{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CDCR6CHLE3FNSRNTLOYFQ6TNSU","short_pith_number":"pith:CDCR6CHL","schema_version":"1.0","canonical_sha256":"10c51f08eb26cad945b35bb0587a6d95120e2470967c22d93673dd69a0f1a53e","source":{"kind":"arxiv","id":"2605.20448","version":1},"attestation_state":"computed","paper":{"title":"Do Vision--Language Models Understand 3D Scenes or Just Catalogue Objects?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Animesh Maheshwari, Divyansh Sahu, Nishit Verma","submitted_at":"2026-05-19T20:01:19Z","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--"},"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":"2605.20448","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T20:01:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"445985ad21cf940720e99f3edfceb353c58bb4c11fc8634006b538e5f38ffa30","abstract_canon_sha256":"b5e7b77ee877c4815e5e8931e9551713d932f8e54addbc84628405a8d811d119"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:38.331078Z","signature_b64":"+2p/R6Zc0S8Fkq/YpDM4MCrrkkjuhCDKF6A5r8Vd3olcXyZn+x8yV3CkERF40SpKx+/vSWtcp7DzGfq7ibcwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10c51f08eb26cad945b35bb0587a6d95120e2470967c22d93673dd69a0f1a53e","last_reissued_at":"2026-05-21T01:04:38.330497Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:38.330497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Vision--Language Models Understand 3D Scenes or Just Catalogue Objects?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Animesh Maheshwari, Divyansh Sahu, Nishit Verma","submitted_at":"2026-05-19T20:01:19Z","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--"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20448","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/2605.20448/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":"2605.20448","created_at":"2026-05-21T01:04:38.330588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20448v1","created_at":"2026-05-21T01:04:38.330588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20448","created_at":"2026-05-21T01:04:38.330588+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDCR6CHLE3FN","created_at":"2026-05-21T01:04:38.330588+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDCR6CHLE3FNSRNT","created_at":"2026-05-21T01:04:38.330588+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDCR6CHL","created_at":"2026-05-21T01:04:38.330588+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/CDCR6CHLE3FNSRNTLOYFQ6TNSU","json":"https://pith.science/pith/CDCR6CHLE3FNSRNTLOYFQ6TNSU.json","graph_json":"https://pith.science/api/pith-number/CDCR6CHLE3FNSRNTLOYFQ6TNSU/graph.json","events_json":"https://pith.science/api/pith-number/CDCR6CHLE3FNSRNTLOYFQ6TNSU/events.json","paper":"https://pith.science/paper/CDCR6CHL"},"agent_actions":{"view_html":"https://pith.science/pith/CDCR6CHLE3FNSRNTLOYFQ6TNSU","download_json":"https://pith.science/pith/CDCR6CHLE3FNSRNTLOYFQ6TNSU.json","view_paper":"https://pith.science/paper/CDCR6CHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20448&json=true","fetch_graph":"https://pith.science/api/pith-number/CDCR6CHLE3FNSRNTLOYFQ6TNSU/graph.json","fetch_events":"https://pith.science/api/pith-number/CDCR6CHLE3FNSRNTLOYFQ6TNSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDCR6CHLE3FNSRNTLOYFQ6TNSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDCR6CHLE3FNSRNTLOYFQ6TNSU/action/storage_attestation","attest_author":"https://pith.science/pith/CDCR6CHLE3FNSRNTLOYFQ6TNSU/action/author_attestation","sign_citation":"https://pith.science/pith/CDCR6CHLE3FNSRNTLOYFQ6TNSU/action/citation_signature","submit_replication":"https://pith.science/pith/CDCR6CHLE3FNSRNTLOYFQ6TNSU/action/replication_record"}},"created_at":"2026-05-21T01:04:38.330588+00:00","updated_at":"2026-05-21T01:04:38.330588+00:00"}