{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HA5EARAVNPJGTFZQK7SO6K2GZF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4bb65f3cbf858291081763f124d6691ffb60d3230a7c1cafa28b4a3bf1eab00b","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T01:07:50Z","title_canon_sha256":"7073df1787865196575f265cf7e42c84ff405137395d86895cf4d8ef0c3b3c48"},"schema_version":"1.0","source":{"id":"2310.18365","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18365","created_at":"2026-07-05T09:03:48Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18365v3","created_at":"2026-07-05T09:03:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18365","created_at":"2026-07-05T09:03:48Z"},{"alias_kind":"pith_short_12","alias_value":"HA5EARAVNPJG","created_at":"2026-07-05T09:03:48Z"},{"alias_kind":"pith_short_16","alias_value":"HA5EARAVNPJGTFZQ","created_at":"2026-07-05T09:03:48Z"},{"alias_kind":"pith_short_8","alias_value":"HA5EARAV","created_at":"2026-07-05T09:03:48Z"}],"graph_snapshots":[{"event_id":"sha256:6a487a18ce795a2c0f67cb6662cfaf81401fae3022347e3137205f0ab8445fa2","target":"graph","created_at":"2026-07-05T09:03:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.18365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Gyeong-Geon Lee, Luyang Fang, Xiaoming Zhai","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T01:07:50Z","title":"Using GPT-4 to Augment Unbalanced Data for Automatic Scoring"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18365","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d50dd090fa7bbb3f79630201581701b52efdb5d6174cb29f78d075e9248623f7","target":"record","created_at":"2026-07-05T09:03:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4bb65f3cbf858291081763f124d6691ffb60d3230a7c1cafa28b4a3bf1eab00b","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T01:07:50Z","title_canon_sha256":"7073df1787865196575f265cf7e42c84ff405137395d86895cf4d8ef0c3b3c48"},"schema_version":"1.0","source":{"id":"2310.18365","kind":"arxiv","version":3}},"canonical_sha256":"383a4044156bd269973057e4ef2b46c9406910d28ca9be739ea84aae355b9590","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"383a4044156bd269973057e4ef2b46c9406910d28ca9be739ea84aae355b9590","first_computed_at":"2026-07-05T09:03:48.380523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:48.380523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bjFPQ6M6GNfy2jw+mbsan62O8YDf9rm7PbbEWFMW2RAn1fqoKz7P7HI4J0Gu9+/Qzg1gAzpP4AAwEyNvLEskCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:48.380918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.18365","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d50dd090fa7bbb3f79630201581701b52efdb5d6174cb29f78d075e9248623f7","sha256:6a487a18ce795a2c0f67cb6662cfaf81401fae3022347e3137205f0ab8445fa2"],"state_sha256":"218ed351088633fde6b3b9214454a944c8e445e6cb5954a618054e032225c9d9"}