{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EAGXZFQUDREX7ONWRY54FS7T63","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":"6985f051f720d729098a623a0ed25f4b1ab5f557eb01753b72d1d49adc26a513","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T15:25:39Z","title_canon_sha256":"0a03cd10e02d4b2030ec6984dd41b633c738b2867d01e135507e5b8a62442560"},"schema_version":"1.0","source":{"id":"2312.12241","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.12241","created_at":"2026-07-05T07:26:00Z"},{"alias_kind":"arxiv_version","alias_value":"2312.12241v1","created_at":"2026-07-05T07:26:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12241","created_at":"2026-07-05T07:26:00Z"},{"alias_kind":"pith_short_12","alias_value":"EAGXZFQUDREX","created_at":"2026-07-05T07:26:00Z"},{"alias_kind":"pith_short_16","alias_value":"EAGXZFQUDREX7ONW","created_at":"2026-07-05T07:26:00Z"},{"alias_kind":"pith_short_8","alias_value":"EAGXZFQU","created_at":"2026-07-05T07:26:00Z"}],"graph_snapshots":[{"event_id":"sha256:3ed9d939bb90074491fc25142701735eb2a13136c3a02d702b42c0e97caa83c0","target":"graph","created_at":"2026-07-05T07:26:00Z","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/2312.12241/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have shown impressive results for multi-hop mathematical reasoning when the input question is only textual. Many mathematical reasoning problems, however, contain both text and image. With the ever-increasing adoption of vision language models (VLMs), understanding their reasoning abilities for such problems is crucial. In this paper, we evaluate the reasoning capabilities of VLMs along various axes through the lens of geometry problems. We procedurally create a synthetic dataset of geometry questions with controllable difficulty levels along multiple axes, thus enabling ","authors_text":"Ankit Anand, Hamidreza Alvari, Jialin Wu, Mehran Kazemi, Radu Soricut, Xi Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T15:25:39Z","title":"GeomVerse: A Systematic Evaluation of Large Models for Geometric Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12241","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:a30f56960676cbe2c697ed07677114fed3658076fe4b2c6204dc50d73522f7f4","target":"record","created_at":"2026-07-05T07:26:00Z","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":"6985f051f720d729098a623a0ed25f4b1ab5f557eb01753b72d1d49adc26a513","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T15:25:39Z","title_canon_sha256":"0a03cd10e02d4b2030ec6984dd41b633c738b2867d01e135507e5b8a62442560"},"schema_version":"1.0","source":{"id":"2312.12241","kind":"arxiv","version":1}},"canonical_sha256":"200d7c96141c497fb9b68e3bc2cbf3f6e09c076580037b40652db25efd1936d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"200d7c96141c497fb9b68e3bc2cbf3f6e09c076580037b40652db25efd1936d7","first_computed_at":"2026-07-05T07:26:00.924514Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:26:00.924514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iVaLdbkORfAyIdndQVU7K+/l27rdXd/ZAg9be0P6zEetfuxLIoWXNTYy+nqfMhQzDY1YcxnfDca2IW2ilCaCCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:26:00.924984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.12241","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a30f56960676cbe2c697ed07677114fed3658076fe4b2c6204dc50d73522f7f4","sha256:3ed9d939bb90074491fc25142701735eb2a13136c3a02d702b42c0e97caa83c0"],"state_sha256":"96ba1ee284d4a8c6cb9317e32d59e57d326058843d74d9b72b1218fa0eb2bb04"}