{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SXX2U4L2KGXUPEHXFLC5ZQ2UM6","short_pith_number":"pith:SXX2U4L2","schema_version":"1.0","canonical_sha256":"95efaa717a51af4790f72ac5dcc35467a42dbfaa29e92aefb1638312b40eae00","source":{"kind":"arxiv","id":"2606.26535","version":1},"attestation_state":"computed","paper":{"title":"From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Yinan Yu, Zhixing Li","submitted_at":"2026-06-25T02:18:38Z","abstract_excerpt":"Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnostic evaluation paradigm that assesses visual spatial intelligence through consistency, the alignment between implicit perception and explicit reasoning. Unlike traditional black-box QA, CRISP utilizes metric 3D Scene Graphs and an oracle intervention protocol to decouple latent reasoning capabilities from perceptual bottlenecks. This granular diagnosis uncovers a systematic perception-reasoning disconnect. Crucially, we reveal that while propriet"},"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":"2606.26535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T02:18:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2d94a4ed4b40c04035a761976180712a463b5f7fef2f016467d932ae3161c191","abstract_canon_sha256":"59a8a5efa354817fe4f857f4badae9ff755a85a6f94e55c6758647b3ee426fd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:33.862620Z","signature_b64":"LWr9gGlJZ7nNKbnh0wqQqr4BtdI14k9ylWzSXUTln8fnTswRKyRo7YD+8TuPMkX2VrjQccZ2XG+w/sMjHOETCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95efaa717a51af4790f72ac5dcc35467a42dbfaa29e92aefb1638312b40eae00","last_reissued_at":"2026-06-26T01:15:33.862235Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:33.862235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Yinan Yu, Zhixing Li","submitted_at":"2026-06-25T02:18:38Z","abstract_excerpt":"Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnostic evaluation paradigm that assesses visual spatial intelligence through consistency, the alignment between implicit perception and explicit reasoning. Unlike traditional black-box QA, CRISP utilizes metric 3D Scene Graphs and an oracle intervention protocol to decouple latent reasoning capabilities from perceptual bottlenecks. This granular diagnosis uncovers a systematic perception-reasoning disconnect. Crucially, we reveal that while propriet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26535","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/2606.26535/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":"2606.26535","created_at":"2026-06-26T01:15:33.862295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26535v1","created_at":"2026-06-26T01:15:33.862295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26535","created_at":"2026-06-26T01:15:33.862295+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXX2U4L2KGXU","created_at":"2026-06-26T01:15:33.862295+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXX2U4L2KGXUPEHX","created_at":"2026-06-26T01:15:33.862295+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXX2U4L2","created_at":"2026-06-26T01:15:33.862295+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/SXX2U4L2KGXUPEHXFLC5ZQ2UM6","json":"https://pith.science/pith/SXX2U4L2KGXUPEHXFLC5ZQ2UM6.json","graph_json":"https://pith.science/api/pith-number/SXX2U4L2KGXUPEHXFLC5ZQ2UM6/graph.json","events_json":"https://pith.science/api/pith-number/SXX2U4L2KGXUPEHXFLC5ZQ2UM6/events.json","paper":"https://pith.science/paper/SXX2U4L2"},"agent_actions":{"view_html":"https://pith.science/pith/SXX2U4L2KGXUPEHXFLC5ZQ2UM6","download_json":"https://pith.science/pith/SXX2U4L2KGXUPEHXFLC5ZQ2UM6.json","view_paper":"https://pith.science/paper/SXX2U4L2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26535&json=true","fetch_graph":"https://pith.science/api/pith-number/SXX2U4L2KGXUPEHXFLC5ZQ2UM6/graph.json","fetch_events":"https://pith.science/api/pith-number/SXX2U4L2KGXUPEHXFLC5ZQ2UM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXX2U4L2KGXUPEHXFLC5ZQ2UM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXX2U4L2KGXUPEHXFLC5ZQ2UM6/action/storage_attestation","attest_author":"https://pith.science/pith/SXX2U4L2KGXUPEHXFLC5ZQ2UM6/action/author_attestation","sign_citation":"https://pith.science/pith/SXX2U4L2KGXUPEHXFLC5ZQ2UM6/action/citation_signature","submit_replication":"https://pith.science/pith/SXX2U4L2KGXUPEHXFLC5ZQ2UM6/action/replication_record"}},"created_at":"2026-06-26T01:15:33.862295+00:00","updated_at":"2026-06-26T01:15:33.862295+00:00"}