{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ALTWPPJQIQJH2UG6O3SHIC72UU","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":"3f27a0785cc65ea350e231d31a0cbe4b1b2512618cddcd60dafb92aaca59c97e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T04:48:43Z","title_canon_sha256":"a7af8fbc602dca6267e86fcc526d6a6fae71047cb0256e014d0df5605e9ae0c0"},"schema_version":"1.0","source":{"id":"2503.10042","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10042","created_at":"2026-07-05T11:15:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10042v4","created_at":"2026-07-05T11:15:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10042","created_at":"2026-07-05T11:15:45Z"},{"alias_kind":"pith_short_12","alias_value":"ALTWPPJQIQJH","created_at":"2026-07-05T11:15:45Z"},{"alias_kind":"pith_short_16","alias_value":"ALTWPPJQIQJH2UG6","created_at":"2026-07-05T11:15:45Z"},{"alias_kind":"pith_short_8","alias_value":"ALTWPPJQ","created_at":"2026-07-05T11:15:45Z"}],"graph_snapshots":[{"event_id":"sha256:90788e2061ca62e3c31c1c4aaa9828e8a485796dc713f726cc316b663cef3cac","target":"graph","created_at":"2026-07-05T11:15:45Z","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/2503.10042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancing of Multimodal Large Language Models (MLLMs) has spurred interest in complex multimodal reasoning tasks in the real-world and virtual environment, which require coordinating multiple abilities, including visual perception, visual reasoning, spatial awareness, and target deduction. However, existing evaluations primarily assess the final task completion, often degrading assessments to isolated abilities such as visual grounding and visual question answering. Less attention is given to comprehensively and quantitatively analyzing reasoning process in multimodal environments, w","authors_text":"Chi Chen, Fuwen Luo, Minyuan Ruan, Peng Li, Yang Liu, Yurui Dong, Zhili Cheng, Ziyue Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T04:48:43Z","title":"EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10042","kind":"arxiv","version":4},"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":"sha256:4aa735cf85d278fa5d27e1f814e0a337252d964994e26e755d7ff994a110309f","target":"record","created_at":"2026-07-05T11:15:45Z","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":"3f27a0785cc65ea350e231d31a0cbe4b1b2512618cddcd60dafb92aaca59c97e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T04:48:43Z","title_canon_sha256":"a7af8fbc602dca6267e86fcc526d6a6fae71047cb0256e014d0df5605e9ae0c0"},"schema_version":"1.0","source":{"id":"2503.10042","kind":"arxiv","version":4}},"canonical_sha256":"02e767bd3044127d50de76e4740bfaa5234d362f757299a73c1048a95eee6ca1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02e767bd3044127d50de76e4740bfaa5234d362f757299a73c1048a95eee6ca1","first_computed_at":"2026-07-05T11:15:45.048174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:45.048174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XCNz5TVmIHTSvpG4QlTpCDSxS+ghyAfQDLJfyNqgoqKdWzZChXUOa8usfBC8sbzHxuC9aq60T/C+QXuyu7PRAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:45.048917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10042","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4aa735cf85d278fa5d27e1f814e0a337252d964994e26e755d7ff994a110309f","sha256:90788e2061ca62e3c31c1c4aaa9828e8a485796dc713f726cc316b663cef3cac"],"state_sha256":"6011bed09f0dbfcaf9f1e41e3cf67b86795b022be1a31e9fa05bd5bff9e63932"}