{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5TYUCBMYVLT3Y433VPYHNSEPAB","short_pith_number":"pith:5TYUCBMY","schema_version":"1.0","canonical_sha256":"ecf1410598aae7bc737babf076c88f006c78dccf486239089362e8d0e05977fa","source":{"kind":"arxiv","id":"2406.14852","version":2},"attestation_state":"computed","paper":{"title":"Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiayu Wang, Neel Joshi, Vibhav Vineet, Xin Wang, Yifei Ming, Yixuan Li, Zhenmei Shi","submitted_at":"2024-06-21T03:53:37Z","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"},"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":"2406.14852","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-21T03:53:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1883f2f60aa7c90d7fe4dd51392ed8119f2971e0405ec9282429460c1eaad70d","abstract_canon_sha256":"222419eb9137b86316f1891b236a63af0805c7e3d4fb03f449e49b1d43e7198b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:04.629905Z","signature_b64":"wzrqGI00r1MA7T32WCAcA0OeROJdcKtMXZf2iskPMk8+jNKAyN8E0n9l85+GeKi5EHkEajWu4gvd4vCpinRTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecf1410598aae7bc737babf076c88f006c78dccf486239089362e8d0e05977fa","last_reissued_at":"2026-07-05T09:31:04.629380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:04.629380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiayu Wang, Neel Joshi, Vibhav Vineet, Xin Wang, Yifei Ming, Yixuan Li, Zhenmei Shi","submitted_at":"2024-06-21T03:53:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14852","kind":"arxiv","version":2},"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/2406.14852/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":"2406.14852","created_at":"2026-07-05T09:31:04.629449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14852v2","created_at":"2026-07-05T09:31:04.629449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14852","created_at":"2026-07-05T09:31:04.629449+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TYUCBMYVLT3","created_at":"2026-07-05T09:31:04.629449+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TYUCBMYVLT3Y433","created_at":"2026-07-05T09:31:04.629449+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TYUCBMY","created_at":"2026-07-05T09:31:04.629449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22219","citing_title":"Lost in Aggregation: A Multi-Scale Diagnostic Benchmark for LLM Spatial Navigation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23771","citing_title":"PhotoFlow: Agentic 3D Virtual Photography Missions","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07557","citing_title":"AutoSpatial: Visual-Language Reasoning for Social Robot Navigation through Efficient Spatial Reasoning Learning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13634","citing_title":"Europe and the Geopolitics of AGI: The Need for a Preparedness Plan","ref_index":296,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5TYUCBMYVLT3Y433VPYHNSEPAB","json":"https://pith.science/pith/5TYUCBMYVLT3Y433VPYHNSEPAB.json","graph_json":"https://pith.science/api/pith-number/5TYUCBMYVLT3Y433VPYHNSEPAB/graph.json","events_json":"https://pith.science/api/pith-number/5TYUCBMYVLT3Y433VPYHNSEPAB/events.json","paper":"https://pith.science/paper/5TYUCBMY"},"agent_actions":{"view_html":"https://pith.science/pith/5TYUCBMYVLT3Y433VPYHNSEPAB","download_json":"https://pith.science/pith/5TYUCBMYVLT3Y433VPYHNSEPAB.json","view_paper":"https://pith.science/paper/5TYUCBMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14852&json=true","fetch_graph":"https://pith.science/api/pith-number/5TYUCBMYVLT3Y433VPYHNSEPAB/graph.json","fetch_events":"https://pith.science/api/pith-number/5TYUCBMYVLT3Y433VPYHNSEPAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TYUCBMYVLT3Y433VPYHNSEPAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TYUCBMYVLT3Y433VPYHNSEPAB/action/storage_attestation","attest_author":"https://pith.science/pith/5TYUCBMYVLT3Y433VPYHNSEPAB/action/author_attestation","sign_citation":"https://pith.science/pith/5TYUCBMYVLT3Y433VPYHNSEPAB/action/citation_signature","submit_replication":"https://pith.science/pith/5TYUCBMYVLT3Y433VPYHNSEPAB/action/replication_record"}},"created_at":"2026-07-05T09:31:04.629449+00:00","updated_at":"2026-07-05T09:31:04.629449+00:00"}