{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LQB3ZA4EOKXWFRCITOH2ZNQBDJ","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":"4fb86b9426a7a5430517bcf964797e0c9c717b69ccca842cc8369ce1ccb87ffd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T11:18:38Z","title_canon_sha256":"8286a24efe77611f1d2de2d5c9d77a490eb2d29acd6b4d250d26fb57cda22e1e"},"schema_version":"1.0","source":{"id":"2504.20648","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20648","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20648v1","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20648","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"pith_short_12","alias_value":"LQB3ZA4EOKXW","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"pith_short_16","alias_value":"LQB3ZA4EOKXWFRCI","created_at":"2026-07-05T10:55:46Z"},{"alias_kind":"pith_short_8","alias_value":"LQB3ZA4E","created_at":"2026-07-05T10:55:46Z"}],"graph_snapshots":[{"event_id":"sha256:6f14efc9e11b1bcb5d9082b0bb18beabb6e9be3d4e707c1731884530f2c983d3","target":"graph","created_at":"2026-07-05T10:55:46Z","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/2504.20648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) work well in tasks ranging from image captioning to visual question answering (VQA), yet they struggle with spatial reasoning, a key skill for understanding our physical world that humans excel at. We find that spatial relations are generally rare in widely used VL datasets, with only a few being well represented, while most form a long tail of underrepresented relations. This gap leaves VLMs ill-equipped to handle diverse spatial relationships. To bridge it, we construct a synthetic VQA dataset focused on spatial reasoning generated from hyper-detailed image desc","authors_text":"Freda Shi, Michael Ogezi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T11:18:38Z","title":"SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20648","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:b24103139b77e1f497aeac4bf73ab15d2ce607beb60dbef76135565d53fbd406","target":"record","created_at":"2026-07-05T10:55:46Z","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":"4fb86b9426a7a5430517bcf964797e0c9c717b69ccca842cc8369ce1ccb87ffd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T11:18:38Z","title_canon_sha256":"8286a24efe77611f1d2de2d5c9d77a490eb2d29acd6b4d250d26fb57cda22e1e"},"schema_version":"1.0","source":{"id":"2504.20648","kind":"arxiv","version":1}},"canonical_sha256":"5c03bc838472af62c4489b8facb6011a55950e1e074090b15649761ac5a3eebc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c03bc838472af62c4489b8facb6011a55950e1e074090b15649761ac5a3eebc","first_computed_at":"2026-07-05T10:55:46.348328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:46.348328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GlpmoJjoK17LX+Y3PQ3VxNLPQGXKXc2RuEwP5YQWnFPacXMWlLZYuZpEO6WrljNhxQbRP8rM2G25OL96pVeZCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:46.349048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.20648","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b24103139b77e1f497aeac4bf73ab15d2ce607beb60dbef76135565d53fbd406","sha256:6f14efc9e11b1bcb5d9082b0bb18beabb6e9be3d4e707c1731884530f2c983d3"],"state_sha256":"155ab030849bd88e617c40ae96819b2c06489062105663f204f7ac88ee46811b"}