{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZC4PDJS6P2TTBNXPQV4544WADH","short_pith_number":"pith:ZC4PDJS6","schema_version":"1.0","canonical_sha256":"c8b8f1a65e7ea730b6ef8579de72c019f959281d5fe288f41b54cfb6ee0d7d3d","source":{"kind":"arxiv","id":"2603.27958","version":2},"attestation_state":"computed","paper":{"title":"CARV: A Diagnostic Benchmark for Compositional Analogical Reasoning in Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lu Lin, Minhao Cheng, Xiaohan Zou, Yongkang Du","submitted_at":"2026-03-30T02:22:30Z","abstract_excerpt":"Analogical reasoning tests a fundamental aspect of human cognition: mapping the relation from one pair of objects to another. Existing evaluations of this ability in multimodal large language models (MLLMs) overlook the ability to compose rules from multiple sources, a critical component of higher-order intelligence. To close this gap, we introduce CARV (Compositional Analogical Reasoning in Vision), a novel task together with a 5,500-sample dataset as the first diagnostic benchmark. We extend the analogy from a single pair to multiple pairs, which requires MLLMs to extract symbolic rules from"},"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":"2603.27958","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-30T02:22:30Z","cross_cats_sorted":[],"title_canon_sha256":"62038722757a977d185fc2bec3bf00e4ed251bd0d76f1f64e6f487e31ca71b70","abstract_canon_sha256":"6fd1e6c5b798bbda4d38890c38899505fb6a25e61610250b5fe5265a96cf78c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:20:46.786897Z","signature_b64":"sl0PVvAp/HIVAiHUd9qhkR+cFUBALLWot+7ax26vwQOA/OVdNXjzn9nEvTukaa8OolkP2bcJ11A2iiLvwsi4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8b8f1a65e7ea730b6ef8579de72c019f959281d5fe288f41b54cfb6ee0d7d3d","last_reissued_at":"2026-07-21T01:20:46.785854Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:20:46.785854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CARV: A Diagnostic Benchmark for Compositional Analogical Reasoning in Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lu Lin, Minhao Cheng, Xiaohan Zou, Yongkang Du","submitted_at":"2026-03-30T02:22:30Z","abstract_excerpt":"Analogical reasoning tests a fundamental aspect of human cognition: mapping the relation from one pair of objects to another. Existing evaluations of this ability in multimodal large language models (MLLMs) overlook the ability to compose rules from multiple sources, a critical component of higher-order intelligence. To close this gap, we introduce CARV (Compositional Analogical Reasoning in Vision), a novel task together with a 5,500-sample dataset as the first diagnostic benchmark. We extend the analogy from a single pair to multiple pairs, which requires MLLMs to extract symbolic rules from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.27958","kind":"arxiv","version":2},"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/2603.27958/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":"2603.27958","created_at":"2026-07-21T01:20:46.786341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.27958v2","created_at":"2026-07-21T01:20:46.786341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.27958","created_at":"2026-07-21T01:20:46.786341+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZC4PDJS6P2TT","created_at":"2026-07-21T01:20:46.786341+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZC4PDJS6P2TTBNXP","created_at":"2026-07-21T01:20:46.786341+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZC4PDJS6","created_at":"2026-07-21T01:20:46.786341+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/ZC4PDJS6P2TTBNXPQV4544WADH","json":"https://pith.science/pith/ZC4PDJS6P2TTBNXPQV4544WADH.json","graph_json":"https://pith.science/api/pith-number/ZC4PDJS6P2TTBNXPQV4544WADH/graph.json","events_json":"https://pith.science/api/pith-number/ZC4PDJS6P2TTBNXPQV4544WADH/events.json","paper":"https://pith.science/paper/ZC4PDJS6"},"agent_actions":{"view_html":"https://pith.science/pith/ZC4PDJS6P2TTBNXPQV4544WADH","download_json":"https://pith.science/pith/ZC4PDJS6P2TTBNXPQV4544WADH.json","view_paper":"https://pith.science/paper/ZC4PDJS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.27958&json=true","fetch_graph":"https://pith.science/api/pith-number/ZC4PDJS6P2TTBNXPQV4544WADH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZC4PDJS6P2TTBNXPQV4544WADH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZC4PDJS6P2TTBNXPQV4544WADH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZC4PDJS6P2TTBNXPQV4544WADH/action/storage_attestation","attest_author":"https://pith.science/pith/ZC4PDJS6P2TTBNXPQV4544WADH/action/author_attestation","sign_citation":"https://pith.science/pith/ZC4PDJS6P2TTBNXPQV4544WADH/action/citation_signature","submit_replication":"https://pith.science/pith/ZC4PDJS6P2TTBNXPQV4544WADH/action/replication_record"}},"created_at":"2026-07-21T01:20:46.786341+00:00","updated_at":"2026-07-21T01:20:46.786341+00:00"}