{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H3R3OCYGTXZD7A75Q6V2OQCEQB","short_pith_number":"pith:H3R3OCYG","schema_version":"1.0","canonical_sha256":"3ee3b70b069df23f83fd87aba74044807f80d2bc9a05014704b8a4dc4de729e5","source":{"kind":"arxiv","id":"2503.10627","version":1},"attestation_state":"computed","paper":{"title":"SciVerse: Unveiling the Knowledge Comprehension and Visual Reasoning of LMMs on Multi-modal Scientific Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Dongzhi Jiang, Hao Chen, Jialin Gao, Jiaze Wang, Pheng-Ann Heng, Ray Zhang, Ziyu Guo","submitted_at":"2025-03-13T17:59:32Z","abstract_excerpt":"The rapid advancement of Large Multi-modal Models (LMMs) has enabled their application in scientific problem-solving, yet their fine-grained capabilities remain under-explored. In this paper, we introduce SciVerse, a multi-modal scientific evaluation benchmark to thoroughly assess LMMs across 5,735 test instances in five distinct versions. We aim to investigate three key dimensions of LMMs: scientific knowledge comprehension, multi-modal content interpretation, and Chain-of-Thought (CoT) reasoning. To unveil whether LMMs possess sufficient scientific expertise, we first transform each problem "},"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":"2503.10627","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:59:32Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"aa784df1445694be99b1be22d15466d77a6f4b60cb5f67d57b93d2d48296c9de","abstract_canon_sha256":"1eec04ce39e04117ec65a9d3f38203f0a05e29e98e2bd3d651cc5a78a91ca7dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:49.258538Z","signature_b64":"zAiJZc15S5lve836LOaAvPwM1pZWE8viHS0pOuGlBw3VTGPOVgpQ+KRWsLbgm+h5lSucLFwDjjMTm+cEZQrFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ee3b70b069df23f83fd87aba74044807f80d2bc9a05014704b8a4dc4de729e5","last_reissued_at":"2026-07-05T10:30:49.257903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:49.257903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciVerse: Unveiling the Knowledge Comprehension and Visual Reasoning of LMMs on Multi-modal Scientific Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Dongzhi Jiang, Hao Chen, Jialin Gao, Jiaze Wang, Pheng-Ann Heng, Ray Zhang, Ziyu Guo","submitted_at":"2025-03-13T17:59:32Z","abstract_excerpt":"The rapid advancement of Large Multi-modal Models (LMMs) has enabled their application in scientific problem-solving, yet their fine-grained capabilities remain under-explored. In this paper, we introduce SciVerse, a multi-modal scientific evaluation benchmark to thoroughly assess LMMs across 5,735 test instances in five distinct versions. We aim to investigate three key dimensions of LMMs: scientific knowledge comprehension, multi-modal content interpretation, and Chain-of-Thought (CoT) reasoning. To unveil whether LMMs possess sufficient scientific expertise, we first transform each problem "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10627","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/2503.10627/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":"2503.10627","created_at":"2026-07-05T10:30:49.257967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10627v1","created_at":"2026-07-05T10:30:49.257967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10627","created_at":"2026-07-05T10:30:49.257967+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3R3OCYGTXZD","created_at":"2026-07-05T10:30:49.257967+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3R3OCYGTXZD7A75","created_at":"2026-07-05T10:30:49.257967+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3R3OCYG","created_at":"2026-07-05T10:30:49.257967+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17888","citing_title":"MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08034","citing_title":"Sci-Rho: A Multilingual Visually-Grounded Symbolic Benchmark for STEM Problems","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3R3OCYGTXZD7A75Q6V2OQCEQB","json":"https://pith.science/pith/H3R3OCYGTXZD7A75Q6V2OQCEQB.json","graph_json":"https://pith.science/api/pith-number/H3R3OCYGTXZD7A75Q6V2OQCEQB/graph.json","events_json":"https://pith.science/api/pith-number/H3R3OCYGTXZD7A75Q6V2OQCEQB/events.json","paper":"https://pith.science/paper/H3R3OCYG"},"agent_actions":{"view_html":"https://pith.science/pith/H3R3OCYGTXZD7A75Q6V2OQCEQB","download_json":"https://pith.science/pith/H3R3OCYGTXZD7A75Q6V2OQCEQB.json","view_paper":"https://pith.science/paper/H3R3OCYG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10627&json=true","fetch_graph":"https://pith.science/api/pith-number/H3R3OCYGTXZD7A75Q6V2OQCEQB/graph.json","fetch_events":"https://pith.science/api/pith-number/H3R3OCYGTXZD7A75Q6V2OQCEQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3R3OCYGTXZD7A75Q6V2OQCEQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3R3OCYGTXZD7A75Q6V2OQCEQB/action/storage_attestation","attest_author":"https://pith.science/pith/H3R3OCYGTXZD7A75Q6V2OQCEQB/action/author_attestation","sign_citation":"https://pith.science/pith/H3R3OCYGTXZD7A75Q6V2OQCEQB/action/citation_signature","submit_replication":"https://pith.science/pith/H3R3OCYGTXZD7A75Q6V2OQCEQB/action/replication_record"}},"created_at":"2026-07-05T10:30:49.257967+00:00","updated_at":"2026-07-05T10:30:49.257967+00:00"}