{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H3I4FEQYQOHIGNQWIBCNX54MCV","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":"4f26ceb45225e9f4990c6d40ba589a92d8e5315c0a19018baf6293d315de9f80","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T03:05:56Z","title_canon_sha256":"f158c206f7c3d449fa6d8f29fec2b887cf5ea9f9d40cb7c340e5c48b2cde6c4b"},"schema_version":"1.0","source":{"id":"2507.02978","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02978","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02978v1","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02978","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"pith_short_12","alias_value":"H3I4FEQYQOHI","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"H3I4FEQYQOHIGNQW","created_at":"2026-07-05T11:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"H3I4FEQY","created_at":"2026-07-05T11:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:224f45d03331ab17e3c80057d82f52310b8b18b66c29ac391e6a56b8765c21a4","target":"graph","created_at":"2026-07-05T11:31:49Z","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/2507.02978/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans naturally possess the spatial reasoning ability to form and manipulate images and structures of objects in space. There is an increasing effort to endow Vision-Language Models (VLMs) with similar spatial reasoning capabilities. However, it remains unclear whether these models truly understand and manipulate spatial objects or not. To address this question, we propose a new evaluation framework aimed at assessing the performance of VLMs in spatial deformation reasoning tasks. Specifically, we construct a benchmark for spatial deformation reasoning from 2D to 3D. Leveraging our data engin","authors_text":"Guozheng Rao, Jiahuan Zhang, Kaicheng Yu, Kai Han, Kaiwen Guo, Shunwen Bai, Tianheng Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T03:05:56Z","title":"Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02978","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":"sha256:7dcc959defb829a2ab19bf1b77e1ab53158bf6ff997eb4f07ddfe07da5865e9f","target":"record","created_at":"2026-07-05T11:31:49Z","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":"4f26ceb45225e9f4990c6d40ba589a92d8e5315c0a19018baf6293d315de9f80","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T03:05:56Z","title_canon_sha256":"f158c206f7c3d449fa6d8f29fec2b887cf5ea9f9d40cb7c340e5c48b2cde6c4b"},"schema_version":"1.0","source":{"id":"2507.02978","kind":"arxiv","version":1}},"canonical_sha256":"3ed1c29218838e8336164044dbf78c155a0aa65ea11ac515f75840514ac1a807","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ed1c29218838e8336164044dbf78c155a0aa65ea11ac515f75840514ac1a807","first_computed_at":"2026-07-05T11:31:49.980348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:49.980348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T3/OGiCyHZDPokGuzYQK5J+2ZGDqs4LnQdb4oEAZiIiHG+yNiRsI87nSlIk0SKsAtm1iyxpCKg6zXmfoz3BYDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:49.980842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02978","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7dcc959defb829a2ab19bf1b77e1ab53158bf6ff997eb4f07ddfe07da5865e9f","sha256:224f45d03331ab17e3c80057d82f52310b8b18b66c29ac391e6a56b8765c21a4"],"state_sha256":"b53fa51fa711d2d111a07f588a0b30d4ca29a709744f0cd65465b0823df21f60"}