{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WIPE5KEZG7L5KKDQTVDRQH5OTX","short_pith_number":"pith:WIPE5KEZ","schema_version":"1.0","canonical_sha256":"b21e4ea89937d7d528709d47181fae9df5f0c4ffa30703738bfefd8303888289","source":{"kind":"arxiv","id":"2608.07584","version":1},"attestation_state":"computed","paper":{"title":"ComplexityWorld: Benchmarking Vision-Language Models on Verifiable Visual Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanyu Li, Ningxin Pan, Yehui Tang","submitted_at":"2026-08-05T10:05:41Z","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"},"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":"2608.07584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T10:05:41Z","cross_cats_sorted":[],"title_canon_sha256":"0b68f7fe88feeca2e360f5861baf9d6725fc2a074f361bb9648576224ded7751","abstract_canon_sha256":"6b452b6f9d4af3cecceaf2749292373d23d818aa787e176a1282a48cd89dad2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T00:15:25.382519Z","signature_b64":"Fglj7nLDSkMIMRAqIN+CfXrsa0lDNTLWTlVnSi4ggY1dxHSPk6SDkM4z+q1V354geyVdikvL8K1j75y9pJZnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b21e4ea89937d7d528709d47181fae9df5f0c4ffa30703738bfefd8303888289","last_reissued_at":"2026-08-11T00:15:25.380298Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T00:15:25.380298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ComplexityWorld: Benchmarking Vision-Language Models on Verifiable Visual Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanyu Li, Ningxin Pan, Yehui Tang","submitted_at":"2026-08-05T10:05:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07584","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/2608.07584/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":"2608.07584","created_at":"2026-08-11T00:15:25.380685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07584v1","created_at":"2026-08-11T00:15:25.380685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07584","created_at":"2026-08-11T00:15:25.380685+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIPE5KEZG7L5","created_at":"2026-08-11T00:15:25.380685+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIPE5KEZG7L5KKDQ","created_at":"2026-08-11T00:15:25.380685+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIPE5KEZ","created_at":"2026-08-11T00:15:25.380685+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WIPE5KEZG7L5KKDQTVDRQH5OTX","json":"https://pith.science/pith/WIPE5KEZG7L5KKDQTVDRQH5OTX.json","graph_json":"https://pith.science/api/pith-number/WIPE5KEZG7L5KKDQTVDRQH5OTX/graph.json","events_json":"https://pith.science/api/pith-number/WIPE5KEZG7L5KKDQTVDRQH5OTX/events.json","paper":"https://pith.science/paper/WIPE5KEZ"},"agent_actions":{"view_html":"https://pith.science/pith/WIPE5KEZG7L5KKDQTVDRQH5OTX","download_json":"https://pith.science/pith/WIPE5KEZG7L5KKDQTVDRQH5OTX.json","view_paper":"https://pith.science/paper/WIPE5KEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07584&json=true","fetch_graph":"https://pith.science/api/pith-number/WIPE5KEZG7L5KKDQTVDRQH5OTX/graph.json","fetch_events":"https://pith.science/api/pith-number/WIPE5KEZG7L5KKDQTVDRQH5OTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIPE5KEZG7L5KKDQTVDRQH5OTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIPE5KEZG7L5KKDQTVDRQH5OTX/action/storage_attestation","attest_author":"https://pith.science/pith/WIPE5KEZG7L5KKDQTVDRQH5OTX/action/author_attestation","sign_citation":"https://pith.science/pith/WIPE5KEZG7L5KKDQTVDRQH5OTX/action/citation_signature","submit_replication":"https://pith.science/pith/WIPE5KEZG7L5KKDQTVDRQH5OTX/action/replication_record"}},"created_at":"2026-08-11T00:15:25.380685+00:00","updated_at":"2026-08-11T00:15:25.380685+00:00"}