{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OLYMTOX342MOPUAJVJQBHGQDVJ","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":"73b3c666145df703036f19c5b279b49e80d4184d70a00e2a5c905bda31d958d7","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-05T21:36:38Z","title_canon_sha256":"1589ce74c33290672632afc88eebc1144c3c8b99dd0a1bacb5cb0df315f2821e"},"schema_version":"1.0","source":{"id":"2501.02669","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02669","created_at":"2026-07-05T11:14:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02669v2","created_at":"2026-07-05T11:14:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02669","created_at":"2026-07-05T11:14:01Z"},{"alias_kind":"pith_short_12","alias_value":"OLYMTOX342MO","created_at":"2026-07-05T11:14:01Z"},{"alias_kind":"pith_short_16","alias_value":"OLYMTOX342MOPUAJ","created_at":"2026-07-05T11:14:01Z"},{"alias_kind":"pith_short_8","alias_value":"OLYMTOX3","created_at":"2026-07-05T11:14:01Z"}],"graph_snapshots":[{"event_id":"sha256:98fa33d631ce7a5e9ec3e3428a5e24d6daa5df684119938a0354f61494d554fc","target":"graph","created_at":"2026-07-05T11:14:01Z","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/2501.02669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Models (VLMs) are impressive at visual question answering and image captioning. But they underperform on multi-step visual reasoning -- even compared to LLMs on the same tasks presented in text form -- giving rise to perceptions of modality imbalance or brittleness. Towards a systematic study of such issues, we introduce a synthetic framework for assessing the ability of VLMs to perform algorithmic visual reasoning, comprising three tasks: Table Readout, Grid Navigation, and Visual Analogy. Each has two levels of difficulty, SIMPLE and HARD, and even the SIMPLE versions are dif","authors_text":"Abhishek Panigrahi, Anirudh Goyal, Dingli Yu, Sanjeev Arora, Simon Park, Yun Cheng","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-05T21:36:38Z","title":"Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02669","kind":"arxiv","version":2},"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":"sha256:1ea1b2b6dd2ee255ce27298dfb25843e18629272e608ccdbdfadf94c6e960d47","target":"record","created_at":"2026-07-05T11:14:01Z","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":"73b3c666145df703036f19c5b279b49e80d4184d70a00e2a5c905bda31d958d7","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-05T21:36:38Z","title_canon_sha256":"1589ce74c33290672632afc88eebc1144c3c8b99dd0a1bacb5cb0df315f2821e"},"schema_version":"1.0","source":{"id":"2501.02669","kind":"arxiv","version":2}},"canonical_sha256":"72f0c9bafbe698e7d009aa60139a03aa614ef8dc1219768c27e2275857e4a4c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72f0c9bafbe698e7d009aa60139a03aa614ef8dc1219768c27e2275857e4a4c1","first_computed_at":"2026-07-05T11:14:01.755954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:01.755954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7iz8DSnxM8DSr0pH34om6zq7x17Sd8qI9++qo6x1TWaJ6C4u/gT9xOqdf8a/oO18CHkZEJy64j78no+VkAn4CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:01.756438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.02669","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ea1b2b6dd2ee255ce27298dfb25843e18629272e608ccdbdfadf94c6e960d47","sha256:98fa33d631ce7a5e9ec3e3428a5e24d6daa5df684119938a0354f61494d554fc"],"state_sha256":"20d4e5be272fab03a85f5e022d41ba7848451baac2df78c457a87fb75542ff5e"}