{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GEHUTJQYQI5353PKXL6SWPEL45","short_pith_number":"pith:GEHUTJQY","schema_version":"1.0","canonical_sha256":"310f49a618823bbeedeabafd2b3c8be7408d569006ebd9bb7472692d0489146f","source":{"kind":"arxiv","id":"2509.09013","version":1},"attestation_state":"computed","paper":{"title":"Can Vision-Language Models Solve Visual Math Equations?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Junling Wang, Monjoy Narayan Choudhury, Mrinmaya Sachan, Yifan Hou","submitted_at":"2025-09-10T21:16:11Z","abstract_excerpt":"Despite strong performance in visual understanding and language-based reasoning, Vision-Language Models (VLMs) struggle with tasks requiring integrated perception and symbolic computation. We study this limitation through visual equation solving, where mathematical equations are embedded in images, variables are represented by object icons, and coefficients must be inferred by counting. While VLMs perform well on textual equations, they fail on visually grounded counterparts. To understand this gap, we decompose the task into coefficient counting and variable recognition, and find that countin"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2509.09013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-10T21:16:11Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"4005dd58b0e83edf1aef59fb71a36f3e801185dc3c7879ea8ffc661cdbfd6c5d","abstract_canon_sha256":"ef99bb56291d0df96a8afecbe3a071533851e11fd8f6ea1a0b225608d8abf2c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:27.599767Z","signature_b64":"ynU17rKGGS4SUucHdcAEiQqE7bqwMxMgldJqByiHSItcjhtBCgMghCkn1drqmPgEPX6Bp8xT3KoltQuSfXbZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"310f49a618823bbeedeabafd2b3c8be7408d569006ebd9bb7472692d0489146f","last_reissued_at":"2026-07-05T12:09:27.599214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:27.599214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Vision-Language Models Solve Visual Math Equations?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Junling Wang, Monjoy Narayan Choudhury, Mrinmaya Sachan, Yifan Hou","submitted_at":"2025-09-10T21:16:11Z","abstract_excerpt":"Despite strong performance in visual understanding and language-based reasoning, Vision-Language Models (VLMs) struggle with tasks requiring integrated perception and symbolic computation. We study this limitation through visual equation solving, where mathematical equations are embedded in images, variables are represented by object icons, and coefficients must be inferred by counting. While VLMs perform well on textual equations, they fail on visually grounded counterparts. To understand this gap, we decompose the task into coefficient counting and variable recognition, and find that countin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09013","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/2509.09013/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2509.09013","created_at":"2026-07-05T12:09:27.599295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09013v1","created_at":"2026-07-05T12:09:27.599295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09013","created_at":"2026-07-05T12:09:27.599295+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEHUTJQYQI53","created_at":"2026-07-05T12:09:27.599295+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEHUTJQYQI5353PK","created_at":"2026-07-05T12:09:27.599295+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEHUTJQY","created_at":"2026-07-05T12:09:27.599295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GEHUTJQYQI5353PKXL6SWPEL45","json":"https://pith.science/pith/GEHUTJQYQI5353PKXL6SWPEL45.json","graph_json":"https://pith.science/api/pith-number/GEHUTJQYQI5353PKXL6SWPEL45/graph.json","events_json":"https://pith.science/api/pith-number/GEHUTJQYQI5353PKXL6SWPEL45/events.json","paper":"https://pith.science/paper/GEHUTJQY"},"agent_actions":{"view_html":"https://pith.science/pith/GEHUTJQYQI5353PKXL6SWPEL45","download_json":"https://pith.science/pith/GEHUTJQYQI5353PKXL6SWPEL45.json","view_paper":"https://pith.science/paper/GEHUTJQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09013&json=true","fetch_graph":"https://pith.science/api/pith-number/GEHUTJQYQI5353PKXL6SWPEL45/graph.json","fetch_events":"https://pith.science/api/pith-number/GEHUTJQYQI5353PKXL6SWPEL45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEHUTJQYQI5353PKXL6SWPEL45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEHUTJQYQI5353PKXL6SWPEL45/action/storage_attestation","attest_author":"https://pith.science/pith/GEHUTJQYQI5353PKXL6SWPEL45/action/author_attestation","sign_citation":"https://pith.science/pith/GEHUTJQYQI5353PKXL6SWPEL45/action/citation_signature","submit_replication":"https://pith.science/pith/GEHUTJQYQI5353PKXL6SWPEL45/action/replication_record"}},"created_at":"2026-07-05T12:09:27.599295+00:00","updated_at":"2026-07-05T12:09:27.599295+00:00"}