{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EK5SK6XRQV4CJMVA6FO4JUK6GH","short_pith_number":"pith:EK5SK6XR","schema_version":"1.0","canonical_sha256":"22bb257af1857824b2a0f15dc4d15e31d845de062250917511761fcff3f021c1","source":{"kind":"arxiv","id":"2605.27311","version":1},"attestation_state":"computed","paper":{"title":"Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dae Yon Hwang, Freda Shi, Jesse C. Cresswell, Yifan Jiang","submitted_at":"2026-05-26T17:20:15Z","abstract_excerpt":"Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning to correctly answer, but models can often reach solutions through shortcuts or prior familiarity with a chart based on their own background knowledge. To strictly evaluate visual reasoning, we propose counterfactual charts where the chart-question task remains fixed, but underlying chart and the corresponding answer are varied. We introduce Chartographer, a framework to reverse engineer charts into executable code, validate reconstruction fidelity, generate seed-controlled counterfactual variants, and "},"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":"2605.27311","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T17:20:15Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"71c56c8414a807c8d9a2ae808160854cfba3e4109621ead3665e584af6f379e3","abstract_canon_sha256":"6e6c19d48ae90f84ebaf238961935f8bc34dd3298b9758105362d7a78db9d9d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:17.589190Z","signature_b64":"HqqpyhjPhyXq0E9oflAd7pJCbOVb2lffaH/Z8SpKmMx1QpynmQTBqmrUfFsGyYF7YF4GsLEHKN0/sWfBKQJvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22bb257af1857824b2a0f15dc4d15e31d845de062250917511761fcff3f021c1","last_reissued_at":"2026-05-27T02:06:17.588531Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:17.588531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chartographer: Counterfactual Chart Generation for Evaluating Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Dae Yon Hwang, Freda Shi, Jesse C. Cresswell, Yifan Jiang","submitted_at":"2026-05-26T17:20:15Z","abstract_excerpt":"Chart question-answering (QA) benchmarks aim to pose questions that require visual reasoning to correctly answer, but models can often reach solutions through shortcuts or prior familiarity with a chart based on their own background knowledge. To strictly evaluate visual reasoning, we propose counterfactual charts where the chart-question task remains fixed, but underlying chart and the corresponding answer are varied. We introduce Chartographer, a framework to reverse engineer charts into executable code, validate reconstruction fidelity, generate seed-controlled counterfactual variants, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27311","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/2605.27311/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":"2605.27311","created_at":"2026-05-27T02:06:17.588624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27311v1","created_at":"2026-05-27T02:06:17.588624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27311","created_at":"2026-05-27T02:06:17.588624+00:00"},{"alias_kind":"pith_short_12","alias_value":"EK5SK6XRQV4C","created_at":"2026-05-27T02:06:17.588624+00:00"},{"alias_kind":"pith_short_16","alias_value":"EK5SK6XRQV4CJMVA","created_at":"2026-05-27T02:06:17.588624+00:00"},{"alias_kind":"pith_short_8","alias_value":"EK5SK6XR","created_at":"2026-05-27T02:06:17.588624+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/EK5SK6XRQV4CJMVA6FO4JUK6GH","json":"https://pith.science/pith/EK5SK6XRQV4CJMVA6FO4JUK6GH.json","graph_json":"https://pith.science/api/pith-number/EK5SK6XRQV4CJMVA6FO4JUK6GH/graph.json","events_json":"https://pith.science/api/pith-number/EK5SK6XRQV4CJMVA6FO4JUK6GH/events.json","paper":"https://pith.science/paper/EK5SK6XR"},"agent_actions":{"view_html":"https://pith.science/pith/EK5SK6XRQV4CJMVA6FO4JUK6GH","download_json":"https://pith.science/pith/EK5SK6XRQV4CJMVA6FO4JUK6GH.json","view_paper":"https://pith.science/paper/EK5SK6XR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27311&json=true","fetch_graph":"https://pith.science/api/pith-number/EK5SK6XRQV4CJMVA6FO4JUK6GH/graph.json","fetch_events":"https://pith.science/api/pith-number/EK5SK6XRQV4CJMVA6FO4JUK6GH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EK5SK6XRQV4CJMVA6FO4JUK6GH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EK5SK6XRQV4CJMVA6FO4JUK6GH/action/storage_attestation","attest_author":"https://pith.science/pith/EK5SK6XRQV4CJMVA6FO4JUK6GH/action/author_attestation","sign_citation":"https://pith.science/pith/EK5SK6XRQV4CJMVA6FO4JUK6GH/action/citation_signature","submit_replication":"https://pith.science/pith/EK5SK6XRQV4CJMVA6FO4JUK6GH/action/replication_record"}},"created_at":"2026-05-27T02:06:17.588624+00:00","updated_at":"2026-05-27T02:06:17.588624+00:00"}