{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ARJZBYAAXRAFWRTZ73D34NZTVJ","short_pith_number":"pith:ARJZBYAA","schema_version":"1.0","canonical_sha256":"045390e000bc405b4679fec7be3733aa5d87d6279ca59dffeec1f9b53bf56832","source":{"kind":"arxiv","id":"2405.04950","version":1},"attestation_state":"computed","paper":{"title":"VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Baotian Hu, Haoyuan Shi, Longyue Wang, Min Zhang, Wei Wang, Yunxin Li","submitted_at":"2024-05-08T10:42:48Z","abstract_excerpt":"Large Multimodal Models (LMMs) have achieved impressive success in visual understanding and reasoning, remarkably improving the performance of mathematical reasoning in a visual context. Yet, a challenging type of visual math lies in the multimodal graph theory problem, which demands that LMMs understand the graphical structures accurately and perform multi-step reasoning on the visual graph. Additionally, exploring multimodal graph theory problems will lead to more effective strategies in fields like biology, transportation, and robotics planning. To step forward in this direction, we are the"},"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":"2405.04950","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-08T10:42:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"afae54d5470615c8312bca4683cf7b0736edf5e964fcde56c779eff4d9b3c1ca","abstract_canon_sha256":"2f9361db187ceae33bef8bf1d1db2ca21668f38df9428d984ad9284fd33bf46c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:56.483234Z","signature_b64":"ZODsGmVsa6wUAQIwyi7b0INy97FmjfA3SZvWVulI3RYgBPquJd6tKIKYOo588HpMwQkD86uIyGkDzMnzQiFaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"045390e000bc405b4679fec7be3733aa5d87d6279ca59dffeec1f9b53bf56832","last_reissued_at":"2026-07-05T08:16:56.482769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:56.482769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Context","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Baotian Hu, Haoyuan Shi, Longyue Wang, Min Zhang, Wei Wang, Yunxin Li","submitted_at":"2024-05-08T10:42:48Z","abstract_excerpt":"Large Multimodal Models (LMMs) have achieved impressive success in visual understanding and reasoning, remarkably improving the performance of mathematical reasoning in a visual context. Yet, a challenging type of visual math lies in the multimodal graph theory problem, which demands that LMMs understand the graphical structures accurately and perform multi-step reasoning on the visual graph. Additionally, exploring multimodal graph theory problems will lead to more effective strategies in fields like biology, transportation, and robotics planning. To step forward in this direction, we are the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04950","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/2405.04950/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":"2405.04950","created_at":"2026-07-05T08:16:56.482825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04950v1","created_at":"2026-07-05T08:16:56.482825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04950","created_at":"2026-07-05T08:16:56.482825+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARJZBYAAXRAF","created_at":"2026-07-05T08:16:56.482825+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARJZBYAAXRAFWRTZ","created_at":"2026-07-05T08:16:56.482825+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARJZBYAA","created_at":"2026-07-05T08:16:56.482825+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06345","citing_title":"Harnessing Adaptive Topology Representations for Zero-Shot Graph Question Answering","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARJZBYAAXRAFWRTZ73D34NZTVJ","json":"https://pith.science/pith/ARJZBYAAXRAFWRTZ73D34NZTVJ.json","graph_json":"https://pith.science/api/pith-number/ARJZBYAAXRAFWRTZ73D34NZTVJ/graph.json","events_json":"https://pith.science/api/pith-number/ARJZBYAAXRAFWRTZ73D34NZTVJ/events.json","paper":"https://pith.science/paper/ARJZBYAA"},"agent_actions":{"view_html":"https://pith.science/pith/ARJZBYAAXRAFWRTZ73D34NZTVJ","download_json":"https://pith.science/pith/ARJZBYAAXRAFWRTZ73D34NZTVJ.json","view_paper":"https://pith.science/paper/ARJZBYAA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04950&json=true","fetch_graph":"https://pith.science/api/pith-number/ARJZBYAAXRAFWRTZ73D34NZTVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ARJZBYAAXRAFWRTZ73D34NZTVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARJZBYAAXRAFWRTZ73D34NZTVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARJZBYAAXRAFWRTZ73D34NZTVJ/action/storage_attestation","attest_author":"https://pith.science/pith/ARJZBYAAXRAFWRTZ73D34NZTVJ/action/author_attestation","sign_citation":"https://pith.science/pith/ARJZBYAAXRAFWRTZ73D34NZTVJ/action/citation_signature","submit_replication":"https://pith.science/pith/ARJZBYAAXRAFWRTZ73D34NZTVJ/action/replication_record"}},"created_at":"2026-07-05T08:16:56.482825+00:00","updated_at":"2026-07-05T08:16:56.482825+00:00"}