{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CDCR6CHLE3FNSRNTLOYFQ6TNSU","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":"b5e7b77ee877c4815e5e8931e9551713d932f8e54addbc84628405a8d811d119","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T20:01:19Z","title_canon_sha256":"445985ad21cf940720e99f3edfceb353c58bb4c11fc8634006b538e5f38ffa30"},"schema_version":"1.0","source":{"id":"2605.20448","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20448","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20448v1","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20448","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"CDCR6CHLE3FN","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"CDCR6CHLE3FNSRNT","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"CDCR6CHL","created_at":"2026-05-21T01:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:6d42185355a54db9857145502e07fdc4015388ad31fd9c1b22cca3836107aad6","target":"graph","created_at":"2026-05-21T01:04:38Z","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/2605.20448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision--language models reliably name objects in a scene, but do they represent the 3D layout those objects inhabit? We introduce a 3,034-sample human-curated benchmark targeting three components of spatial understanding: depth-ordered occlusion (probed via three independent counterfactual operationalisations), optical-geometry inference over visible reflections, and volumetric rearrangement planning. Six frontier and open-weight VLMs, scored by trained annotators on 18,204 responses with no LLM-as-judge, reveal a sharp dissociation: models that plan rearrangements over visible layouts at 53--","authors_text":"Animesh Maheshwari, Divyansh Sahu, Nishit Verma","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T20:01:19Z","title":"Do Vision--Language Models Understand 3D Scenes or Just Catalogue Objects?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20448","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":"sha256:107e64975a0104b0ff621946138373e5780fd66d2b163a3e35fb1215707b4f22","target":"record","created_at":"2026-05-21T01:04:38Z","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":"b5e7b77ee877c4815e5e8931e9551713d932f8e54addbc84628405a8d811d119","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T20:01:19Z","title_canon_sha256":"445985ad21cf940720e99f3edfceb353c58bb4c11fc8634006b538e5f38ffa30"},"schema_version":"1.0","source":{"id":"2605.20448","kind":"arxiv","version":1}},"canonical_sha256":"10c51f08eb26cad945b35bb0587a6d95120e2470967c22d93673dd69a0f1a53e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10c51f08eb26cad945b35bb0587a6d95120e2470967c22d93673dd69a0f1a53e","first_computed_at":"2026-05-21T01:04:38.330497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:38.330497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+2p/R6Zc0S8Fkq/YpDM4MCrrkkjuhCDKF6A5r8Vd3olcXyZn+x8yV3CkERF40SpKx+/vSWtcp7DzGfq7ibcwBw==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:38.331078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20448","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:107e64975a0104b0ff621946138373e5780fd66d2b163a3e35fb1215707b4f22","sha256:6d42185355a54db9857145502e07fdc4015388ad31fd9c1b22cca3836107aad6"],"state_sha256":"2b31a81aff10942e682f064336a4cb1b6107b03c7dc115862cc2b61615f442f1"}