{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L3QDQ6AUCDD5JICIUB2XZW46TT","short_pith_number":"pith:L3QDQ6AU","schema_version":"1.0","canonical_sha256":"5ee038781410c7d4a048a0757cdb9e9cfdfc65bd2296021cb91bc475a947e49c","source":{"kind":"arxiv","id":"2605.31148","version":1},"attestation_state":"computed","paper":{"title":"SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Hangyu Fan, Jie Feng, Pan Hui, Shengyuan Wang, Tianhui Liu, Yanxin Xi, Yiming Guo, Yong Li, Zhiheng Zheng","submitted_at":"2026-05-29T10:59:26Z","abstract_excerpt":"Humans can effortlessly perceive spatial layouts, form cognitive representations, reason about spatial relations, and translate such reasoning into actions in everyday 3D environments. Although recent vision-language models (VLMs) have shown promising performance on observation-conditioned spatial perception and reasoning tasks, it remains unclear whether they can build coherent spatial understanding, act upon it, and refine their actions through multi-turn feedback. To study this problem, we introduce \\textbf{SpatialAct}, a simulator-grounded benchmark for probing \\textit{action-conditioned 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":"2605.31148","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T10:59:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c6c255123cb5fb70e4128ff1d8460a1fdc56f305b76e64022d5f6ab08e8a49f2","abstract_canon_sha256":"3feee843539edbca647feec1a0934040ff4677a8de64f836e63f80ee72161890"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:04:01.215236Z","signature_b64":"JTMljokQbEhgcpYLCPPnYGXic+osWmIhAPdWTM8VjGKXOBoRJxAzpd/iRMEYjmTl2qICPbNveznA5Jgu2DdNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ee038781410c7d4a048a0757cdb9e9cfdfc65bd2296021cb91bc475a947e49c","last_reissued_at":"2026-06-01T01:04:01.214381Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:04:01.214381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Hangyu Fan, Jie Feng, Pan Hui, Shengyuan Wang, Tianhui Liu, Yanxin Xi, Yiming Guo, Yong Li, Zhiheng Zheng","submitted_at":"2026-05-29T10:59:26Z","abstract_excerpt":"Humans can effortlessly perceive spatial layouts, form cognitive representations, reason about spatial relations, and translate such reasoning into actions in everyday 3D environments. Although recent vision-language models (VLMs) have shown promising performance on observation-conditioned spatial perception and reasoning tasks, it remains unclear whether they can build coherent spatial understanding, act upon it, and refine their actions through multi-turn feedback. To study this problem, we introduce \\textbf{SpatialAct}, a simulator-grounded benchmark for probing \\textit{action-conditioned s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31148","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/2605.31148/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":"2605.31148","created_at":"2026-06-01T01:04:01.214521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31148v1","created_at":"2026-06-01T01:04:01.214521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31148","created_at":"2026-06-01T01:04:01.214521+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3QDQ6AUCDD5","created_at":"2026-06-01T01:04:01.214521+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3QDQ6AUCDD5JICI","created_at":"2026-06-01T01:04:01.214521+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3QDQ6AU","created_at":"2026-06-01T01:04:01.214521+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/L3QDQ6AUCDD5JICIUB2XZW46TT","json":"https://pith.science/pith/L3QDQ6AUCDD5JICIUB2XZW46TT.json","graph_json":"https://pith.science/api/pith-number/L3QDQ6AUCDD5JICIUB2XZW46TT/graph.json","events_json":"https://pith.science/api/pith-number/L3QDQ6AUCDD5JICIUB2XZW46TT/events.json","paper":"https://pith.science/paper/L3QDQ6AU"},"agent_actions":{"view_html":"https://pith.science/pith/L3QDQ6AUCDD5JICIUB2XZW46TT","download_json":"https://pith.science/pith/L3QDQ6AUCDD5JICIUB2XZW46TT.json","view_paper":"https://pith.science/paper/L3QDQ6AU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31148&json=true","fetch_graph":"https://pith.science/api/pith-number/L3QDQ6AUCDD5JICIUB2XZW46TT/graph.json","fetch_events":"https://pith.science/api/pith-number/L3QDQ6AUCDD5JICIUB2XZW46TT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3QDQ6AUCDD5JICIUB2XZW46TT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3QDQ6AUCDD5JICIUB2XZW46TT/action/storage_attestation","attest_author":"https://pith.science/pith/L3QDQ6AUCDD5JICIUB2XZW46TT/action/author_attestation","sign_citation":"https://pith.science/pith/L3QDQ6AUCDD5JICIUB2XZW46TT/action/citation_signature","submit_replication":"https://pith.science/pith/L3QDQ6AUCDD5JICIUB2XZW46TT/action/replication_record"}},"created_at":"2026-06-01T01:04:01.214521+00:00","updated_at":"2026-06-01T01:04:01.214521+00:00"}