{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WQOAWIUJCAHUOHHES446343PT3","short_pith_number":"pith:WQOAWIUJ","canonical_record":{"source":{"id":"2406.02537","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T17:55:43Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"cb41a6274cde15ee2565d6c4cb994276fb69140fc356eb2ee0d24bba0a3d05dc","abstract_canon_sha256":"9aa957058df1d50d62747486b46e27cafe017118a5363e6ce7d5159d5c991151"},"schema_version":"1.0"},"canonical_sha256":"b41c0b2289100f471ce49739edf36f9eed32f06146ee07498c25684bec8d0a45","source":{"kind":"arxiv","id":"2406.02537","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02537","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02537v1","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02537","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"pith_short_12","alias_value":"WQOAWIUJCAHU","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"pith_short_16","alias_value":"WQOAWIUJCAHUOHHE","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"pith_short_8","alias_value":"WQOAWIUJ","created_at":"2026-07-05T08:27:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WQOAWIUJCAHUOHHES446343PT3","target":"record","payload":{"canonical_record":{"source":{"id":"2406.02537","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T17:55:43Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"cb41a6274cde15ee2565d6c4cb994276fb69140fc356eb2ee0d24bba0a3d05dc","abstract_canon_sha256":"9aa957058df1d50d62747486b46e27cafe017118a5363e6ce7d5159d5c991151"},"schema_version":"1.0"},"canonical_sha256":"b41c0b2289100f471ce49739edf36f9eed32f06146ee07498c25684bec8d0a45","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:21.059965Z","signature_b64":"gqKlpNq03xAMJXWk6XsmZTAcvMjYA+x56X43yuVqyAszinl7OrqEIL4YBIyMdKG7KeNJIcohqP6iW779V0m5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b41c0b2289100f471ce49739edf36f9eed32f06146ee07498c25684bec8d0a45","last_reissued_at":"2026-07-05T08:27:21.059536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:21.059536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.02537","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:27:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bWxXBZUXCwcgn8JI2YB2L9HKwEYS3Mu9HR6OYGod2gXvAvBXj2QIMY7fVZdWYHkxPJ1SQcKlRM2hLV9HHyR3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:46:05.404383Z"},"content_sha256":"d44c5c840665a2c09c42d691a8ee82394b8a32b39ba1a830cf938823249f1d61","schema_version":"1.0","event_id":"sha256:d44c5c840665a2c09c42d691a8ee82394b8a32b39ba1a830cf938823249f1d61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WQOAWIUJCAHUOHHES446343PT3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TopViewRS: Vision-Language Models as Top-View Spatial Reasoners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Caiqi Zhang, Chengzu Li, Han Zhou, Ivan Vuli\\'c, Nigel Collier","submitted_at":"2024-06-04T17:55:43Z","abstract_excerpt":"Top-view perspective denotes a typical way in which humans read and reason over different types of maps, and it is vital for localization and navigation of humans as well as of `non-human' agents, such as the ones backed by large Vision-Language Models (VLMs). Nonetheless, spatial reasoning capabilities of modern VLMs remain unattested and underexplored. In this work, we thus study their capability to understand and reason over spatial relations from the top view. The focus on top view also enables controlled evaluations at different granularity of spatial reasoning; we clearly disentangle dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02537","kind":"arxiv","version":1},"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/2406.02537/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:27:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3GSvMwpln+YHDtcUZXeOlAB0vNv3wPNbTPQbOEMe8iVjGw81YOJEOCmohKRN7BTPQ2t+Ud8m8R66T4BIArUqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:46:05.404891Z"},"content_sha256":"2ebde1a614bc7983edcd8dc9873536f877b73291e92f33bf50aa7d6185b48c1a","schema_version":"1.0","event_id":"sha256:2ebde1a614bc7983edcd8dc9873536f877b73291e92f33bf50aa7d6185b48c1a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WQOAWIUJCAHUOHHES446343PT3/bundle.json","state_url":"https://pith.science/pith/WQOAWIUJCAHUOHHES446343PT3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WQOAWIUJCAHUOHHES446343PT3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T05:46:05Z","links":{"resolver":"https://pith.science/pith/WQOAWIUJCAHUOHHES446343PT3","bundle":"https://pith.science/pith/WQOAWIUJCAHUOHHES446343PT3/bundle.json","state":"https://pith.science/pith/WQOAWIUJCAHUOHHES446343PT3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WQOAWIUJCAHUOHHES446343PT3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WQOAWIUJCAHUOHHES446343PT3","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":"9aa957058df1d50d62747486b46e27cafe017118a5363e6ce7d5159d5c991151","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T17:55:43Z","title_canon_sha256":"cb41a6274cde15ee2565d6c4cb994276fb69140fc356eb2ee0d24bba0a3d05dc"},"schema_version":"1.0","source":{"id":"2406.02537","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.02537","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"arxiv_version","alias_value":"2406.02537v1","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02537","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"pith_short_12","alias_value":"WQOAWIUJCAHU","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"pith_short_16","alias_value":"WQOAWIUJCAHUOHHE","created_at":"2026-07-05T08:27:21Z"},{"alias_kind":"pith_short_8","alias_value":"WQOAWIUJ","created_at":"2026-07-05T08:27:21Z"}],"graph_snapshots":[{"event_id":"sha256:2ebde1a614bc7983edcd8dc9873536f877b73291e92f33bf50aa7d6185b48c1a","target":"graph","created_at":"2026-07-05T08:27:21Z","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/2406.02537/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Top-view perspective denotes a typical way in which humans read and reason over different types of maps, and it is vital for localization and navigation of humans as well as of `non-human' agents, such as the ones backed by large Vision-Language Models (VLMs). Nonetheless, spatial reasoning capabilities of modern VLMs remain unattested and underexplored. In this work, we thus study their capability to understand and reason over spatial relations from the top view. The focus on top view also enables controlled evaluations at different granularity of spatial reasoning; we clearly disentangle dif","authors_text":"Anna Korhonen, Caiqi Zhang, Chengzu Li, Han Zhou, Ivan Vuli\\'c, Nigel Collier","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T17:55:43Z","title":"TopViewRS: Vision-Language Models as Top-View Spatial Reasoners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02537","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:d44c5c840665a2c09c42d691a8ee82394b8a32b39ba1a830cf938823249f1d61","target":"record","created_at":"2026-07-05T08:27:21Z","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":"9aa957058df1d50d62747486b46e27cafe017118a5363e6ce7d5159d5c991151","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T17:55:43Z","title_canon_sha256":"cb41a6274cde15ee2565d6c4cb994276fb69140fc356eb2ee0d24bba0a3d05dc"},"schema_version":"1.0","source":{"id":"2406.02537","kind":"arxiv","version":1}},"canonical_sha256":"b41c0b2289100f471ce49739edf36f9eed32f06146ee07498c25684bec8d0a45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b41c0b2289100f471ce49739edf36f9eed32f06146ee07498c25684bec8d0a45","first_computed_at":"2026-07-05T08:27:21.059536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:21.059536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gqKlpNq03xAMJXWk6XsmZTAcvMjYA+x56X43yuVqyAszinl7OrqEIL4YBIyMdKG7KeNJIcohqP6iW779V0m5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:21.059965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.02537","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d44c5c840665a2c09c42d691a8ee82394b8a32b39ba1a830cf938823249f1d61","sha256:2ebde1a614bc7983edcd8dc9873536f877b73291e92f33bf50aa7d6185b48c1a"],"state_sha256":"30ef279baf167177967c505374264b4ffcf35c8602b86414a70381e9359cedac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QGX5c5sldq/LSeCg22MQGn4QdxWwZkyqDChEvvN4q8iknfV8MIT02Hrj350JaVmQE7eJnt+NHkmLNwgLgbirBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T05:46:05.407839Z","bundle_sha256":"87c551bdbcefd4f1599f19f1cde81dc0199bb505d673f2adf0987d5927838476"}}