{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JWZXFGZRKVDGRLCJNCXZGT4VCD","short_pith_number":"pith:JWZXFGZR","schema_version":"1.0","canonical_sha256":"4db3729b31554668ac4968af934f9510fe67e6e2607cb795241300bcc37a7386","source":{"kind":"arxiv","id":"2401.08660","version":1},"attestation_state":"computed","paper":{"title":"Gemini Pro Defeated by GPT-4V: Evidence from Education","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ehsan Latif, Gyeong-Geon Lee, Lehong Shi, Xiaoming Zhai","submitted_at":"2023-12-27T02:56:41Z","abstract_excerpt":"This study compared the classification performance of Gemini Pro and GPT-4V in educational settings. Employing visual question answering (VQA) techniques, the study examined both models' abilities to read text-based rubrics and then automatically score student-drawn models in science education. We employed both quantitative and qualitative analyses using a dataset derived from student-drawn scientific models and employing NERIF (Notation-Enhanced Rubrics for Image Feedback) prompting methods. The findings reveal that GPT-4V significantly outperforms Gemini Pro in terms of scoring accuracy and "},"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":"2401.08660","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-27T02:56:41Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"2c7ebb5c67917a5ea4f0cc2aeeee7586e6c16c9d0360eab4df264adb34e1d9e4","abstract_canon_sha256":"bf5cecc99980cc50904946509bc801d4d375732caeff9333c875c14f51436fa5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:19.652567Z","signature_b64":"OZakh/RubQLX48WYlo1w64lHKy3HGgVaOr1hSljOXMq5p+WmBzjfw5yIy9nqTTJsmZhIys4sMy7klcw51fMcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4db3729b31554668ac4968af934f9510fe67e6e2607cb795241300bcc37a7386","last_reissued_at":"2026-07-05T07:34:19.652126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:19.652126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gemini Pro Defeated by GPT-4V: Evidence from Education","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Ehsan Latif, Gyeong-Geon Lee, Lehong Shi, Xiaoming Zhai","submitted_at":"2023-12-27T02:56:41Z","abstract_excerpt":"This study compared the classification performance of Gemini Pro and GPT-4V in educational settings. Employing visual question answering (VQA) techniques, the study examined both models' abilities to read text-based rubrics and then automatically score student-drawn models in science education. We employed both quantitative and qualitative analyses using a dataset derived from student-drawn scientific models and employing NERIF (Notation-Enhanced Rubrics for Image Feedback) prompting methods. The findings reveal that GPT-4V significantly outperforms Gemini Pro in terms of scoring accuracy and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08660","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/2401.08660/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":"2401.08660","created_at":"2026-07-05T07:34:19.652192+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08660v1","created_at":"2026-07-05T07:34:19.652192+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08660","created_at":"2026-07-05T07:34:19.652192+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWZXFGZRKVDG","created_at":"2026-07-05T07:34:19.652192+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWZXFGZRKVDGRLCJ","created_at":"2026-07-05T07:34:19.652192+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWZXFGZR","created_at":"2026-07-05T07:34:19.652192+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15269","citing_title":"Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JWZXFGZRKVDGRLCJNCXZGT4VCD","json":"https://pith.science/pith/JWZXFGZRKVDGRLCJNCXZGT4VCD.json","graph_json":"https://pith.science/api/pith-number/JWZXFGZRKVDGRLCJNCXZGT4VCD/graph.json","events_json":"https://pith.science/api/pith-number/JWZXFGZRKVDGRLCJNCXZGT4VCD/events.json","paper":"https://pith.science/paper/JWZXFGZR"},"agent_actions":{"view_html":"https://pith.science/pith/JWZXFGZRKVDGRLCJNCXZGT4VCD","download_json":"https://pith.science/pith/JWZXFGZRKVDGRLCJNCXZGT4VCD.json","view_paper":"https://pith.science/paper/JWZXFGZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08660&json=true","fetch_graph":"https://pith.science/api/pith-number/JWZXFGZRKVDGRLCJNCXZGT4VCD/graph.json","fetch_events":"https://pith.science/api/pith-number/JWZXFGZRKVDGRLCJNCXZGT4VCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWZXFGZRKVDGRLCJNCXZGT4VCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWZXFGZRKVDGRLCJNCXZGT4VCD/action/storage_attestation","attest_author":"https://pith.science/pith/JWZXFGZRKVDGRLCJNCXZGT4VCD/action/author_attestation","sign_citation":"https://pith.science/pith/JWZXFGZRKVDGRLCJNCXZGT4VCD/action/citation_signature","submit_replication":"https://pith.science/pith/JWZXFGZRKVDGRLCJNCXZGT4VCD/action/replication_record"}},"created_at":"2026-07-05T07:34:19.652192+00:00","updated_at":"2026-07-05T07:34:19.652192+00:00"}