{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O2Q2E7RZGTMPWCYBQW6IZXAOE4","short_pith_number":"pith:O2Q2E7RZ","schema_version":"1.0","canonical_sha256":"76a1a27e3934d8fb0b0185bc8cdc0e271df944dc20f0abadb2d343d7b6cb1bf9","source":{"kind":"arxiv","id":"2509.05019","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Transfer Learning and Mobile-enabled Convolutional Neural Networks for Improved Arabic Handwritten Character Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayyad Maafiri, Hamzah Ali Alkhazaleh, Mohsine EL Khayati, Shadi Atalla, Wathiq Mansoor, Yassine Himeur","submitted_at":"2025-09-05T11:28:53Z","abstract_excerpt":"The study explores the integration of transfer learning (TL) with mobile-enabled convolutional neural networks (MbNets) to enhance Arabic Handwritten Character Recognition (AHCR). Addressing challenges like extensive computational requirements and dataset scarcity, this research evaluates three TL strategies--full fine-tuning, partial fine-tuning, and training from scratch--using four lightweight MbNets: MobileNet, SqueezeNet, MnasNet, and ShuffleNet. Experiments were conducted on three benchmark datasets: AHCD, HIJJA, and IFHCDB. MobileNet emerged as the top-performing model, consistently ach"},"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":"2509.05019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-05T11:28:53Z","cross_cats_sorted":[],"title_canon_sha256":"af0fc8ce290cd9706c3725e7b6f620a7a970b3797882b56791d602a7f0e38b04","abstract_canon_sha256":"9fe81e0b582a5139ddb452264880327105c188cc50ba67342d46ca2c09107c93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:34.551429Z","signature_b64":"1jxnn05MlB4unnOe2R+Zq2cRl6ycCTp/5AkuFBLilW4jrb8MD6M51fr/nYPjZOG1uYR3bjhNvRCrZJo80NaPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76a1a27e3934d8fb0b0185bc8cdc0e271df944dc20f0abadb2d343d7b6cb1bf9","last_reissued_at":"2026-07-05T12:05:34.550935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:34.550935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Transfer Learning and Mobile-enabled Convolutional Neural Networks for Improved Arabic Handwritten Character Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ayyad Maafiri, Hamzah Ali Alkhazaleh, Mohsine EL Khayati, Shadi Atalla, Wathiq Mansoor, Yassine Himeur","submitted_at":"2025-09-05T11:28:53Z","abstract_excerpt":"The study explores the integration of transfer learning (TL) with mobile-enabled convolutional neural networks (MbNets) to enhance Arabic Handwritten Character Recognition (AHCR). Addressing challenges like extensive computational requirements and dataset scarcity, this research evaluates three TL strategies--full fine-tuning, partial fine-tuning, and training from scratch--using four lightweight MbNets: MobileNet, SqueezeNet, MnasNet, and ShuffleNet. Experiments were conducted on three benchmark datasets: AHCD, HIJJA, and IFHCDB. MobileNet emerged as the top-performing model, consistently ach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05019","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/2509.05019/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":"2509.05019","created_at":"2026-07-05T12:05:34.550985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05019v1","created_at":"2026-07-05T12:05:34.550985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05019","created_at":"2026-07-05T12:05:34.550985+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2Q2E7RZGTMP","created_at":"2026-07-05T12:05:34.550985+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2Q2E7RZGTMPWCYB","created_at":"2026-07-05T12:05:34.550985+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2Q2E7RZ","created_at":"2026-07-05T12:05:34.550985+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/O2Q2E7RZGTMPWCYBQW6IZXAOE4","json":"https://pith.science/pith/O2Q2E7RZGTMPWCYBQW6IZXAOE4.json","graph_json":"https://pith.science/api/pith-number/O2Q2E7RZGTMPWCYBQW6IZXAOE4/graph.json","events_json":"https://pith.science/api/pith-number/O2Q2E7RZGTMPWCYBQW6IZXAOE4/events.json","paper":"https://pith.science/paper/O2Q2E7RZ"},"agent_actions":{"view_html":"https://pith.science/pith/O2Q2E7RZGTMPWCYBQW6IZXAOE4","download_json":"https://pith.science/pith/O2Q2E7RZGTMPWCYBQW6IZXAOE4.json","view_paper":"https://pith.science/paper/O2Q2E7RZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05019&json=true","fetch_graph":"https://pith.science/api/pith-number/O2Q2E7RZGTMPWCYBQW6IZXAOE4/graph.json","fetch_events":"https://pith.science/api/pith-number/O2Q2E7RZGTMPWCYBQW6IZXAOE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2Q2E7RZGTMPWCYBQW6IZXAOE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2Q2E7RZGTMPWCYBQW6IZXAOE4/action/storage_attestation","attest_author":"https://pith.science/pith/O2Q2E7RZGTMPWCYBQW6IZXAOE4/action/author_attestation","sign_citation":"https://pith.science/pith/O2Q2E7RZGTMPWCYBQW6IZXAOE4/action/citation_signature","submit_replication":"https://pith.science/pith/O2Q2E7RZGTMPWCYBQW6IZXAOE4/action/replication_record"}},"created_at":"2026-07-05T12:05:34.550985+00:00","updated_at":"2026-07-05T12:05:34.550985+00:00"}