{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H3I4FEQYQOHIGNQWIBCNX54MCV","short_pith_number":"pith:H3I4FEQY","schema_version":"1.0","canonical_sha256":"3ed1c29218838e8336164044dbf78c155a0aa65ea11ac515f75840514ac1a807","source":{"kind":"arxiv","id":"2507.02978","version":1},"attestation_state":"computed","paper":{"title":"Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guozheng Rao, Jiahuan Zhang, Kaicheng Yu, Kai Han, Kaiwen Guo, Shunwen Bai, Tianheng Wang","submitted_at":"2025-07-01T03:05:56Z","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"},"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":"2507.02978","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T03:05:56Z","cross_cats_sorted":[],"title_canon_sha256":"f158c206f7c3d449fa6d8f29fec2b887cf5ea9f9d40cb7c340e5c48b2cde6c4b","abstract_canon_sha256":"4f26ceb45225e9f4990c6d40ba589a92d8e5315c0a19018baf6293d315de9f80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:49.980842Z","signature_b64":"T3/OGiCyHZDPokGuzYQK5J+2ZGDqs4LnQdb4oEAZiIiHG+yNiRsI87nSlIk0SKsAtm1iyxpCKg6zXmfoz3BYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ed1c29218838e8336164044dbf78c155a0aa65ea11ac515f75840514ac1a807","last_reissued_at":"2026-07-05T11:31:49.980348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:49.980348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guozheng Rao, Jiahuan Zhang, Kaicheng Yu, Kai Han, Kaiwen Guo, Shunwen Bai, Tianheng Wang","submitted_at":"2025-07-01T03:05:56Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02978","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/2507.02978/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":"2507.02978","created_at":"2026-07-05T11:31:49.980409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02978v1","created_at":"2026-07-05T11:31:49.980409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02978","created_at":"2026-07-05T11:31:49.980409+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3I4FEQYQOHI","created_at":"2026-07-05T11:31:49.980409+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3I4FEQYQOHIGNQW","created_at":"2026-07-05T11:31:49.980409+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3I4FEQY","created_at":"2026-07-05T11:31:49.980409+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/H3I4FEQYQOHIGNQWIBCNX54MCV","json":"https://pith.science/pith/H3I4FEQYQOHIGNQWIBCNX54MCV.json","graph_json":"https://pith.science/api/pith-number/H3I4FEQYQOHIGNQWIBCNX54MCV/graph.json","events_json":"https://pith.science/api/pith-number/H3I4FEQYQOHIGNQWIBCNX54MCV/events.json","paper":"https://pith.science/paper/H3I4FEQY"},"agent_actions":{"view_html":"https://pith.science/pith/H3I4FEQYQOHIGNQWIBCNX54MCV","download_json":"https://pith.science/pith/H3I4FEQYQOHIGNQWIBCNX54MCV.json","view_paper":"https://pith.science/paper/H3I4FEQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02978&json=true","fetch_graph":"https://pith.science/api/pith-number/H3I4FEQYQOHIGNQWIBCNX54MCV/graph.json","fetch_events":"https://pith.science/api/pith-number/H3I4FEQYQOHIGNQWIBCNX54MCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3I4FEQYQOHIGNQWIBCNX54MCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3I4FEQYQOHIGNQWIBCNX54MCV/action/storage_attestation","attest_author":"https://pith.science/pith/H3I4FEQYQOHIGNQWIBCNX54MCV/action/author_attestation","sign_citation":"https://pith.science/pith/H3I4FEQYQOHIGNQWIBCNX54MCV/action/citation_signature","submit_replication":"https://pith.science/pith/H3I4FEQYQOHIGNQWIBCNX54MCV/action/replication_record"}},"created_at":"2026-07-05T11:31:49.980409+00:00","updated_at":"2026-07-05T11:31:49.980409+00:00"}