{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TLCTVMVGDLNOVQHA4E5LHH6URU","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":"32d02fcb72ed47efe8459fa12f52e49452158da0e1f10990d6bb48259b997286","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T05:15:46Z","title_canon_sha256":"ffb226dc83cf353d64da1588cb7e95ea986b67b74a4abc475adfe813b7809c59"},"schema_version":"1.0","source":{"id":"2608.01709","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01709","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01709v1","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01709","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"pith_short_12","alias_value":"TLCTVMVGDLNO","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"pith_short_16","alias_value":"TLCTVMVGDLNOVQHA","created_at":"2026-08-04T02:06:36Z"},{"alias_kind":"pith_short_8","alias_value":"TLCTVMVG","created_at":"2026-08-04T02:06:36Z"}],"graph_snapshots":[{"event_id":"sha256:f0e08408c38f968c0552e690245e9f3a2ce98cefc27c6c2c5d6cc2efcd6d911a","target":"graph","created_at":"2026-08-04T02:06:36Z","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/2608.01709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) achieve strong semantic understanding but remain unreliable in metric spatial reasoning, particularly when queries require comparing multiple instances of the same object category. We study this problem through the Closest-Instance Distance Query (CIDQ), where a model must identify the nearest visible candidate to a unique reference object and estimate their gravity-aligned floor-plane distance. We introduce SPATIALQUERY, a training- free framework for CIDQ reasoning from a single RGB image, together with SPATIALQUERY-1M, a benchmark containing over one million RG","authors_text":"Cong Tran, Hai Nguyen, Tung Vu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T05:15:46Z","title":"SpatialQuery: Benchmarking Geometry-Grounded Multi-Instance Spatial Reasoning in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01709","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:fb0b4400d3f5120f984c866cbe62f8014b164b03cc990f1375077296e0a4f371","target":"record","created_at":"2026-08-04T02:06:36Z","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":"32d02fcb72ed47efe8459fa12f52e49452158da0e1f10990d6bb48259b997286","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T05:15:46Z","title_canon_sha256":"ffb226dc83cf353d64da1588cb7e95ea986b67b74a4abc475adfe813b7809c59"},"schema_version":"1.0","source":{"id":"2608.01709","kind":"arxiv","version":1}},"canonical_sha256":"9ac53ab2a61adaeac0e0e13ab39fd48d315ef37dff7eed2769063e93e87666cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ac53ab2a61adaeac0e0e13ab39fd48d315ef37dff7eed2769063e93e87666cb","first_computed_at":"2026-08-04T02:06:36.203966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:06:36.203966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5tMnAQbNh21pgOxkSAV1XKZdjb4g8Mz5RYGgQwuDfvd4sq0iVBK4/7AvPgCdZp2cit9ii61EoHHVFiQnFKGtBQ==","signature_status":"signed_v1","signed_at":"2026-08-04T02:06:36.205555Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01709","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb0b4400d3f5120f984c866cbe62f8014b164b03cc990f1375077296e0a4f371","sha256:f0e08408c38f968c0552e690245e9f3a2ce98cefc27c6c2c5d6cc2efcd6d911a"],"state_sha256":"0c6aa44647648b94b08025bd6c53f239bfdbc5f839ce128b529082b73ff87e26"}