{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5OB76VFEDWFOGEQTRX4YEE5LTH","short_pith_number":"pith:5OB76VFE","schema_version":"1.0","canonical_sha256":"eb83ff54a41d8ae312138df98213ab99f4fddd12fa521e549689cb1f39d110e9","source":{"kind":"arxiv","id":"1911.01577","version":2},"attestation_state":"computed","paper":{"title":"Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duc Nguyen, Hung Le, Nhan Tran","submitted_at":"2019-11-05T02:42:09Z","abstract_excerpt":"Convolutional Recurrent Neural Networks (CRNNs) excel at scene text recognition. Unfortunately, they are likely to suffer from vanishing/exploding gradient problems when processing long text images, which are commonly found in scanned documents. This poses a major challenge to goal of completely solving Optical Character Recognition (OCR) problem. Inspired by recently proposed memory-augmented neural networks (MANNs) for long-term sequential modeling, we present a new architecture dubbed Convolutional Multi-way Associative Memory (CMAM) to tackle the limitation of current CRNNs. By leveraging "},"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":"1911.01577","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-05T02:42:09Z","cross_cats_sorted":[],"title_canon_sha256":"0e15e7d7fc3d46585599c2828263c1d970a0af3c903269bc12e5703598334947","abstract_canon_sha256":"839eebaca65e84a24f4e1d4149711137ef5fc7e9fbb0f68f4b0a40a719eb5e0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:02.756843Z","signature_b64":"/6+ucGBDc0yOEBMwqmiL2LgYKjuKkWCuI0F6vSgQ25QcZ1A//aoNPdzzQ0mt1ttkb6EqG9cySCBHFoMf7oyPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb83ff54a41d8ae312138df98213ab99f4fddd12fa521e549689cb1f39d110e9","last_reissued_at":"2026-07-05T00:35:02.756358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:02.756358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duc Nguyen, Hung Le, Nhan Tran","submitted_at":"2019-11-05T02:42:09Z","abstract_excerpt":"Convolutional Recurrent Neural Networks (CRNNs) excel at scene text recognition. Unfortunately, they are likely to suffer from vanishing/exploding gradient problems when processing long text images, which are commonly found in scanned documents. This poses a major challenge to goal of completely solving Optical Character Recognition (OCR) problem. Inspired by recently proposed memory-augmented neural networks (MANNs) for long-term sequential modeling, we present a new architecture dubbed Convolutional Multi-way Associative Memory (CMAM) to tackle the limitation of current CRNNs. By leveraging "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.01577","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/1911.01577/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":"1911.01577","created_at":"2026-07-05T00:35:02.756417+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.01577v2","created_at":"2026-07-05T00:35:02.756417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.01577","created_at":"2026-07-05T00:35:02.756417+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OB76VFEDWFO","created_at":"2026-07-05T00:35:02.756417+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OB76VFEDWFOGEQT","created_at":"2026-07-05T00:35:02.756417+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OB76VFE","created_at":"2026-07-05T00:35:02.756417+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/5OB76VFEDWFOGEQTRX4YEE5LTH","json":"https://pith.science/pith/5OB76VFEDWFOGEQTRX4YEE5LTH.json","graph_json":"https://pith.science/api/pith-number/5OB76VFEDWFOGEQTRX4YEE5LTH/graph.json","events_json":"https://pith.science/api/pith-number/5OB76VFEDWFOGEQTRX4YEE5LTH/events.json","paper":"https://pith.science/paper/5OB76VFE"},"agent_actions":{"view_html":"https://pith.science/pith/5OB76VFEDWFOGEQTRX4YEE5LTH","download_json":"https://pith.science/pith/5OB76VFEDWFOGEQTRX4YEE5LTH.json","view_paper":"https://pith.science/paper/5OB76VFE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.01577&json=true","fetch_graph":"https://pith.science/api/pith-number/5OB76VFEDWFOGEQTRX4YEE5LTH/graph.json","fetch_events":"https://pith.science/api/pith-number/5OB76VFEDWFOGEQTRX4YEE5LTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OB76VFEDWFOGEQTRX4YEE5LTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OB76VFEDWFOGEQTRX4YEE5LTH/action/storage_attestation","attest_author":"https://pith.science/pith/5OB76VFEDWFOGEQTRX4YEE5LTH/action/author_attestation","sign_citation":"https://pith.science/pith/5OB76VFEDWFOGEQTRX4YEE5LTH/action/citation_signature","submit_replication":"https://pith.science/pith/5OB76VFEDWFOGEQTRX4YEE5LTH/action/replication_record"}},"created_at":"2026-07-05T00:35:02.756417+00:00","updated_at":"2026-07-05T00:35:02.756417+00:00"}