{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GWSRFO24C55MMA2L5OPFN4ACTU","short_pith_number":"pith:GWSRFO24","schema_version":"1.0","canonical_sha256":"35a512bb5c177ac6034beb9e56f0029d1a46a8b3ff72b7db06594a31da6d8440","source":{"kind":"arxiv","id":"2305.02593","version":1},"attestation_state":"computed","paper":{"title":"How to Choose Pretrained Handwriting Recognition Models for Single Writer Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CV","authors_text":"Christopher Kermorvant, Rita Cucchiara, Silvia Cascianelli, Vittorio Pippi","submitted_at":"2023-05-04T07:00:28Z","abstract_excerpt":"Recent advancements in Deep Learning-based Handwritten Text Recognition (HTR) have led to models with remarkable performance on both modern and historical manuscripts in large benchmark datasets. Nonetheless, those models struggle to obtain the same performance when applied to manuscripts with peculiar characteristics, such as language, paper support, ink, and author handwriting. This issue is very relevant for valuable but small collections of documents preserved in historical archives, for which obtaining sufficient annotated training data is costly or, in some cases, unfeasible. To overcome"},"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":"2305.02593","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-04T07:00:28Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"f7afb83c21fd73bf2390b5337850338aff61e55b98a55f47bc6efc173c1ea1d9","abstract_canon_sha256":"2ea1966120f73d446d11904995e2676ce6ff1490367f78dbe4b61f563e7b84d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:03.049832Z","signature_b64":"EEP7pa7SewqqnhPkZ6hfAk3NGOE61WF+8JH/A+JiWrmxyRW10wziRh9ERvFVBJR9HKIui6Fo9Ksop/SIPgMEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35a512bb5c177ac6034beb9e56f0029d1a46a8b3ff72b7db06594a31da6d8440","last_reissued_at":"2026-07-05T06:07:03.049270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:03.049270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Choose Pretrained Handwriting Recognition Models for Single Writer Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CV","authors_text":"Christopher Kermorvant, Rita Cucchiara, Silvia Cascianelli, Vittorio Pippi","submitted_at":"2023-05-04T07:00:28Z","abstract_excerpt":"Recent advancements in Deep Learning-based Handwritten Text Recognition (HTR) have led to models with remarkable performance on both modern and historical manuscripts in large benchmark datasets. Nonetheless, those models struggle to obtain the same performance when applied to manuscripts with peculiar characteristics, such as language, paper support, ink, and author handwriting. This issue is very relevant for valuable but small collections of documents preserved in historical archives, for which obtaining sufficient annotated training data is costly or, in some cases, unfeasible. To overcome"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02593","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/2305.02593/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":"2305.02593","created_at":"2026-07-05T06:07:03.049341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.02593v1","created_at":"2026-07-05T06:07:03.049341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02593","created_at":"2026-07-05T06:07:03.049341+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWSRFO24C55M","created_at":"2026-07-05T06:07:03.049341+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWSRFO24C55MMA2L","created_at":"2026-07-05T06:07:03.049341+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWSRFO24","created_at":"2026-07-05T06:07:03.049341+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/GWSRFO24C55MMA2L5OPFN4ACTU","json":"https://pith.science/pith/GWSRFO24C55MMA2L5OPFN4ACTU.json","graph_json":"https://pith.science/api/pith-number/GWSRFO24C55MMA2L5OPFN4ACTU/graph.json","events_json":"https://pith.science/api/pith-number/GWSRFO24C55MMA2L5OPFN4ACTU/events.json","paper":"https://pith.science/paper/GWSRFO24"},"agent_actions":{"view_html":"https://pith.science/pith/GWSRFO24C55MMA2L5OPFN4ACTU","download_json":"https://pith.science/pith/GWSRFO24C55MMA2L5OPFN4ACTU.json","view_paper":"https://pith.science/paper/GWSRFO24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.02593&json=true","fetch_graph":"https://pith.science/api/pith-number/GWSRFO24C55MMA2L5OPFN4ACTU/graph.json","fetch_events":"https://pith.science/api/pith-number/GWSRFO24C55MMA2L5OPFN4ACTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWSRFO24C55MMA2L5OPFN4ACTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWSRFO24C55MMA2L5OPFN4ACTU/action/storage_attestation","attest_author":"https://pith.science/pith/GWSRFO24C55MMA2L5OPFN4ACTU/action/author_attestation","sign_citation":"https://pith.science/pith/GWSRFO24C55MMA2L5OPFN4ACTU/action/citation_signature","submit_replication":"https://pith.science/pith/GWSRFO24C55MMA2L5OPFN4ACTU/action/replication_record"}},"created_at":"2026-07-05T06:07:03.049341+00:00","updated_at":"2026-07-05T06:07:03.049341+00:00"}