{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JSRXVPDUH774STATZYRQ3VGYE4","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":"4e62fe72059166afc1bf9233f0bc9fbea1c3e08e73ed4b2037497707a59e467a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T16:18:01Z","title_canon_sha256":"4fa880b9fdee2a9480e7628f3bf053eb2b6fdc2f3f1f33df4cd70f831fa1d743"},"schema_version":"1.0","source":{"id":"2605.30161","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30161","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30161v1","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30161","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"pith_short_12","alias_value":"JSRXVPDUH774","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"pith_short_16","alias_value":"JSRXVPDUH774STAT","created_at":"2026-05-29T02:06:11Z"},{"alias_kind":"pith_short_8","alias_value":"JSRXVPDU","created_at":"2026-05-29T02:06:11Z"}],"graph_snapshots":[{"event_id":"sha256:288f5d1abef7ebcf0d5b293e3c30235a51b991af21b70731619e5284b6c5f8f9","target":"graph","created_at":"2026-05-29T02:06:11Z","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/2605.30161/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) achieve strong performance on spatial reasoning benchmarks, yet it remains unclear whether this reflects structured 3D understanding or reliance on statistical shortcuts in natural images. We introduce a representation-level analysis framework that constructs minimal contrastive pairs to measure how spatial axes are organized and disentangled within VLM embeddings. Our analysis across multiple model families reveals a consistent vertical-distance entanglement: models conflate vertical image position with distance, mirroring the perspective bias of natural photogra","authors_text":"Chan Hee Song, Cheolhong Min, Daeun Lee, Hyeonseong Jeon, Jaesik Park, Jaeyun Jung, Jonathan Tremblay, Yu Su","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T16:18:01Z","title":"Why Far Looks Up: Probing Spatial Representation in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30161","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:b4d0170181387dc0f006c89afb9dce271cd06a05953ce064e6e4f16d93023512","target":"record","created_at":"2026-05-29T02:06:11Z","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":"4e62fe72059166afc1bf9233f0bc9fbea1c3e08e73ed4b2037497707a59e467a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T16:18:01Z","title_canon_sha256":"4fa880b9fdee2a9480e7628f3bf053eb2b6fdc2f3f1f33df4cd70f831fa1d743"},"schema_version":"1.0","source":{"id":"2605.30161","kind":"arxiv","version":1}},"canonical_sha256":"4ca37abc743fffc94c13ce230dd4d8272cbf6254d230eadab5f73c401d8bf4ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ca37abc743fffc94c13ce230dd4d8272cbf6254d230eadab5f73c401d8bf4ed","first_computed_at":"2026-05-29T02:06:11.428660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:11.428660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IAZWq4Iz7nkXUuoSQWHD8nphVSzjpQBew51G1R7mq2KTr6oODLtyr9Su5IK9umdLESp2O2ob9Z+5ZhXP6EaJAQ==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:11.429066Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30161","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4d0170181387dc0f006c89afb9dce271cd06a05953ce064e6e4f16d93023512","sha256:288f5d1abef7ebcf0d5b293e3c30235a51b991af21b70731619e5284b6c5f8f9"],"state_sha256":"0392eac71e331037998e53bbd2fbe4eb1c50b9b5aecbef8a9aa569ef279a8a46"}