{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:W4VABBGH5QYQCSMNAC4G7ZR2O7","short_pith_number":"pith:W4VABBGH","schema_version":"1.0","canonical_sha256":"b72a0084c7ec3101498d00b86fe63a77c7c5ac63cf2d598fbdf03dd3df644993","source":{"kind":"arxiv","id":"2412.10019","version":3},"attestation_state":"computed","paper":{"title":"Performance of ChatGPT on tasks involving physics visual representations: the case of the Brief Electricity and Magnetism Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"physics.ed-ph","authors_text":"Bor Gregorcic, Elias Onerud, Giulia Polverini, Jakob Melin","submitted_at":"2024-12-13T10:00:41Z","abstract_excerpt":"Artificial intelligence-based chatbots are increasingly influencing physics education due to their ability to interpret and respond to textual and visual inputs. This study evaluates the performance of two large multimodal model-based chatbots, ChatGPT-4 and ChatGPT-4o on the Brief Electricity and Magnetism Assessment (BEMA), a conceptual physics inventory rich in visual representations such as vector fields, circuit diagrams, and graphs. Quantitative analysis shows that ChatGPT-4o outperforms both ChatGPT-4 and a large sample of university students, and demonstrates improvements in ChatGPT-4o"},"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":"2412.10019","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.ed-ph","submitted_at":"2024-12-13T10:00:41Z","cross_cats_sorted":[],"title_canon_sha256":"46fd0b90bb0ad26b9d94d8b8291dc93f8f2bf3f8548d87bc44b9cb3daa3aba46","abstract_canon_sha256":"c157337d702e47272a66ffa24400d7718ba379c68b8c729ee27443c7cb028aa1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:21.136866Z","signature_b64":"8+OTNXuEqaYPn3HVsAc+KI4UC15P97w3+jH2mgFYBo08wmjLyEV0k2+X5ed4z0+lnrZfAmrtTRfPnFzgIz4ZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b72a0084c7ec3101498d00b86fe63a77c7c5ac63cf2d598fbdf03dd3df644993","last_reissued_at":"2026-07-05T11:11:21.136357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:21.136357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Performance of ChatGPT on tasks involving physics visual representations: the case of the Brief Electricity and Magnetism Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"physics.ed-ph","authors_text":"Bor Gregorcic, Elias Onerud, Giulia Polverini, Jakob Melin","submitted_at":"2024-12-13T10:00:41Z","abstract_excerpt":"Artificial intelligence-based chatbots are increasingly influencing physics education due to their ability to interpret and respond to textual and visual inputs. This study evaluates the performance of two large multimodal model-based chatbots, ChatGPT-4 and ChatGPT-4o on the Brief Electricity and Magnetism Assessment (BEMA), a conceptual physics inventory rich in visual representations such as vector fields, circuit diagrams, and graphs. Quantitative analysis shows that ChatGPT-4o outperforms both ChatGPT-4 and a large sample of university students, and demonstrates improvements in ChatGPT-4o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10019","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/2412.10019/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":"2412.10019","created_at":"2026-07-05T11:11:21.136418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10019v3","created_at":"2026-07-05T11:11:21.136418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10019","created_at":"2026-07-05T11:11:21.136418+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4VABBGH5QYQ","created_at":"2026-07-05T11:11:21.136418+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4VABBGH5QYQCSMN","created_at":"2026-07-05T11:11:21.136418+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4VABBGH","created_at":"2026-07-05T11:11:21.136418+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06143","citing_title":"Multilingual Performance of a Multimodal Artificial Intelligence System on Multisubject Physics Concept Inventories","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W4VABBGH5QYQCSMNAC4G7ZR2O7","json":"https://pith.science/pith/W4VABBGH5QYQCSMNAC4G7ZR2O7.json","graph_json":"https://pith.science/api/pith-number/W4VABBGH5QYQCSMNAC4G7ZR2O7/graph.json","events_json":"https://pith.science/api/pith-number/W4VABBGH5QYQCSMNAC4G7ZR2O7/events.json","paper":"https://pith.science/paper/W4VABBGH"},"agent_actions":{"view_html":"https://pith.science/pith/W4VABBGH5QYQCSMNAC4G7ZR2O7","download_json":"https://pith.science/pith/W4VABBGH5QYQCSMNAC4G7ZR2O7.json","view_paper":"https://pith.science/paper/W4VABBGH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10019&json=true","fetch_graph":"https://pith.science/api/pith-number/W4VABBGH5QYQCSMNAC4G7ZR2O7/graph.json","fetch_events":"https://pith.science/api/pith-number/W4VABBGH5QYQCSMNAC4G7ZR2O7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4VABBGH5QYQCSMNAC4G7ZR2O7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4VABBGH5QYQCSMNAC4G7ZR2O7/action/storage_attestation","attest_author":"https://pith.science/pith/W4VABBGH5QYQCSMNAC4G7ZR2O7/action/author_attestation","sign_citation":"https://pith.science/pith/W4VABBGH5QYQCSMNAC4G7ZR2O7/action/citation_signature","submit_replication":"https://pith.science/pith/W4VABBGH5QYQCSMNAC4G7ZR2O7/action/replication_record"}},"created_at":"2026-07-05T11:11:21.136418+00:00","updated_at":"2026-07-05T11:11:21.136418+00:00"}