{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NLFCQ4SWMJL2ZHNQTUVGXCR2J2","short_pith_number":"pith:NLFCQ4SW","schema_version":"1.0","canonical_sha256":"6aca2872566257ac9db09d2a6b8a3a4ea7fe139f9a5b32675cc961a831b90dc1","source":{"kind":"arxiv","id":"2507.03013","version":1},"attestation_state":"computed","paper":{"title":"Challenges for AI in Multimodal STEM Assessments: a Human-AI Comparison","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Anna Sotnikova, Antoine Bosselut, Aymeric de Chillaz, Patrick Jermann","submitted_at":"2025-07-02T12:06:46Z","abstract_excerpt":"Generative AI systems have rapidly advanced, with multimodal input capabilities enabling reasoning beyond text-based tasks. In education, these advancements could influence assessment design and question answering, presenting both opportunities and challenges. To investigate these effects, we introduce a high-quality dataset of 201 university-level STEM questions, manually annotated with features such as image type, role, problem complexity, and question format. Our study analyzes how these features affect generative AI performance compared to students. We evaluate four model families with fiv"},"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":"2507.03013","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2025-07-02T12:06:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"195c82f692e38a96a72295f048f2db89ffee1caa88f1c64abbef12e0d8ff878a","abstract_canon_sha256":"46cfe9fd0efc56ae985594cf3c7e5a26427d3e14502e78853ec824449b88e3c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:50.711825Z","signature_b64":"Gs/PvidCns3+ziN1db+kkUzGc7zzxnWkdkVDyNUu7do788mPDDd2bc7WqrvBpfuef3VYWG3XdjypgAH04+p6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6aca2872566257ac9db09d2a6b8a3a4ea7fe139f9a5b32675cc961a831b90dc1","last_reissued_at":"2026-07-05T11:31:50.711307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:50.711307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Challenges for AI in Multimodal STEM Assessments: a Human-AI Comparison","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Anna Sotnikova, Antoine Bosselut, Aymeric de Chillaz, Patrick Jermann","submitted_at":"2025-07-02T12:06:46Z","abstract_excerpt":"Generative AI systems have rapidly advanced, with multimodal input capabilities enabling reasoning beyond text-based tasks. In education, these advancements could influence assessment design and question answering, presenting both opportunities and challenges. To investigate these effects, we introduce a high-quality dataset of 201 university-level STEM questions, manually annotated with features such as image type, role, problem complexity, and question format. Our study analyzes how these features affect generative AI performance compared to students. We evaluate four model families with fiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03013","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/2507.03013/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":"2507.03013","created_at":"2026-07-05T11:31:50.711369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03013v1","created_at":"2026-07-05T11:31:50.711369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03013","created_at":"2026-07-05T11:31:50.711369+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLFCQ4SWMJL2","created_at":"2026-07-05T11:31:50.711369+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLFCQ4SWMJL2ZHNQ","created_at":"2026-07-05T11:31:50.711369+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLFCQ4SW","created_at":"2026-07-05T11:31:50.711369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NLFCQ4SWMJL2ZHNQTUVGXCR2J2","json":"https://pith.science/pith/NLFCQ4SWMJL2ZHNQTUVGXCR2J2.json","graph_json":"https://pith.science/api/pith-number/NLFCQ4SWMJL2ZHNQTUVGXCR2J2/graph.json","events_json":"https://pith.science/api/pith-number/NLFCQ4SWMJL2ZHNQTUVGXCR2J2/events.json","paper":"https://pith.science/paper/NLFCQ4SW"},"agent_actions":{"view_html":"https://pith.science/pith/NLFCQ4SWMJL2ZHNQTUVGXCR2J2","download_json":"https://pith.science/pith/NLFCQ4SWMJL2ZHNQTUVGXCR2J2.json","view_paper":"https://pith.science/paper/NLFCQ4SW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03013&json=true","fetch_graph":"https://pith.science/api/pith-number/NLFCQ4SWMJL2ZHNQTUVGXCR2J2/graph.json","fetch_events":"https://pith.science/api/pith-number/NLFCQ4SWMJL2ZHNQTUVGXCR2J2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLFCQ4SWMJL2ZHNQTUVGXCR2J2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLFCQ4SWMJL2ZHNQTUVGXCR2J2/action/storage_attestation","attest_author":"https://pith.science/pith/NLFCQ4SWMJL2ZHNQTUVGXCR2J2/action/author_attestation","sign_citation":"https://pith.science/pith/NLFCQ4SWMJL2ZHNQTUVGXCR2J2/action/citation_signature","submit_replication":"https://pith.science/pith/NLFCQ4SWMJL2ZHNQTUVGXCR2J2/action/replication_record"}},"created_at":"2026-07-05T11:31:50.711369+00:00","updated_at":"2026-07-05T11:31:50.711369+00:00"}