{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WIPE5KEZG7L5KKDQTVDRQH5OTX","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":"6b452b6f9d4af3cecceaf2749292373d23d818aa787e176a1282a48cd89dad2e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T10:05:41Z","title_canon_sha256":"0b68f7fe88feeca2e360f5861baf9d6725fc2a074f361bb9648576224ded7751"},"schema_version":"1.0","source":{"id":"2608.07584","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07584","created_at":"2026-08-11T00:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07584v1","created_at":"2026-08-11T00:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07584","created_at":"2026-08-11T00:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"WIPE5KEZG7L5","created_at":"2026-08-11T00:15:25Z"},{"alias_kind":"pith_short_16","alias_value":"WIPE5KEZG7L5KKDQ","created_at":"2026-08-11T00:15:25Z"},{"alias_kind":"pith_short_8","alias_value":"WIPE5KEZ","created_at":"2026-08-11T00:15:25Z"}],"graph_snapshots":[{"event_id":"sha256:7e1e01a9b65921b597e94f5fb12d85bc9844a7635bfb3e97ad45b9d356d8a39d","target":"graph","created_at":"2026-08-11T00:15:25Z","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/2608.07584/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have made rapid progress in visual perception and increasingly support real-world tasks that depend on images. Many such tasks, however, require more than rec- ognizing what an image contains: a model must use visual evidence to make a complete decision whose parts jointly satisfy global constraints. We introduce COMPLEXITYWORLD, a benchmark of 390 tasks across 39 domain-inspired visual worlds and 29 decision categories. Each task is generated from a hidden structured specification, rendered as a visual scene, and scored by an exe- cutable verifier that accepts an","authors_text":"Hanyu Li, Ningxin Pan, Yehui Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T10:05:41Z","title":"ComplexityWorld: Benchmarking Vision-Language Models on Verifiable Visual Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07584","kind":"arxiv","version":1},"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:c81cfd2e08df33f1e7c217db1d0a7ba88eb438322f64f6ef5c05c393ca28b0c9","target":"record","created_at":"2026-08-11T00:15:25Z","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":"6b452b6f9d4af3cecceaf2749292373d23d818aa787e176a1282a48cd89dad2e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T10:05:41Z","title_canon_sha256":"0b68f7fe88feeca2e360f5861baf9d6725fc2a074f361bb9648576224ded7751"},"schema_version":"1.0","source":{"id":"2608.07584","kind":"arxiv","version":1}},"canonical_sha256":"b21e4ea89937d7d528709d47181fae9df5f0c4ffa30703738bfefd8303888289","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b21e4ea89937d7d528709d47181fae9df5f0c4ffa30703738bfefd8303888289","first_computed_at":"2026-08-11T00:15:25.380298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T00:15:25.380298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fglj7nLDSkMIMRAqIN+CfXrsa0lDNTLWTlVnSi4ggY1dxHSPk6SDkM4z+q1V354geyVdikvL8K1j75y9pJZnAA==","signature_status":"signed_v1","signed_at":"2026-08-11T00:15:25.382519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.07584","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c81cfd2e08df33f1e7c217db1d0a7ba88eb438322f64f6ef5c05c393ca28b0c9","sha256:7e1e01a9b65921b597e94f5fb12d85bc9844a7635bfb3e97ad45b9d356d8a39d"],"state_sha256":"5c48f0a5fa161c6252d66eed1f06a667a2d1d7ffcef5919dd0ef59f530d24089"}