{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PCRQIQEX3DBIF3E4YUWM2W4QDZ","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":"42ecfe5fd66800bd66cc2ad6e417f08ae64b460ad7cae9b726830dd2673c5b4a","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T19:31:35Z","title_canon_sha256":"b3ff352d27a8addc4a3a77d1824c32efec001249533c44a7b2afb53a61545adc"},"schema_version":"1.0","source":{"id":"2506.21596","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21596","created_at":"2026-07-05T11:37:24Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21596v2","created_at":"2026-07-05T11:37:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21596","created_at":"2026-07-05T11:37:24Z"},{"alias_kind":"pith_short_12","alias_value":"PCRQIQEX3DBI","created_at":"2026-07-05T11:37:24Z"},{"alias_kind":"pith_short_16","alias_value":"PCRQIQEX3DBIF3E4","created_at":"2026-07-05T11:37:24Z"},{"alias_kind":"pith_short_8","alias_value":"PCRQIQEX","created_at":"2026-07-05T11:37:24Z"}],"graph_snapshots":[{"event_id":"sha256:c226b4eb3042e0e539b62d35b1dd17981b2b2e8a4c5b0fce0d4b16c8de07392c","target":"graph","created_at":"2026-07-05T11:37:24Z","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/2506.21596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have shown success in vision-language tasks, but their ability to reason over complex educational materials remains largely untested. This work presents the first evaluation of state-of-the-art MLLMs, including LLaVA-1.5 and LLaMA 3.2-Vision, on the textbook question answering (TQA) task using the CK12-QA dataset. We introduce a multimodal retrieval-augmented generation (RAG) pipeline to simulate real-world learning by providing relevant lesson paragraphs and diagrams as context. Our zero-shot experiments reveal a critical trade-off: while retrieved con","authors_text":"Ali Alkhathlan, Amani Jamal, Anas Zafar, Areej Alhothali, Hessa A. Alawwad, Usman Naseem","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T19:31:35Z","title":"Evaluating Multimodal Large Language Models on Educational Textbook Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21596","kind":"arxiv","version":2},"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:cfee61d9e351a189c5ededf334941dcf0a087f0309da7e8afe09e6b1f0efe58d","target":"record","created_at":"2026-07-05T11:37:24Z","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":"42ecfe5fd66800bd66cc2ad6e417f08ae64b460ad7cae9b726830dd2673c5b4a","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T19:31:35Z","title_canon_sha256":"b3ff352d27a8addc4a3a77d1824c32efec001249533c44a7b2afb53a61545adc"},"schema_version":"1.0","source":{"id":"2506.21596","kind":"arxiv","version":2}},"canonical_sha256":"78a3044097d8c282ec9cc52ccd5b901e68855780591df029db5e4758ea32bd9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78a3044097d8c282ec9cc52ccd5b901e68855780591df029db5e4758ea32bd9a","first_computed_at":"2026-07-05T11:37:24.524728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:24.524728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nl7xNjDRFp9fnJLHYDkevtV5U/F0KGovHloik+tnVBbXIX7RyqFPzxbASyJWwJgO1hl/FD2BRSKLEelFZTPIBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:24.525244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21596","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfee61d9e351a189c5ededf334941dcf0a087f0309da7e8afe09e6b1f0efe58d","sha256:c226b4eb3042e0e539b62d35b1dd17981b2b2e8a4c5b0fce0d4b16c8de07392c"],"state_sha256":"ed36ee17a2126722a0fa3c7eedd7899987156dcfae08b87d989de4040009da96"}