{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:W4UCAIR2F7LH4KJ2XBBEQQH7ZL","short_pith_number":"pith:W4UCAIR2","schema_version":"1.0","canonical_sha256":"b72820223a2fd67e293ab8424840ffcac72ed3d4d71b36499e4d082a60a759c2","source":{"kind":"arxiv","id":"2506.04633","version":1},"attestation_state":"computed","paper":{"title":"Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiawei Gu, Linjie Li, Mahtab Bigverdi, Ranjay Krishna, Yejin Choi, Yinuo Yang, Ziang Li, Zixian Ma","submitted_at":"2025-06-05T05:09:46Z","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"},"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":"2506.04633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T05:09:46Z","cross_cats_sorted":[],"title_canon_sha256":"af4399596815d5bb8ab4103eb611cbe03fedb9704ff4628016130ed22dbf6409","abstract_canon_sha256":"ea1374b651b1bdb644d43c6ff0dda08da5bda5c346f0369867811224b6ed3efa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:18.200115Z","signature_b64":"DHrzHaC+8dPpykAW1ktbsJtWv/8upF6YaV351I2K6rMbxZSIWPEU3iHkjvEifsu1uI+ip1j+Kd4XPJ0EePs3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b72820223a2fd67e293ab8424840ffcac72ed3d4d71b36499e4d082a60a759c2","last_reissued_at":"2026-07-05T11:16:18.199700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:18.199700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiawei Gu, Linjie Li, Mahtab Bigverdi, Ranjay Krishna, Yejin Choi, Yinuo Yang, Ziang Li, Zixian Ma","submitted_at":"2025-06-05T05:09:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04633","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/2506.04633/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":"2506.04633","created_at":"2026-07-05T11:16:18.199762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04633v1","created_at":"2026-07-05T11:16:18.199762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04633","created_at":"2026-07-05T11:16:18.199762+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4UCAIR2F7LH","created_at":"2026-07-05T11:16:18.199762+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4UCAIR2F7LH4KJ2","created_at":"2026-07-05T11:16:18.199762+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4UCAIR2","created_at":"2026-07-05T11:16:18.199762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24539","citing_title":"PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22570","citing_title":"VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10941","citing_title":"Mull-Tokens: Modality-Agnostic Latent Thinking","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11635","citing_title":"Do MLLMs Really Understand Space? A Mathematical Reasoning Evaluation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W4UCAIR2F7LH4KJ2XBBEQQH7ZL","json":"https://pith.science/pith/W4UCAIR2F7LH4KJ2XBBEQQH7ZL.json","graph_json":"https://pith.science/api/pith-number/W4UCAIR2F7LH4KJ2XBBEQQH7ZL/graph.json","events_json":"https://pith.science/api/pith-number/W4UCAIR2F7LH4KJ2XBBEQQH7ZL/events.json","paper":"https://pith.science/paper/W4UCAIR2"},"agent_actions":{"view_html":"https://pith.science/pith/W4UCAIR2F7LH4KJ2XBBEQQH7ZL","download_json":"https://pith.science/pith/W4UCAIR2F7LH4KJ2XBBEQQH7ZL.json","view_paper":"https://pith.science/paper/W4UCAIR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04633&json=true","fetch_graph":"https://pith.science/api/pith-number/W4UCAIR2F7LH4KJ2XBBEQQH7ZL/graph.json","fetch_events":"https://pith.science/api/pith-number/W4UCAIR2F7LH4KJ2XBBEQQH7ZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4UCAIR2F7LH4KJ2XBBEQQH7ZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4UCAIR2F7LH4KJ2XBBEQQH7ZL/action/storage_attestation","attest_author":"https://pith.science/pith/W4UCAIR2F7LH4KJ2XBBEQQH7ZL/action/author_attestation","sign_citation":"https://pith.science/pith/W4UCAIR2F7LH4KJ2XBBEQQH7ZL/action/citation_signature","submit_replication":"https://pith.science/pith/W4UCAIR2F7LH4KJ2XBBEQQH7ZL/action/replication_record"}},"created_at":"2026-07-05T11:16:18.199762+00:00","updated_at":"2026-07-05T11:16:18.199762+00:00"}