{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:L3QDQ6AUCDD5JICIUB2XZW46TT","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":"3feee843539edbca647feec1a0934040ff4677a8de64f836e63f80ee72161890","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T10:59:26Z","title_canon_sha256":"c6c255123cb5fb70e4128ff1d8460a1fdc56f305b76e64022d5f6ab08e8a49f2"},"schema_version":"1.0","source":{"id":"2605.31148","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.31148","created_at":"2026-06-01T01:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.31148v1","created_at":"2026-06-01T01:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31148","created_at":"2026-06-01T01:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"L3QDQ6AUCDD5","created_at":"2026-06-01T01:04:01Z"},{"alias_kind":"pith_short_16","alias_value":"L3QDQ6AUCDD5JICI","created_at":"2026-06-01T01:04:01Z"},{"alias_kind":"pith_short_8","alias_value":"L3QDQ6AU","created_at":"2026-06-01T01:04:01Z"}],"graph_snapshots":[{"event_id":"sha256:bce73da4708ce45eeebe899e6efe12153980c104e52df9be5918b0e58a7440f8","target":"graph","created_at":"2026-06-01T01:04:01Z","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/2605.31148/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hangyu Fan, Jie Feng, Pan Hui, Shengyuan Wang, Tianhui Liu, Yanxin Xi, Yiming Guo, Yong Li, Zhiheng Zheng","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T10:59:26Z","title":"SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31148","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":"sha256:48cce1868eaf3a3aefadafc22ea8f5838f6603131c1e1fd266132b5ec678704e","target":"record","created_at":"2026-06-01T01:04:01Z","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":"3feee843539edbca647feec1a0934040ff4677a8de64f836e63f80ee72161890","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T10:59:26Z","title_canon_sha256":"c6c255123cb5fb70e4128ff1d8460a1fdc56f305b76e64022d5f6ab08e8a49f2"},"schema_version":"1.0","source":{"id":"2605.31148","kind":"arxiv","version":1}},"canonical_sha256":"5ee038781410c7d4a048a0757cdb9e9cfdfc65bd2296021cb91bc475a947e49c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ee038781410c7d4a048a0757cdb9e9cfdfc65bd2296021cb91bc475a947e49c","first_computed_at":"2026-06-01T01:04:01.214381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:04:01.214381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JTMljokQbEhgcpYLCPPnYGXic+osWmIhAPdWTM8VjGKXOBoRJxAzpd/iRMEYjmTl2qICPbNveznA5Jgu2DdNAA==","signature_status":"signed_v1","signed_at":"2026-06-01T01:04:01.215236Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.31148","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48cce1868eaf3a3aefadafc22ea8f5838f6603131c1e1fd266132b5ec678704e","sha256:bce73da4708ce45eeebe899e6efe12153980c104e52df9be5918b0e58a7440f8"],"state_sha256":"3a8f964b50dc2575517680614939f8d7d55e0a081d99377a18833832dfa23cdd"}