_record"}},"created_at":"2026-07-05T07:21:06.535020+00:00","updated_at":"2026-07-05T07:21:06.535020+00:00"}