{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7Z5VT4N3GL3HAVT55OQQ4WP4RK","short_pith_number":"pith:7Z5VT4N3","schema_version":"1.0","canonical_sha256":"fe7b59f1bb32f670567deba10e59fc8aa95867ea60461e1aed0753fd3b5add66","source":{"kind":"arxiv","id":"2402.02130","version":5},"attestation_state":"computed","paper":{"title":"GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"James T. Kwok, Qi Wu, Shuai Fu, Weisen Jiang, Yanbin Wei, Yu Zhang, Zejian Zhang, Zhixiong Zeng","submitted_at":"2024-02-03T12:19:47Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used for various tasks with graph structures. Though LLMs can process graph information in a textual format, they overlook the rich vision modality, which is an intuitive way for humans to comprehend structural information and conduct general graph reasoning. The potential benefits and capabilities of representing graph structures as visual images (i.e., $\\textit{visual graph}$) are still unexplored. To fill the gap, we innovatively propose an end-to-end framework, called $\\textbf{G}$raph to v$\\textbf{I}$sual and $\\textbf{T}$extual Integr$\\textbf{A"},"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":"2402.02130","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T12:19:47Z","cross_cats_sorted":[],"title_canon_sha256":"a6d72f07ec1d80c3c7fdb378431c782fd84f569aa088919cf89f87915800dedf","abstract_canon_sha256":"329aeea9762500ba890a3faf12b931ac858520f31b29ee2ee413ba16e39de3c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:47.412767Z","signature_b64":"ZgERxsifRBAsRFNHURQ1YQIzu94HJ1IGMqZWQNnFwdSmZifPW/xSY2+sKnQm2O8yRvDu1IeDnNy19e3k6YoXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe7b59f1bb32f670567deba10e59fc8aa95867ea60461e1aed0753fd3b5add66","last_reissued_at":"2026-07-05T09:28:47.412279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:47.412279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"James T. Kwok, Qi Wu, Shuai Fu, Weisen Jiang, Yanbin Wei, Yu Zhang, Zejian Zhang, Zhixiong Zeng","submitted_at":"2024-02-03T12:19:47Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used for various tasks with graph structures. Though LLMs can process graph information in a textual format, they overlook the rich vision modality, which is an intuitive way for humans to comprehend structural information and conduct general graph reasoning. The potential benefits and capabilities of representing graph structures as visual images (i.e., $\\textit{visual graph}$) are still unexplored. To fill the gap, we innovatively propose an end-to-end framework, called $\\textbf{G}$raph to v$\\textbf{I}$sual and $\\textbf{T}$extual Integr$\\textbf{A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02130","kind":"arxiv","version":5},"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/2402.02130/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":"2402.02130","created_at":"2026-07-05T09:28:47.412334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02130v5","created_at":"2026-07-05T09:28:47.412334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02130","created_at":"2026-07-05T09:28:47.412334+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Z5VT4N3GL3H","created_at":"2026-07-05T09:28:47.412334+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Z5VT4N3GL3HAVT5","created_at":"2026-07-05T09:28:47.412334+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Z5VT4N3","created_at":"2026-07-05T09:28:47.412334+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.20814","citing_title":"SPHINX: A Synthetic Environment for Visual Perception and Reasoning","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2505.07062","citing_title":"Seed1.5-VL Technical Report","ref_index":147,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7Z5VT4N3GL3HAVT55OQQ4WP4RK","json":"https://pith.science/pith/7Z5VT4N3GL3HAVT55OQQ4WP4RK.json","graph_json":"https://pith.science/api/pith-number/7Z5VT4N3GL3HAVT55OQQ4WP4RK/graph.json","events_json":"https://pith.science/api/pith-number/7Z5VT4N3GL3HAVT55OQQ4WP4RK/events.json","paper":"https://pith.science/paper/7Z5VT4N3"},"agent_actions":{"view_html":"https://pith.science/pith/7Z5VT4N3GL3HAVT55OQQ4WP4RK","download_json":"https://pith.science/pith/7Z5VT4N3GL3HAVT55OQQ4WP4RK.json","view_paper":"https://pith.science/paper/7Z5VT4N3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02130&json=true","fetch_graph":"https://pith.science/api/pith-number/7Z5VT4N3GL3HAVT55OQQ4WP4RK/graph.json","fetch_events":"https://pith.science/api/pith-number/7Z5VT4N3GL3HAVT55OQQ4WP4RK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Z5VT4N3GL3HAVT55OQQ4WP4RK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Z5VT4N3GL3HAVT55OQQ4WP4RK/action/storage_attestation","attest_author":"https://pith.science/pith/7Z5VT4N3GL3HAVT55OQQ4WP4RK/action/author_attestation","sign_citation":"https://pith.science/pith/7Z5VT4N3GL3HAVT55OQQ4WP4RK/action/citation_signature","submit_replication":"https://pith.science/pith/7Z5VT4N3GL3HAVT55OQQ4WP4RK/action/replication_record"}},"created_at":"2026-07-05T09:28:47.412334+00:00","updated_at":"2026-07-05T09:28:47.412334+00:00"}