{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OLYMTOX342MOPUAJVJQBHGQDVJ","short_pith_number":"pith:OLYMTOX3","canonical_record":{"source":{"id":"2501.02669","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-05T21:36:38Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1589ce74c33290672632afc88eebc1144c3c8b99dd0a1bacb5cb0df315f2821e","abstract_canon_sha256":"73b3c666145df703036f19c5b279b49e80d4184d70a00e2a5c905bda31d958d7"},"schema_version":"1.0"},"canonical_sha256":"72f0c9bafbe698e7d009aa60139a03aa614ef8dc1219768c27e2275857e4a4c1","source":{"kind":"arxiv","id":"2501.02669","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OLYMTOX342MOPUAJVJQBHGQDVJ","target":"record","payload":{"canonical_record":{"source":{"id":"2501.02669","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-05T21:36:38Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1589ce74c33290672632afc88eebc1144c3c8b99dd0a1bacb5cb0df315f2821e","abstract_canon_sha256":"73b3c666145df703036f19c5b279b49e80d4184d70a00e2a5c905bda31d958d7"},"schema_version":"1.0"},"canonical_sha256":"72f0c9bafbe698e7d009aa60139a03aa614ef8dc1219768c27e2275857e4a4c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:01.756438Z","signature_b64":"7iz8DSnxM8DSr0pH34om6zq7x17Sd8qI9++qo6x1TWaJ6C4u/gT9xOqdf8a/oO18CHkZEJy64j78no+VkAn4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72f0c9bafbe698e7d009aa60139a03aa614ef8dc1219768c27e2275857e4a4c1","last_reissued_at":"2026-07-05T11:14:01.755954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:01.755954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.02669","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lpVmD9IBrtoF266uz4ebs5zHIAb+Ui1Nn/zdgws2CpcZ+FADxZ1jsMBepsqJuyZDfYZfXge+w/vFcu7toAQYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:10:15.602160Z"},"content_sha256":"1ea1b2b6dd2ee255ce27298dfb25843e18629272e608ccdbdfadf94c6e960d47","schema_version":"1.0","event_id":"sha256:1ea1b2b6dd2ee255ce27298dfb25843e18629272e608ccdbdfadf94c6e960d47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OLYMTOX342MOPUAJVJQBHGQDVJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhishek Panigrahi, Anirudh Goyal, Dingli Yu, Sanjeev Arora, Simon Park, Yun Cheng","submitted_at":"2025-01-05T21:36:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02669","kind":"arxiv","version":2},"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/2501.02669/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":"2026-07-05T11:14:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"67OQVaWFqvwAko0Z0gxciSfSlTrLu+PYR6KfmDmgwk5eVX7ZJGEq247436wVquUj/ul6ehkfFCCnAa3HU8CyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:10:15.602997Z"},"content_sha256":"98fa33d631ce7a5e9ec3e3428a5e24d6daa5df684119938a0354f61494d554fc","schema_version":"1.0","event_id":"sha256:98fa33d631ce7a5e9ec3e3428a5e24d6daa5df684119938a0354f61494d554fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OLYMTOX342MOPUAJVJQBHGQDVJ/bundle.json","state_url":"https://pith.science/pith/OLYMTOX342MOPUAJVJQBHGQDVJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OLYMTOX342MOPUAJVJQBHGQDVJ/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":"2026-08-18T04:10:15Z","links":{"resolver":"https://pith.science/pith/OLYMTOX342MOPUAJVJQBHGQDVJ","bundle":"https://pith.science/pith/OLYMTOX342MOPUAJVJQBHGQDVJ/bundle.json","state":"https://pith.science/pith/OLYMTOX342MOPUAJVJQBHGQDVJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OLYMTOX342MOPUAJVJQBHGQDVJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CNjsC1LjTVRPpheRLMZbhe/9g/m79kOFf4nN9f6/IJxAdI+MAcmvRyONFXVjM05Lvo5OumKbw9amArpAN5J1Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T04:10:15.609330Z","bundle_sha256":"e15ec9ab0572dab19d3c7f1f605f7f335c64dd0cee9644ef261a871ff39c8cec"}}