{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NY2IQIFT4VOHNHGXZKFWWQEMWX","short_pith_number":"pith:NY2IQIFT","schema_version":"1.0","canonical_sha256":"6e348820b3e55c769cd7ca8b6b408cb5d920f40b24ac24aa99598cb8fbb4fc06","source":{"kind":"arxiv","id":"2411.04075","version":1},"attestation_state":"computed","paper":{"title":"M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Chuhan Li, Deyuan Li, Yilun Zhao, Yixin Liu, Ziyao Shangguan","submitted_at":"2024-11-06T17:52:01Z","abstract_excerpt":"Existing benchmarks for evaluating foundation models mainly focus on single-document, text-only tasks. However, they often fail to fully capture the complexity of research workflows, which typically involve interpreting non-textual data and gathering information across multiple documents. To address this gap, we introduce M3SciQA, a multi-modal, multi-document scientific question answering benchmark designed for a more comprehensive evaluation of foundation models. M3SciQA consists of 1,452 expert-annotated questions spanning 70 natural language processing paper clusters, where each cluster re"},"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":"2411.04075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-06T17:52:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a483d122fc6d21bf25aacb6b6ef7a5d276295f33cc7cf900a3f7e472b8af839d","abstract_canon_sha256":"50bb0a3cdb20350596c243a39bce26c31c7faf7f29a689b2d1736080272ddcfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:00.444903Z","signature_b64":"O8xefH507jWgtXk6Hvi6NRg5lX50cmo4z6LxjqElROXirsLnHn7cTcBjv4s9GctyRwyICaxCtaEUXxVB0lIFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e348820b3e55c769cd7ca8b6b408cb5d920f40b24ac24aa99598cb8fbb4fc06","last_reissued_at":"2026-07-05T09:32:00.444415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:00.444415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Chuhan Li, Deyuan Li, Yilun Zhao, Yixin Liu, Ziyao Shangguan","submitted_at":"2024-11-06T17:52:01Z","abstract_excerpt":"Existing benchmarks for evaluating foundation models mainly focus on single-document, text-only tasks. However, they often fail to fully capture the complexity of research workflows, which typically involve interpreting non-textual data and gathering information across multiple documents. To address this gap, we introduce M3SciQA, a multi-modal, multi-document scientific question answering benchmark designed for a more comprehensive evaluation of foundation models. M3SciQA consists of 1,452 expert-annotated questions spanning 70 natural language processing paper clusters, where each cluster re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04075","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/2411.04075/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":"2411.04075","created_at":"2026-07-05T09:32:00.444494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04075v1","created_at":"2026-07-05T09:32:00.444494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04075","created_at":"2026-07-05T09:32:00.444494+00:00"},{"alias_kind":"pith_short_12","alias_value":"NY2IQIFT4VOH","created_at":"2026-07-05T09:32:00.444494+00:00"},{"alias_kind":"pith_short_16","alias_value":"NY2IQIFT4VOHNHGX","created_at":"2026-07-05T09:32:00.444494+00:00"},{"alias_kind":"pith_short_8","alias_value":"NY2IQIFT","created_at":"2026-07-05T09:32:00.444494+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/NY2IQIFT4VOHNHGXZKFWWQEMWX","json":"https://pith.science/pith/NY2IQIFT4VOHNHGXZKFWWQEMWX.json","graph_json":"https://pith.science/api/pith-number/NY2IQIFT4VOHNHGXZKFWWQEMWX/graph.json","events_json":"https://pith.science/api/pith-number/NY2IQIFT4VOHNHGXZKFWWQEMWX/events.json","paper":"https://pith.science/paper/NY2IQIFT"},"agent_actions":{"view_html":"https://pith.science/pith/NY2IQIFT4VOHNHGXZKFWWQEMWX","download_json":"https://pith.science/pith/NY2IQIFT4VOHNHGXZKFWWQEMWX.json","view_paper":"https://pith.science/paper/NY2IQIFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04075&json=true","fetch_graph":"https://pith.science/api/pith-number/NY2IQIFT4VOHNHGXZKFWWQEMWX/graph.json","fetch_events":"https://pith.science/api/pith-number/NY2IQIFT4VOHNHGXZKFWWQEMWX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NY2IQIFT4VOHNHGXZKFWWQEMWX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NY2IQIFT4VOHNHGXZKFWWQEMWX/action/storage_attestation","attest_author":"https://pith.science/pith/NY2IQIFT4VOHNHGXZKFWWQEMWX/action/author_attestation","sign_citation":"https://pith.science/pith/NY2IQIFT4VOHNHGXZKFWWQEMWX/action/citation_signature","submit_replication":"https://pith.science/pith/NY2IQIFT4VOHNHGXZKFWWQEMWX/action/replication_record"}},"created_at":"2026-07-05T09:32:00.444494+00:00","updated_at":"2026-07-05T09:32:00.444494+00:00"}