{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N3C5OSCYYTSF5B4NHNUDT5EDBN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3ead1d3bc361654d6c3f349e6e4bcacc22bd98c01ca021d4a761d59e388961f5","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T07:10:31Z","title_canon_sha256":"e6beb4970670c78adaa6acf61f389e552dc0358d6cbdf5f309da742c1f265158"},"schema_version":"1.0","source":{"id":"2403.01777","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01777","created_at":"2026-07-05T11:59:51Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01777v3","created_at":"2026-07-05T11:59:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01777","created_at":"2026-07-05T11:59:51Z"},{"alias_kind":"pith_short_12","alias_value":"N3C5OSCYYTSF","created_at":"2026-07-05T11:59:51Z"},{"alias_kind":"pith_short_16","alias_value":"N3C5OSCYYTSF5B4N","created_at":"2026-07-05T11:59:51Z"},{"alias_kind":"pith_short_8","alias_value":"N3C5OSCY","created_at":"2026-07-05T11:59:51Z"}],"graph_snapshots":[{"event_id":"sha256:1236bc97f03242ad02c5416d05acfd3b2d05d3f47c4b53780ee5b431560fe9c9","target":"graph","created_at":"2026-07-05T11:59:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.01777/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haoyang Ling, Jindong Wang, Jinkui Chi, Kaijie Zhu, Lingyao Li, Lizhou Fan, Qi Dou, Wenyue Hua, Xiang Li, Xin Ma, Yongfeng Zhang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T07:10:31Z","title":"NPHardEval4V: Dynamic Evaluation of Large Vision-Language Models with Effects of Vision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01777","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f6e63c3a11c9d26f0e1ff0f8ec9ce5587f5c2a5ef833f6e7c3004601cadc6215","target":"record","created_at":"2026-07-05T11:59:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3ead1d3bc361654d6c3f349e6e4bcacc22bd98c01ca021d4a761d59e388961f5","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T07:10:31Z","title_canon_sha256":"e6beb4970670c78adaa6acf61f389e552dc0358d6cbdf5f309da742c1f265158"},"schema_version":"1.0","source":{"id":"2403.01777","kind":"arxiv","version":3}},"canonical_sha256":"6ec5d74858c4e45e878d3b6839f4830b49352273a7e9904579a94231398def30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ec5d74858c4e45e878d3b6839f4830b49352273a7e9904579a94231398def30","first_computed_at":"2026-07-05T11:59:51.596611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:51.596611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iEqPENfsXazpAaa+SD5TnqjuW7UiooFazCmwHtXkNEwTccxTWue/RucM8N5qtZiiGi6MIiBWsdIJXqT/d8nYDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:51.597081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01777","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6e63c3a11c9d26f0e1ff0f8ec9ce5587f5c2a5ef833f6e7c3004601cadc6215","sha256:1236bc97f03242ad02c5416d05acfd3b2d05d3f47c4b53780ee5b431560fe9c9"],"state_sha256":"22da8e14d6616f1c6e00569d73a7f98ede33dc764b73a79e9e632e99482c6529"}