{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N3C5OSCYYTSF5B4NHNUDT5EDBN","short_pith_number":"pith:N3C5OSCY","schema_version":"1.0","canonical_sha256":"6ec5d74858c4e45e878d3b6839f4830b49352273a7e9904579a94231398def30","source":{"kind":"arxiv","id":"2403.01777","version":3},"attestation_state":"computed","paper":{"title":"NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haoyang Ling, Jindong Wang, Jinkui Chi, Kaijie Zhu, Lingyao Li, Lizhou Fan, Qi Dou, Wenyue Hua, Xiang Li, Xin Ma, Yongfeng Zhang","submitted_at":"2024-03-04T07:10:31Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in multimodal understanding, yet their reasoning abilities remain underexplored. Existing benchmarks tend to focus on perception or text-based comprehension, offering limited insight into how well these models perform on structured, logic-driven tasks that require both visual and linguistic reasoning. To address this gap, we introduce NPHardEval4V, a multimodal benchmark suite grounded in four classical NP-hard problems: Knapsack, Set Cover, Traveling Salesperson, and Vertex Cover. Each task is presented through a c"},"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":"2403.01777","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T07:10:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e6beb4970670c78adaa6acf61f389e552dc0358d6cbdf5f309da742c1f265158","abstract_canon_sha256":"3ead1d3bc361654d6c3f349e6e4bcacc22bd98c01ca021d4a761d59e388961f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:51.597081Z","signature_b64":"iEqPENfsXazpAaa+SD5TnqjuW7UiooFazCmwHtXkNEwTccxTWue/RucM8N5qtZiiGi6MIiBWsdIJXqT/d8nYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ec5d74858c4e45e878d3b6839f4830b49352273a7e9904579a94231398def30","last_reissued_at":"2026-07-05T11:59:51.596611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:51.596611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Haoyang Ling, Jindong Wang, Jinkui Chi, Kaijie Zhu, Lingyao Li, Lizhou Fan, Qi Dou, Wenyue Hua, Xiang Li, Xin Ma, Yongfeng Zhang","submitted_at":"2024-03-04T07:10:31Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in multimodal understanding, yet their reasoning abilities remain underexplored. Existing benchmarks tend to focus on perception or text-based comprehension, offering limited insight into how well these models perform on structured, logic-driven tasks that require both visual and linguistic reasoning. To address this gap, we introduce NPHardEval4V, a multimodal benchmark suite grounded in four classical NP-hard problems: Knapsack, Set Cover, Traveling Salesperson, and Vertex Cover. Each task is presented through a c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01777","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/2403.01777/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":"2403.01777","created_at":"2026-07-05T11:59:51.596669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01777v3","created_at":"2026-07-05T11:59:51.596669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01777","created_at":"2026-07-05T11:59:51.596669+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3C5OSCYYTSF","created_at":"2026-07-05T11:59:51.596669+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3C5OSCYYTSF5B4N","created_at":"2026-07-05T11:59:51.596669+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3C5OSCY","created_at":"2026-07-05T11:59:51.596669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07642","citing_title":"Do VLMs See What Sensors Feel? A Scalable Expert-Guided Design for Wheelchair Accessibility Assessment from Street View","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08945","citing_title":"FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2406.12708","citing_title":"AgentReview: Exploring Peer Review Dynamics with LLM Agents","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2508.01608","citing_title":"From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N3C5OSCYYTSF5B4NHNUDT5EDBN","json":"https://pith.science/pith/N3C5OSCYYTSF5B4NHNUDT5EDBN.json","graph_json":"https://pith.science/api/pith-number/N3C5OSCYYTSF5B4NHNUDT5EDBN/graph.json","events_json":"https://pith.science/api/pith-number/N3C5OSCYYTSF5B4NHNUDT5EDBN/events.json","paper":"https://pith.science/paper/N3C5OSCY"},"agent_actions":{"view_html":"https://pith.science/pith/N3C5OSCYYTSF5B4NHNUDT5EDBN","download_json":"https://pith.science/pith/N3C5OSCYYTSF5B4NHNUDT5EDBN.json","view_paper":"https://pith.science/paper/N3C5OSCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01777&json=true","fetch_graph":"https://pith.science/api/pith-number/N3C5OSCYYTSF5B4NHNUDT5EDBN/graph.json","fetch_events":"https://pith.science/api/pith-number/N3C5OSCYYTSF5B4NHNUDT5EDBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3C5OSCYYTSF5B4NHNUDT5EDBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3C5OSCYYTSF5B4NHNUDT5EDBN/action/storage_attestation","attest_author":"https://pith.science/pith/N3C5OSCYYTSF5B4NHNUDT5EDBN/action/author_attestation","sign_citation":"https://pith.science/pith/N3C5OSCYYTSF5B4NHNUDT5EDBN/action/citation_signature","submit_replication":"https://pith.science/pith/N3C5OSCYYTSF5B4NHNUDT5EDBN/action/replication_record"}},"created_at":"2026-07-05T11:59:51.596669+00:00","updated_at":"2026-07-05T11:59:51.596669+00:00"}