{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:P4V4UUMA3PIUXQSFTKCHZ6EJZG","short_pith_number":"pith:P4V4UUMA","schema_version":"1.0","canonical_sha256":"7f2bca5180dbd14bc2459a847cf889c9bcfd79216caf3dae674fd2c10aa2f3f6","source":{"kind":"arxiv","id":"2205.14879","version":1},"attestation_state":"computed","paper":{"title":"Easter2.0: Improving convolutional models for handwritten text recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kartik Chaudhary, Raghav Bali","submitted_at":"2022-05-30T06:33:15Z","abstract_excerpt":"Convolutional Neural Networks (CNN) have shown promising results for the task of Handwritten Text Recognition (HTR) but they still fall behind Recurrent Neural Networks (RNNs)/Transformer based models in terms of performance. In this paper, we propose a CNN based architecture that bridges this gap. Our work, Easter2.0, is composed of multiple layers of 1D Convolution, Batch Normalization, ReLU, Dropout, Dense Residual connection, Squeeze-and-Excitation module and make use of Connectionist Temporal Classification (CTC) loss. In addition to the Easter2.0 architecture, we propose a simple and eff"},"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":"2205.14879","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-30T06:33:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"50499671a1a58b5bd8b03e83598673cedeea35964612d41af713da2c4999f386","abstract_canon_sha256":"6111271f21d76023e60c603e2c85fffbf289713993702f8c57bd799b251f174e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:22.067303Z","signature_b64":"oeC+E9sUtz/qPVihTnMOxo4unqo+GzYPG2Bbvs0m590zdGTnh/DpbalrHcTQ2HfDcryZVJanw0kSfXgcLuowCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f2bca5180dbd14bc2459a847cf889c9bcfd79216caf3dae674fd2c10aa2f3f6","last_reissued_at":"2026-07-05T04:27:22.066793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:22.066793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Easter2.0: Improving convolutional models for handwritten text recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kartik Chaudhary, Raghav Bali","submitted_at":"2022-05-30T06:33:15Z","abstract_excerpt":"Convolutional Neural Networks (CNN) have shown promising results for the task of Handwritten Text Recognition (HTR) but they still fall behind Recurrent Neural Networks (RNNs)/Transformer based models in terms of performance. In this paper, we propose a CNN based architecture that bridges this gap. Our work, Easter2.0, is composed of multiple layers of 1D Convolution, Batch Normalization, ReLU, Dropout, Dense Residual connection, Squeeze-and-Excitation module and make use of Connectionist Temporal Classification (CTC) loss. In addition to the Easter2.0 architecture, we propose a simple and eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14879","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/2205.14879/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":"2205.14879","created_at":"2026-07-05T04:27:22.066841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14879v1","created_at":"2026-07-05T04:27:22.066841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14879","created_at":"2026-07-05T04:27:22.066841+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4V4UUMA3PIU","created_at":"2026-07-05T04:27:22.066841+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4V4UUMA3PIUXQSF","created_at":"2026-07-05T04:27:22.066841+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4V4UUMA","created_at":"2026-07-05T04:27:22.066841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20513","citing_title":"MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuning","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4V4UUMA3PIUXQSFTKCHZ6EJZG","json":"https://pith.science/pith/P4V4UUMA3PIUXQSFTKCHZ6EJZG.json","graph_json":"https://pith.science/api/pith-number/P4V4UUMA3PIUXQSFTKCHZ6EJZG/graph.json","events_json":"https://pith.science/api/pith-number/P4V4UUMA3PIUXQSFTKCHZ6EJZG/events.json","paper":"https://pith.science/paper/P4V4UUMA"},"agent_actions":{"view_html":"https://pith.science/pith/P4V4UUMA3PIUXQSFTKCHZ6EJZG","download_json":"https://pith.science/pith/P4V4UUMA3PIUXQSFTKCHZ6EJZG.json","view_paper":"https://pith.science/paper/P4V4UUMA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14879&json=true","fetch_graph":"https://pith.science/api/pith-number/P4V4UUMA3PIUXQSFTKCHZ6EJZG/graph.json","fetch_events":"https://pith.science/api/pith-number/P4V4UUMA3PIUXQSFTKCHZ6EJZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4V4UUMA3PIUXQSFTKCHZ6EJZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4V4UUMA3PIUXQSFTKCHZ6EJZG/action/storage_attestation","attest_author":"https://pith.science/pith/P4V4UUMA3PIUXQSFTKCHZ6EJZG/action/author_attestation","sign_citation":"https://pith.science/pith/P4V4UUMA3PIUXQSFTKCHZ6EJZG/action/citation_signature","submit_replication":"https://pith.science/pith/P4V4UUMA3PIUXQSFTKCHZ6EJZG/action/replication_record"}},"created_at":"2026-07-05T04:27:22.066841+00:00","updated_at":"2026-07-05T04:27:22.066841+00:00"}