{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XQQAGQOERYBLD6JHVXRBM2NC2L","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":"d0fd3437689c0deb822cf7e32519857ec77d100d8e1a75f154952b933c1067f4","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T14:34:06Z","title_canon_sha256":"7527ad2302863734d44440fbc596b6474def68e870cd0e887ee62bc70903995f"},"schema_version":"1.0","source":{"id":"2503.19707","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19707","created_at":"2026-07-05T10:39:00Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19707v1","created_at":"2026-07-05T10:39:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19707","created_at":"2026-07-05T10:39:00Z"},{"alias_kind":"pith_short_12","alias_value":"XQQAGQOERYBL","created_at":"2026-07-05T10:39:00Z"},{"alias_kind":"pith_short_16","alias_value":"XQQAGQOERYBLD6JH","created_at":"2026-07-05T10:39:00Z"},{"alias_kind":"pith_short_8","alias_value":"XQQAGQOE","created_at":"2026-07-05T10:39:00Z"}],"graph_snapshots":[{"event_id":"sha256:fd699903a38ba5e4fb7d9db7cc1c8fb235e0e3c64e9b37f2dc0f2d46d7396352","target":"graph","created_at":"2026-07-05T10:39:00Z","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/2503.19707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have recently emerged as powerful tools, excelling in tasks that integrate visual and textual comprehension, such as image captioning, visual question answering, and image-text retrieval. However, existing benchmarks for VLMs include spatial components, which often fail to isolate spatial reasoning from related tasks such as object detection or semantic comprehension. In this paper, we address these deficiencies with a multi-faceted approach towards understanding spatial reasoning. Informed by the diverse and multi-dimensional nature of human spatial reasoning abi","authors_text":"Ilias Stogiannidis, Sotirios A. Tsaftaris, Steven McDonagh","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T14:34:06Z","title":"Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19707","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:bc10c0b44c222e6edcbe1c0e28acf18961e9d3dffb971b59c47d6f8ff13865e8","target":"record","created_at":"2026-07-05T10:39:00Z","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":"d0fd3437689c0deb822cf7e32519857ec77d100d8e1a75f154952b933c1067f4","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T14:34:06Z","title_canon_sha256":"7527ad2302863734d44440fbc596b6474def68e870cd0e887ee62bc70903995f"},"schema_version":"1.0","source":{"id":"2503.19707","kind":"arxiv","version":1}},"canonical_sha256":"bc200341c48e02b1f927ade21669a2d2c48908438f29af271f91c239c438fd33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc200341c48e02b1f927ade21669a2d2c48908438f29af271f91c239c438fd33","first_computed_at":"2026-07-05T10:39:00.118977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:00.118977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HXSmb+IBBB887HAFAaliiy7VpkoDuL6OdKhrXb7570xiavHP263+OmziQTh78e7e2FubHbsOw7ZasMxZ4a74Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:00.119483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19707","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc10c0b44c222e6edcbe1c0e28acf18961e9d3dffb971b59c47d6f8ff13865e8","sha256:fd699903a38ba5e4fb7d9db7cc1c8fb235e0e3c64e9b37f2dc0f2d46d7396352"],"state_sha256":"fe112ca7695733a157556b3821b7e4aa2ed1e16e1f63a0d16fa06ca20806507b"}