{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NSB3RKAXWXODVDVBFRRQRAQFVQ","short_pith_number":"pith:NSB3RKAX","schema_version":"1.0","canonical_sha256":"6c83b8a817b5dc3a8ea12c63088205ac288b50afa626be8247818a01b8eb237b","source":{"kind":"arxiv","id":"2412.13540","version":3},"attestation_state":"computed","paper":{"title":"Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jun Yu, Kehai Chen, Min Zhang, Xuefeng Bai, Yang Xiang, Yingjie Zhu","submitted_at":"2024-12-18T06:35:18Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across diverse tasks. Despite great success, recent studies show that LVLMs encounter substantial limitations when engaging with visual graphs. To study the reason behind these limitations, we propose VGCure, a comprehensive benchmark covering 22 tasks for examining the fundamental graph understanding and reasoning capacities of LVLMs. Extensive evaluations conducted on 14 LVLMs reveal that LVLMs are weak in basic graph understanding and reasoning tasks, particularly those concerning relational or structurally comple"},"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":"2412.13540","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T06:35:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a104a1c84249f4e08a201c1602f0fa5e5edf1ebe5a0353a8696fdb28081555b3","abstract_canon_sha256":"98a7688602960c00896b787bb79f05743a51fc95cf85a14dabff6e75abe097df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:53.387581Z","signature_b64":"JGonFYftu/P5dk3U7oCrsLwOg+orH7cF69dwVXTmt1TccTeJGMbpfendMmA8E1C1wiedga8hdMkXr2USDrRrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c83b8a817b5dc3a8ea12c63088205ac288b50afa626be8247818a01b8eb237b","last_reissued_at":"2026-07-05T11:16:53.386930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:53.386930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Jun Yu, Kehai Chen, Min Zhang, Xuefeng Bai, Yang Xiang, Yingjie Zhu","submitted_at":"2024-12-18T06:35:18Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across diverse tasks. Despite great success, recent studies show that LVLMs encounter substantial limitations when engaging with visual graphs. To study the reason behind these limitations, we propose VGCure, a comprehensive benchmark covering 22 tasks for examining the fundamental graph understanding and reasoning capacities of LVLMs. Extensive evaluations conducted on 14 LVLMs reveal that LVLMs are weak in basic graph understanding and reasoning tasks, particularly those concerning relational or structurally comple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13540","kind":"arxiv","version":3},"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/2412.13540/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":"2412.13540","created_at":"2026-07-05T11:16:53.387003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13540v3","created_at":"2026-07-05T11:16:53.387003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13540","created_at":"2026-07-05T11:16:53.387003+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSB3RKAXWXOD","created_at":"2026-07-05T11:16:53.387003+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSB3RKAXWXODVDVB","created_at":"2026-07-05T11:16:53.387003+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSB3RKAX","created_at":"2026-07-05T11:16:53.387003+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01748","citing_title":"Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NSB3RKAXWXODVDVBFRRQRAQFVQ","json":"https://pith.science/pith/NSB3RKAXWXODVDVBFRRQRAQFVQ.json","graph_json":"https://pith.science/api/pith-number/NSB3RKAXWXODVDVBFRRQRAQFVQ/graph.json","events_json":"https://pith.science/api/pith-number/NSB3RKAXWXODVDVBFRRQRAQFVQ/events.json","paper":"https://pith.science/paper/NSB3RKAX"},"agent_actions":{"view_html":"https://pith.science/pith/NSB3RKAXWXODVDVBFRRQRAQFVQ","download_json":"https://pith.science/pith/NSB3RKAXWXODVDVBFRRQRAQFVQ.json","view_paper":"https://pith.science/paper/NSB3RKAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13540&json=true","fetch_graph":"https://pith.science/api/pith-number/NSB3RKAXWXODVDVBFRRQRAQFVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NSB3RKAXWXODVDVBFRRQRAQFVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSB3RKAXWXODVDVBFRRQRAQFVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSB3RKAXWXODVDVBFRRQRAQFVQ/action/storage_attestation","attest_author":"https://pith.science/pith/NSB3RKAXWXODVDVBFRRQRAQFVQ/action/author_attestation","sign_citation":"https://pith.science/pith/NSB3RKAXWXODVDVBFRRQRAQFVQ/action/citation_signature","submit_replication":"https://pith.science/pith/NSB3RKAXWXODVDVBFRRQRAQFVQ/action/replication_record"}},"created_at":"2026-07-05T11:16:53.387003+00:00","updated_at":"2026-07-05T11:16:53.387003+00:00"}