{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7QAJJB5CGCISAB243HTBFI2TLA","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":"4c13e56ee426cae938defad7f788b28cc2d8f70aa854302c8e3b80ea3838c599","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-30T23:03:49Z","title_canon_sha256":"27e9ba5e6a6f4aaac9b2383c121bb090e2b6c87ed7bec3c6eab77bdaf6d39752"},"schema_version":"1.0","source":{"id":"2205.00363","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.00363","created_at":"2026-07-05T05:53:31Z"},{"alias_kind":"arxiv_version","alias_value":"2205.00363v3","created_at":"2026-07-05T05:53:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.00363","created_at":"2026-07-05T05:53:31Z"},{"alias_kind":"pith_short_12","alias_value":"7QAJJB5CGCIS","created_at":"2026-07-05T05:53:31Z"},{"alias_kind":"pith_short_16","alias_value":"7QAJJB5CGCISAB24","created_at":"2026-07-05T05:53:31Z"},{"alias_kind":"pith_short_8","alias_value":"7QAJJB5C","created_at":"2026-07-05T05:53:31Z"}],"graph_snapshots":[{"event_id":"sha256:cbcde6649e961bb493ead25027a4d2c85d4ae160d07b8a2c5471a2ab469765e9","target":"graph","created_at":"2026-07-05T05:53:31Z","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/2205.00363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial relations are a basic part of human cognition. However, they are expressed in natural language in a variety of ways, and previous work has suggested that current vision-and-language models (VLMs) struggle to capture relational information. In this paper, we present Visual Spatial Reasoning (VSR), a dataset containing more than 10k natural text-image pairs with 66 types of spatial relations in English (such as: under, in front of, and facing). While using a seemingly simple annotation format, we show how the dataset includes challenging linguistic phenomena, such as varying reference fr","authors_text":"Fangyu Liu, Guy Emerson, Nigel Collier","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-30T23:03:49Z","title":"Visual Spatial Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.00363","kind":"arxiv","version":3},"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":"sha256:2a45831c0fceda807f0ebe5e4560019fabc524e178d9375c2d819bdcb33343ec","target":"record","created_at":"2026-07-05T05:53:31Z","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":"4c13e56ee426cae938defad7f788b28cc2d8f70aa854302c8e3b80ea3838c599","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-30T23:03:49Z","title_canon_sha256":"27e9ba5e6a6f4aaac9b2383c121bb090e2b6c87ed7bec3c6eab77bdaf6d39752"},"schema_version":"1.0","source":{"id":"2205.00363","kind":"arxiv","version":3}},"canonical_sha256":"fc009487a2309120075cd9e612a35358364501e63962dd762e28473dc37e677a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc009487a2309120075cd9e612a35358364501e63962dd762e28473dc37e677a","first_computed_at":"2026-07-05T05:53:31.718601Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:53:31.718601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pfwTzUdudk5tvDXpjIsAWDyMp47du2yd0gbYA/OWaB1isRjX4ne7ntUe+MASuWGg/9TEN14cWphoHMWc9SiSBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:53:31.719148Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.00363","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a45831c0fceda807f0ebe5e4560019fabc524e178d9375c2d819bdcb33343ec","sha256:cbcde6649e961bb493ead25027a4d2c85d4ae160d07b8a2c5471a2ab469765e9"],"state_sha256":"95fe816ae551fa637b432f66c6a99e3b8e1eaba697fe8c9f91a2bb1396c95e97"}