{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HHYIE2QW764TLW255AV7QJL6FT","short_pith_number":"pith:HHYIE2QW","schema_version":"1.0","canonical_sha256":"39f0826a16ffb935db5de82bf8257e2cffcdc3e0afaf9e815e80c7c16b5cea85","source":{"kind":"arxiv","id":"2506.15569","version":1},"attestation_state":"computed","paper":{"title":"SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Chengye Wang, Yifei Shen, Yilun Zhao, Zexi Kuang","submitted_at":"2025-06-18T15:43:26Z","abstract_excerpt":"We introduce SciVer, the first benchmark specifically designed to evaluate the ability of foundation models to verify claims within a multimodal scientific context. SciVer consists of 3,000 expert-annotated examples over 1,113 scientific papers, covering four subsets, each representing a common reasoning type in multimodal scientific claim verification. To enable fine-grained evaluation, each example includes expert-annotated supporting evidence. We assess the performance of 21 state-of-the-art multimodal foundation models, including o4-mini, Gemini-2.5-Flash, Llama-3.2-Vision, and Qwen2.5-VL."},"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":"2506.15569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T15:43:26Z","cross_cats_sorted":[],"title_canon_sha256":"e22b5ef6b80fc066385f4d7ec7bda34ecff3a1f115289882ec2c5666d4ccd7f9","abstract_canon_sha256":"bbc2ec977536347111a50d6717da105cdec75f44a94dc73ad8aa752a9e7a5b4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:46.309108Z","signature_b64":"0aCpDbVz4tmrx0x+mUlh6HSlsPrYk76fnf4MdtnmnC1T47drW/2uwoIvYRHMdMudAMx04uqQrHIXpZ4uwsH1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39f0826a16ffb935db5de82bf8257e2cffcdc3e0afaf9e815e80c7c16b5cea85","last_reissued_at":"2026-07-05T11:23:46.308462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:46.308462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Chengye Wang, Yifei Shen, Yilun Zhao, Zexi Kuang","submitted_at":"2025-06-18T15:43:26Z","abstract_excerpt":"We introduce SciVer, the first benchmark specifically designed to evaluate the ability of foundation models to verify claims within a multimodal scientific context. SciVer consists of 3,000 expert-annotated examples over 1,113 scientific papers, covering four subsets, each representing a common reasoning type in multimodal scientific claim verification. To enable fine-grained evaluation, each example includes expert-annotated supporting evidence. We assess the performance of 21 state-of-the-art multimodal foundation models, including o4-mini, Gemini-2.5-Flash, Llama-3.2-Vision, and Qwen2.5-VL."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15569","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/2506.15569/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":"2506.15569","created_at":"2026-07-05T11:23:46.308552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15569v1","created_at":"2026-07-05T11:23:46.308552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15569","created_at":"2026-07-05T11:23:46.308552+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHYIE2QW764T","created_at":"2026-07-05T11:23:46.308552+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHYIE2QW764TLW25","created_at":"2026-07-05T11:23:46.308552+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHYIE2QW","created_at":"2026-07-05T11:23:46.308552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13300","citing_title":"AbGen: Evaluating Large Language Models in Ablation Study Design and Evaluation for Scientific Research","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HHYIE2QW764TLW255AV7QJL6FT","json":"https://pith.science/pith/HHYIE2QW764TLW255AV7QJL6FT.json","graph_json":"https://pith.science/api/pith-number/HHYIE2QW764TLW255AV7QJL6FT/graph.json","events_json":"https://pith.science/api/pith-number/HHYIE2QW764TLW255AV7QJL6FT/events.json","paper":"https://pith.science/paper/HHYIE2QW"},"agent_actions":{"view_html":"https://pith.science/pith/HHYIE2QW764TLW255AV7QJL6FT","download_json":"https://pith.science/pith/HHYIE2QW764TLW255AV7QJL6FT.json","view_paper":"https://pith.science/paper/HHYIE2QW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15569&json=true","fetch_graph":"https://pith.science/api/pith-number/HHYIE2QW764TLW255AV7QJL6FT/graph.json","fetch_events":"https://pith.science/api/pith-number/HHYIE2QW764TLW255AV7QJL6FT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHYIE2QW764TLW255AV7QJL6FT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHYIE2QW764TLW255AV7QJL6FT/action/storage_attestation","attest_author":"https://pith.science/pith/HHYIE2QW764TLW255AV7QJL6FT/action/author_attestation","sign_citation":"https://pith.science/pith/HHYIE2QW764TLW255AV7QJL6FT/action/citation_signature","submit_replication":"https://pith.science/pith/HHYIE2QW764TLW255AV7QJL6FT/action/replication_record"}},"created_at":"2026-07-05T11:23:46.308552+00:00","updated_at":"2026-07-05T11:23:46.308552+00:00"}