{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5L7LQVUF5KYYKQTOGFL5FILBWF","short_pith_number":"pith:5L7LQVUF","schema_version":"1.0","canonical_sha256":"eafeb85685eab185426e3157d2a161b1606685f0bd4124fba2511ffb09efb187","source":{"kind":"arxiv","id":"2605.25924","version":1},"attestation_state":"computed","paper":{"title":"Does Continued Pretraining on a Learner Corpus Improve Automated Essay Scoring on English Proficiency Tests? Evidence from EFCAMDAT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Duy Anh Nguyen","submitted_at":"2026-05-25T15:04:37Z","abstract_excerpt":"Recent automated essay scoring (AES) studies increasingly use pretrained transformer models, but these models are usually pretrained on general-domain English and may under-represent second-language learner writing. This study investigates whether domain-adaptive continued pretraining (DAPT) on the EFCAMDAT learner corpus improves transformer-based AES for English proficiency tests. We apply DAPT to three transformer encoders and evaluate them on FCE and IELTS in both in-domain scoring and few-shot cross-dataset transfer. Full-corpus DAPT produces mixed results across models, datasets, and met"},"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":"2605.25924","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T15:04:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f7d38d1f305f211487f3b59693e8327650bad03b5b094615f2a1170005883da6","abstract_canon_sha256":"c4507bb9e2d4a3378fa7e7e6c185d382cc5e4d04f8eb49b64a525068e7f1776c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:18.651887Z","signature_b64":"R+xSxpW1ZsFIGSpFDrL4cKcX9tlduOz4z5+MCNU3cUsAyoVbmjMnFG6X/zmt9GyObtO5QGtZ2ceaiHrKLWjPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eafeb85685eab185426e3157d2a161b1606685f0bd4124fba2511ffb09efb187","last_reissued_at":"2026-05-26T02:05:18.651178Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:18.651178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Continued Pretraining on a Learner Corpus Improve Automated Essay Scoring on English Proficiency Tests? Evidence from EFCAMDAT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Duy Anh Nguyen","submitted_at":"2026-05-25T15:04:37Z","abstract_excerpt":"Recent automated essay scoring (AES) studies increasingly use pretrained transformer models, but these models are usually pretrained on general-domain English and may under-represent second-language learner writing. This study investigates whether domain-adaptive continued pretraining (DAPT) on the EFCAMDAT learner corpus improves transformer-based AES for English proficiency tests. We apply DAPT to three transformer encoders and evaluate them on FCE and IELTS in both in-domain scoring and few-shot cross-dataset transfer. Full-corpus DAPT produces mixed results across models, datasets, and met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25924","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/2605.25924/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":"2605.25924","created_at":"2026-05-26T02:05:18.651287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25924v1","created_at":"2026-05-26T02:05:18.651287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25924","created_at":"2026-05-26T02:05:18.651287+00:00"},{"alias_kind":"pith_short_12","alias_value":"5L7LQVUF5KYY","created_at":"2026-05-26T02:05:18.651287+00:00"},{"alias_kind":"pith_short_16","alias_value":"5L7LQVUF5KYYKQTO","created_at":"2026-05-26T02:05:18.651287+00:00"},{"alias_kind":"pith_short_8","alias_value":"5L7LQVUF","created_at":"2026-05-26T02:05:18.651287+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/5L7LQVUF5KYYKQTOGFL5FILBWF","json":"https://pith.science/pith/5L7LQVUF5KYYKQTOGFL5FILBWF.json","graph_json":"https://pith.science/api/pith-number/5L7LQVUF5KYYKQTOGFL5FILBWF/graph.json","events_json":"https://pith.science/api/pith-number/5L7LQVUF5KYYKQTOGFL5FILBWF/events.json","paper":"https://pith.science/paper/5L7LQVUF"},"agent_actions":{"view_html":"https://pith.science/pith/5L7LQVUF5KYYKQTOGFL5FILBWF","download_json":"https://pith.science/pith/5L7LQVUF5KYYKQTOGFL5FILBWF.json","view_paper":"https://pith.science/paper/5L7LQVUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25924&json=true","fetch_graph":"https://pith.science/api/pith-number/5L7LQVUF5KYYKQTOGFL5FILBWF/graph.json","fetch_events":"https://pith.science/api/pith-number/5L7LQVUF5KYYKQTOGFL5FILBWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5L7LQVUF5KYYKQTOGFL5FILBWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5L7LQVUF5KYYKQTOGFL5FILBWF/action/storage_attestation","attest_author":"https://pith.science/pith/5L7LQVUF5KYYKQTOGFL5FILBWF/action/author_attestation","sign_citation":"https://pith.science/pith/5L7LQVUF5KYYKQTOGFL5FILBWF/action/citation_signature","submit_replication":"https://pith.science/pith/5L7LQVUF5KYYKQTOGFL5FILBWF/action/replication_record"}},"created_at":"2026-05-26T02:05:18.651287+00:00","updated_at":"2026-05-26T02:05:18.651287+00:00"}