{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HA5EARAVNPJGTFZQK7SO6K2GZF","short_pith_number":"pith:HA5EARAV","schema_version":"1.0","canonical_sha256":"383a4044156bd269973057e4ef2b46c9406910d28ca9be739ea84aae355b9590","source":{"kind":"arxiv","id":"2310.18365","version":3},"attestation_state":"computed","paper":{"title":"Using GPT-4 to Augment Unbalanced Data for Automatic Scoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Gyeong-Geon Lee, Luyang Fang, Xiaoming Zhai","submitted_at":"2023-10-25T01:07:50Z","abstract_excerpt":"Machine learning-based automatic scoring faces challenges with unbalanced student responses across scoring categories. To address this, we introduce a novel text data augmentation framework leveraging GPT-4, a generative large language model, specifically tailored for unbalanced datasets in automatic scoring. Our experimental dataset comprised student written responses to four science items. We crafted prompts for GPT-4 to generate responses, especially for minority scoring classes, enhancing the data set. We then finetuned DistillBERT for automatic scoring based on the augmented and original "},"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":"2310.18365","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T01:07:50Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"7073df1787865196575f265cf7e42c84ff405137395d86895cf4d8ef0c3b3c48","abstract_canon_sha256":"4bb65f3cbf858291081763f124d6691ffb60d3230a7c1cafa28b4a3bf1eab00b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:48.380918Z","signature_b64":"bjFPQ6M6GNfy2jw+mbsan62O8YDf9rm7PbbEWFMW2RAn1fqoKz7P7HI4J0Gu9+/Qzg1gAzpP4AAwEyNvLEskCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"383a4044156bd269973057e4ef2b46c9406910d28ca9be739ea84aae355b9590","last_reissued_at":"2026-07-05T09:03:48.380523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:48.380523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using GPT-4 to Augment Unbalanced Data for Automatic Scoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Gyeong-Geon Lee, Luyang Fang, Xiaoming Zhai","submitted_at":"2023-10-25T01:07:50Z","abstract_excerpt":"Machine learning-based automatic scoring faces challenges with unbalanced student responses across scoring categories. To address this, we introduce a novel text data augmentation framework leveraging GPT-4, a generative large language model, specifically tailored for unbalanced datasets in automatic scoring. Our experimental dataset comprised student written responses to four science items. We crafted prompts for GPT-4 to generate responses, especially for minority scoring classes, enhancing the data set. We then finetuned DistillBERT for automatic scoring based on the augmented and original "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18365","kind":"arxiv","version":3},"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/2310.18365/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":"2310.18365","created_at":"2026-07-05T09:03:48.380579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18365v3","created_at":"2026-07-05T09:03:48.380579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18365","created_at":"2026-07-05T09:03:48.380579+00:00"},{"alias_kind":"pith_short_12","alias_value":"HA5EARAVNPJG","created_at":"2026-07-05T09:03:48.380579+00:00"},{"alias_kind":"pith_short_16","alias_value":"HA5EARAVNPJGTFZQ","created_at":"2026-07-05T09:03:48.380579+00:00"},{"alias_kind":"pith_short_8","alias_value":"HA5EARAV","created_at":"2026-07-05T09:03:48.380579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19266","citing_title":"Using Large Language Models to Assess Teachers' Pedagogical Content Knowledge","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF","json":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF.json","graph_json":"https://pith.science/api/pith-number/HA5EARAVNPJGTFZQK7SO6K2GZF/graph.json","events_json":"https://pith.science/api/pith-number/HA5EARAVNPJGTFZQK7SO6K2GZF/events.json","paper":"https://pith.science/paper/HA5EARAV"},"agent_actions":{"view_html":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF","download_json":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF.json","view_paper":"https://pith.science/paper/HA5EARAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18365&json=true","fetch_graph":"https://pith.science/api/pith-number/HA5EARAVNPJGTFZQK7SO6K2GZF/graph.json","fetch_events":"https://pith.science/api/pith-number/HA5EARAVNPJGTFZQK7SO6K2GZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF/action/storage_attestation","attest_author":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF/action/author_attestation","sign_citation":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF/action/citation_signature","submit_replication":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF/action/replication_record"}},"created_at":"2026-07-05T09:03:48.380579+00:00","updated_at":"2026-07-05T09:03:48.380579+00:00"}