{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:L3QDQ6AUCDD5JICIUB2XZW46TT","short_pith_number":"pith:L3QDQ6AU","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"},"canonical_sha256":"5ee038781410c7d4a048a0757cdb9e9cfdfc65bd2296021cb91bc475a947e49c","source":{"kind":"arxiv","id":"2605.31148","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:L3QDQ6AUCDD5JICIUB2XZW46TT","target":"record","payload":{"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"},"canonical_sha256":"5ee038781410c7d4a048a0757cdb9e9cfdfc65bd2296021cb91bc475a947e49c","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"},"source_kind":"arxiv","source_id":"2605.31148","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:04:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8gB4C8K9qkmtR3b9C8q1W1NjTvE0DPR503nXgj0UPxAkGxq3bBEX5Zov8yom30pDgELgFIJBmIfJ59e0378qAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:36:05.183130Z"},"content_sha256":"48cce1868eaf3a3aefadafc22ea8f5838f6603131c1e1fd266132b5ec678704e","schema_version":"1.0","event_id":"sha256:48cce1868eaf3a3aefadafc22ea8f5838f6603131c1e1fd266132b5ec678704e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:L3QDQ6AUCDD5JICIUB2XZW46TT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:04:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6vLfD6Bz/gZY0eN3NfIDRQnJpn7FtsSC4xATdMyl+l6IZzlNrauxVRZl41uIaUmnl75hcZJJjszX37PQIXsQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:36:05.183536Z"},"content_sha256":"bce73da4708ce45eeebe899e6efe12153980c104e52df9be5918b0e58a7440f8","schema_version":"1.0","event_id":"sha256:bce73da4708ce45eeebe899e6efe12153980c104e52df9be5918b0e58a7440f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L3QDQ6AUCDD5JICIUB2XZW46TT/bundle.json","state_url":"https://pith.science/pith/L3QDQ6AUCDD5JICIUB2XZW46TT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L3QDQ6AUCDD5JICIUB2XZW46TT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T21:36:05Z","links":{"resolver":"https://pith.science/pith/L3QDQ6AUCDD5JICIUB2XZW46TT","bundle":"https://pith.science/pith/L3QDQ6AUCDD5JICIUB2XZW46TT/bundle.json","state":"https://pith.science/pith/L3QDQ6AUCDD5JICIUB2XZW46TT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L3QDQ6AUCDD5JICIUB2XZW46TT/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ld7z3+dBRe5VHfKvQLkCVXHMJSz9ZKZSMBq6bDq/qV9344Bz6jY0JpFvmL1bSlGOjWSB/UqtfM6tDSMhacFUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T21:36:05.185598Z","bundle_sha256":"b392c00ba5651148a3dd42d962d5426c15f053b2e19cecd061dd5d25b17677cc"}}