{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BFYLXW5FOZPT4ZCOY2W7YCK7SP","short_pith_number":"pith:BFYLXW5F","schema_version":"1.0","canonical_sha256":"0970bbdba5765f3e644ec6adfc095f93c53a03c228ae6a12969e1a70cd829ada","source":{"kind":"arxiv","id":"1710.07300","version":2},"attestation_state":"computed","paper":{"title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Atkinson, Adam Trischler, Akos Kadar, Samira Ebrahimi Kahou, Vincent Michalski, Yoshua Bengio","submitted_at":"2017-10-19T18:01:38Z","abstract_excerpt":"We introduce FigureQA, a visual reasoning corpus of over one million question-answer pairs grounded in over 100,000 images. The images are synthetic, scientific-style figures from five classes: line plots, dot-line plots, vertical and horizontal bar graphs, and pie charts. We formulate our reasoning task by generating questions from 15 templates; questions concern various relationships between plot elements and examine characteristics like the maximum, the minimum, area-under-the-curve, smoothness, and intersection. To resolve, such questions often require reference to multiple plot elements a"},"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":"1710.07300","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-10-19T18:01:38Z","cross_cats_sorted":[],"title_canon_sha256":"4f4bcdcca150faf52e2d4ce8414aaa35586213b043c0c6ec55742987e469877e","abstract_canon_sha256":"19896e05ae8dd53d118d1be54f7e685e1c0e0108e11c711efb4d6c5f712f4e9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:44.447374Z","signature_b64":"hTJbrdYgdjg55YQIg7tUjD1hLfoU1WO3jZIms9PAmY/EcXnFHa5cpWLjmKySPLnh5GXu8tAC7C3t7hk5zUIQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0970bbdba5765f3e644ec6adfc095f93c53a03c228ae6a12969e1a70cd829ada","last_reissued_at":"2026-05-18T00:22:44.446917Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:44.446917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Atkinson, Adam Trischler, Akos Kadar, Samira Ebrahimi Kahou, Vincent Michalski, Yoshua Bengio","submitted_at":"2017-10-19T18:01:38Z","abstract_excerpt":"We introduce FigureQA, a visual reasoning corpus of over one million question-answer pairs grounded in over 100,000 images. The images are synthetic, scientific-style figures from five classes: line plots, dot-line plots, vertical and horizontal bar graphs, and pie charts. We formulate our reasoning task by generating questions from 15 templates; questions concern various relationships between plot elements and examine characteristics like the maximum, the minimum, area-under-the-curve, smoothness, and intersection. To resolve, such questions often require reference to multiple plot elements a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.07300","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":""},"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":"1710.07300","created_at":"2026-05-18T00:22:44.446999+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.07300v2","created_at":"2026-05-18T00:22:44.446999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.07300","created_at":"2026-05-18T00:22:44.446999+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFYLXW5FOZPT","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFYLXW5FOZPT4ZCO","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFYLXW5F","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":10,"sample":[{"citing_arxiv_id":"2410.14702","citing_title":"Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15529","citing_title":"Process Rewards with Learned Reliability","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2503.17352","citing_title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2508.07630","citing_title":"InterChart: Benchmarking Visual Reasoning Across Decomposed and Distributed Chart Information","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2503.07536","citing_title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2601.13606","citing_title":"ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2601.17736","citing_title":"From Static to Interactive: Authoring Interactive Visualizations via Natural Language","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2602.13232","citing_title":"PlotChain: Deterministic Checkpointed Evaluation of Multimodal LLMs on Engineering Plot Reading","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2601.10611","citing_title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2409.17146","citing_title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00161","citing_title":"Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03157","citing_title":"Chart-RL: Policy Optimization Reinforcement Learning for Enhanced Visual Reasoning in Chart Question Answering with Vision Language Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04172","citing_title":"GENFIG1: Visual Summaries of Scholarly Work as a Challenge for Vision-Language Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11307","citing_title":"Vision2Code: A Multi-Domain Benchmark for Evaluating Image-to-Code Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08560","citing_title":"ZAYA1-VL-8B Technical Report","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25884","citing_title":"QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understanding","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19567","citing_title":"Multi-modal Reasoning with LLMs for Visual Semantic Arithmetic","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01882","citing_title":"Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2505.07062","citing_title":"Seed1.5-VL Technical Report","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09691","citing_title":"CAGE: Bridging the Accuracy-Aesthetics Gap in Educational Diagrams via Code-Anchored Generative Enhancement","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04411","citing_title":"Responses Fall Short of Understanding: Revealing the Gap between Internal Representations and Responses in Visual Document Understanding","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01800","citing_title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21344","citing_title":"Beyond Single Plots: A Benchmark for Question Answering on Multi-Charts","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24987","citing_title":"Assessing Y-Axis Influence: Bias in Multimodal Language Models on Chart-to-Table Translation","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BFYLXW5FOZPT4ZCOY2W7YCK7SP","json":"https://pith.science/pith/BFYLXW5FOZPT4ZCOY2W7YCK7SP.json","graph_json":"https://pith.science/api/pith-number/BFYLXW5FOZPT4ZCOY2W7YCK7SP/graph.json","events_json":"https://pith.science/api/pith-number/BFYLXW5FOZPT4ZCOY2W7YCK7SP/events.json","paper":"https://pith.science/paper/BFYLXW5F"},"agent_actions":{"view_html":"https://pith.science/pith/BFYLXW5FOZPT4ZCOY2W7YCK7SP","download_json":"https://pith.science/pith/BFYLXW5FOZPT4ZCOY2W7YCK7SP.json","view_paper":"https://pith.science/paper/BFYLXW5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.07300&json=true","fetch_graph":"https://pith.science/api/pith-number/BFYLXW5FOZPT4ZCOY2W7YCK7SP/graph.json","fetch_events":"https://pith.science/api/pith-number/BFYLXW5FOZPT4ZCOY2W7YCK7SP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFYLXW5FOZPT4ZCOY2W7YCK7SP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFYLXW5FOZPT4ZCOY2W7YCK7SP/action/storage_attestation","attest_author":"https://pith.science/pith/BFYLXW5FOZPT4ZCOY2W7YCK7SP/action/author_attestation","sign_citation":"https://pith.science/pith/BFYLXW5FOZPT4ZCOY2W7YCK7SP/action/citation_signature","submit_replication":"https://pith.science/pith/BFYLXW5FOZPT4ZCOY2W7YCK7SP/action/replication_record"}},"created_at":"2026-05-18T00:22:44.446999+00:00","updated_at":"2026-05-18T00:22:44.446999+00:00"}