{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W4UCAIR2F7LH4KJ2XBBEQQH7ZL","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":"ea1374b651b1bdb644d43c6ff0dda08da5bda5c346f0369867811224b6ed3efa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T05:09:46Z","title_canon_sha256":"af4399596815d5bb8ab4103eb611cbe03fedb9704ff4628016130ed22dbf6409"},"schema_version":"1.0","source":{"id":"2506.04633","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04633","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04633v1","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04633","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"W4UCAIR2F7LH","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_16","alias_value":"W4UCAIR2F7LH4KJ2","created_at":"2026-07-05T11:16:18Z"},{"alias_kind":"pith_short_8","alias_value":"W4UCAIR2","created_at":"2026-07-05T11:16:18Z"}],"graph_snapshots":[{"event_id":"sha256:bb7607870260dec01d1807bab01abf7342389a58c09aac822e361801495a35b6","target":"graph","created_at":"2026-07-05T11:16:18Z","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/2506.04633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial cognition is essential for human intelligence, enabling problem-solving through visual simulations rather than solely relying on verbal reasoning. However, existing AI benchmarks primarily assess verbal reasoning, neglecting the complexities of non-verbal, multi-step visual simulation. We introduce STARE(Spatial Transformations and Reasoning Evaluation), a benchmark designed to rigorously evaluate multimodal large language models on tasks better solved through multi-step visual simulation. STARE features 4K tasks spanning foundational geometric transformations (2D and 3D), integrated s","authors_text":"Jiawei Gu, Linjie Li, Mahtab Bigverdi, Ranjay Krishna, Yejin Choi, Yinuo Yang, Ziang Li, Zixian Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T05:09:46Z","title":"Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04633","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":"sha256:5cdcc1d074df900fe7d18ab6391910e2e1ca6ba22c6e1476e2c5068375d37419","target":"record","created_at":"2026-07-05T11:16:18Z","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":"ea1374b651b1bdb644d43c6ff0dda08da5bda5c346f0369867811224b6ed3efa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T05:09:46Z","title_canon_sha256":"af4399596815d5bb8ab4103eb611cbe03fedb9704ff4628016130ed22dbf6409"},"schema_version":"1.0","source":{"id":"2506.04633","kind":"arxiv","version":1}},"canonical_sha256":"b72820223a2fd67e293ab8424840ffcac72ed3d4d71b36499e4d082a60a759c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b72820223a2fd67e293ab8424840ffcac72ed3d4d71b36499e4d082a60a759c2","first_computed_at":"2026-07-05T11:16:18.199700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:18.199700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DHrzHaC+8dPpykAW1ktbsJtWv/8upF6YaV351I2K6rMbxZSIWPEU3iHkjvEifsu1uI+ip1j+Kd4XPJ0EePs3DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:18.200115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04633","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cdcc1d074df900fe7d18ab6391910e2e1ca6ba22c6e1476e2c5068375d37419","sha256:bb7607870260dec01d1807bab01abf7342389a58c09aac822e361801495a35b6"],"state_sha256":"1bcb7a43cf789f0d662e08ab8bfa1915cb6648bf0e25fd14673d8ae40d44dc90"}