{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7UULODPIO4CMLY324CM2Y5CLT7","short_pith_number":"pith:7UULODPI","schema_version":"1.0","canonical_sha256":"fd28b70de87704c5e37ae099ac744b9feaca6add21cbce222711079e4d6234c1","source":{"kind":"arxiv","id":"2506.06242","version":1},"attestation_state":"computed","paper":{"title":"Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daniela Rus, Peyman M. Kiasari, Radu Grosu, Zahra Babaiee","submitted_at":"2025-06-06T17:06:25Z","abstract_excerpt":"Recent advancements in multimodal large language models have driven breakthroughs in visual question answering. Yet, a critical gap persists, `conceptualization'-the ability to recognize and reason about the same concept despite variations in visual form, a basic ability of human reasoning. To address this challenge, we introduce the Visual Graph Arena (VGA), a dataset featuring six graph-based tasks designed to evaluate and improve AI systems' capacity for visual abstraction. VGA uses diverse graph layouts (e.g., Kamada-Kawai vs. planar) to test reasoning independent of visual form. Experimen"},"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":"2506.06242","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T17:06:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c44a6c41c0eeb206ce46fe4ae7549a3487ee21eaa6aa3376939a1678a0a7a60a","abstract_canon_sha256":"64d085d5a41fb970e0c816d8db9675e69bda98cd0a8dd83a6476731097d1c211"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:27.980397Z","signature_b64":"XiziR8EALG7ZMGcSmGCsZJKaLTPZHD8DIQl4rdhRKtCcPSNRMcofhePkbHvg9z6k5VK6tlhYKiV2/Q0TCI9HBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd28b70de87704c5e37ae099ac744b9feaca6add21cbce222711079e4d6234c1","last_reissued_at":"2026-07-05T11:17:27.979885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:27.979885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Daniela Rus, Peyman M. Kiasari, Radu Grosu, Zahra Babaiee","submitted_at":"2025-06-06T17:06:25Z","abstract_excerpt":"Recent advancements in multimodal large language models have driven breakthroughs in visual question answering. Yet, a critical gap persists, `conceptualization'-the ability to recognize and reason about the same concept despite variations in visual form, a basic ability of human reasoning. To address this challenge, we introduce the Visual Graph Arena (VGA), a dataset featuring six graph-based tasks designed to evaluate and improve AI systems' capacity for visual abstraction. VGA uses diverse graph layouts (e.g., Kamada-Kawai vs. planar) to test reasoning independent of visual form. Experimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06242","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/2506.06242/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":"2506.06242","created_at":"2026-07-05T11:17:27.979942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06242v1","created_at":"2026-07-05T11:17:27.979942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06242","created_at":"2026-07-05T11:17:27.979942+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UULODPIO4CM","created_at":"2026-07-05T11:17:27.979942+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UULODPIO4CMLY32","created_at":"2026-07-05T11:17:27.979942+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UULODPI","created_at":"2026-07-05T11:17:27.979942+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/7UULODPIO4CMLY324CM2Y5CLT7","json":"https://pith.science/pith/7UULODPIO4CMLY324CM2Y5CLT7.json","graph_json":"https://pith.science/api/pith-number/7UULODPIO4CMLY324CM2Y5CLT7/graph.json","events_json":"https://pith.science/api/pith-number/7UULODPIO4CMLY324CM2Y5CLT7/events.json","paper":"https://pith.science/paper/7UULODPI"},"agent_actions":{"view_html":"https://pith.science/pith/7UULODPIO4CMLY324CM2Y5CLT7","download_json":"https://pith.science/pith/7UULODPIO4CMLY324CM2Y5CLT7.json","view_paper":"https://pith.science/paper/7UULODPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06242&json=true","fetch_graph":"https://pith.science/api/pith-number/7UULODPIO4CMLY324CM2Y5CLT7/graph.json","fetch_events":"https://pith.science/api/pith-number/7UULODPIO4CMLY324CM2Y5CLT7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UULODPIO4CMLY324CM2Y5CLT7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UULODPIO4CMLY324CM2Y5CLT7/action/storage_attestation","attest_author":"https://pith.science/pith/7UULODPIO4CMLY324CM2Y5CLT7/action/author_attestation","sign_citation":"https://pith.science/pith/7UULODPIO4CMLY324CM2Y5CLT7/action/citation_signature","submit_replication":"https://pith.science/pith/7UULODPIO4CMLY324CM2Y5CLT7/action/replication_record"}},"created_at":"2026-07-05T11:17:27.979942+00:00","updated_at":"2026-07-05T11:17:27.979942+00:00"}