{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5TYUCBMYVLT3Y433VPYHNSEPAB","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":"222419eb9137b86316f1891b236a63af0805c7e3d4fb03f449e49b1d43e7198b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-21T03:53:37Z","title_canon_sha256":"1883f2f60aa7c90d7fe4dd51392ed8119f2971e0405ec9282429460c1eaad70d"},"schema_version":"1.0","source":{"id":"2406.14852","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14852","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14852v2","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14852","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"pith_short_12","alias_value":"5TYUCBMYVLT3","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"pith_short_16","alias_value":"5TYUCBMYVLT3Y433","created_at":"2026-07-05T09:31:04Z"},{"alias_kind":"pith_short_8","alias_value":"5TYUCBMY","created_at":"2026-07-05T09:31:04Z"}],"graph_snapshots":[{"event_id":"sha256:f95d22ff2b0ec7dfc3a51bdf1c720739ba860627eb7459b5c29d6d8756ce447f","target":"graph","created_at":"2026-07-05T09:31:04Z","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/2406.14852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) and vision-language models (VLMs) have demonstrated remarkable performance across a wide range of tasks and domains. Despite this promise, spatial understanding and reasoning -- a fundamental component of human cognition -- remains under-explored. We propose SpatialEval, a novel benchmark that covers diverse aspects of spatial reasoning such as relationship understanding, navigation, and counting. We conduct a comprehensive evaluation of competitive language and vision-language models. Our findings reveal several counter-intuitive insights that have been overlooked","authors_text":"Jiayu Wang, Neel Joshi, Vibhav Vineet, Xin Wang, Yifei Ming, Yixuan Li, Zhenmei Shi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-21T03:53:37Z","title":"Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14852","kind":"arxiv","version":2},"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:d41a84a5a277a3c58f2c23b8ee444f77429662deb4db62359a11244eb46810e0","target":"record","created_at":"2026-07-05T09:31:04Z","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":"222419eb9137b86316f1891b236a63af0805c7e3d4fb03f449e49b1d43e7198b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-21T03:53:37Z","title_canon_sha256":"1883f2f60aa7c90d7fe4dd51392ed8119f2971e0405ec9282429460c1eaad70d"},"schema_version":"1.0","source":{"id":"2406.14852","kind":"arxiv","version":2}},"canonical_sha256":"ecf1410598aae7bc737babf076c88f006c78dccf486239089362e8d0e05977fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecf1410598aae7bc737babf076c88f006c78dccf486239089362e8d0e05977fa","first_computed_at":"2026-07-05T09:31:04.629380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:04.629380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wzrqGI00r1MA7T32WCAcA0OeROJdcKtMXZf2iskPMk8+jNKAyN8E0n9l85+GeKi5EHkEajWu4gvd4vCpinRTCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:04.629905Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14852","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d41a84a5a277a3c58f2c23b8ee444f77429662deb4db62359a11244eb46810e0","sha256:f95d22ff2b0ec7dfc3a51bdf1c720739ba860627eb7459b5c29d6d8756ce447f"],"state_sha256":"e2af9a0e01006ef845403764b2aa9aa4cf6e1ad05865a10405151bf8339eb4d6"}