{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HA5EARAVNPJGTFZQK7SO6K2GZF","short_pith_number":"pith:HA5EARAV","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"},"canonical_sha256":"383a4044156bd269973057e4ef2b46c9406910d28ca9be739ea84aae355b9590","source":{"kind":"arxiv","id":"2310.18365","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HA5EARAVNPJGTFZQK7SO6K2GZF","target":"record","payload":{"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"},"canonical_sha256":"383a4044156bd269973057e4ef2b46c9406910d28ca9be739ea84aae355b9590","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"},"source_kind":"arxiv","source_id":"2310.18365","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:03:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jhu+9yuixa/VEIvbuBF5QwFIXfaCEtUctp7qwMOK318sk+3q+rQpaxR8P1rBMO+QefJh5igx1IRX4NqZye0BAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:38:02.707634Z"},"content_sha256":"d50dd090fa7bbb3f79630201581701b52efdb5d6174cb29f78d075e9248623f7","schema_version":"1.0","event_id":"sha256:d50dd090fa7bbb3f79630201581701b52efdb5d6174cb29f78d075e9248623f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HA5EARAVNPJGTFZQK7SO6K2GZF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:03:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VVl+o7HIX5/88k8eiyJSKPgcVDcL+lrFxn+ebIgR5bvB3nPB1PRwl+LZu3IC7Q+jFb9drUvVew6i6J1EUO1cDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:38:02.708306Z"},"content_sha256":"6a487a18ce795a2c0f67cb6662cfaf81401fae3022347e3137205f0ab8445fa2","schema_version":"1.0","event_id":"sha256:6a487a18ce795a2c0f67cb6662cfaf81401fae3022347e3137205f0ab8445fa2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF/bundle.json","state_url":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HA5EARAVNPJGTFZQK7SO6K2GZF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T19:38:02Z","links":{"resolver":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF","bundle":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF/bundle.json","state":"https://pith.science/pith/HA5EARAVNPJGTFZQK7SO6K2GZF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HA5EARAVNPJGTFZQK7SO6K2GZF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2jsR/sQxDvaWNPbn5RiJKAFpn4Y48b+GD8Ww/D5YsOkmldIy2o2SqpBbyFE6gq6R1d83QWcdZswTV2xgPasfBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:38:02.714291Z","bundle_sha256":"a5559ea543f183a5af42bda5a686fa462bb544ada3f1b225f70eaacce35f9e04"}}