{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:DIE44MVXJD23LMGDXSXH4PYIF6","short_pith_number":"pith:DIE44MVX","schema_version":"1.0","canonical_sha256":"1a09ce32b748f5b5b0c3bcae7e3f082fafd90ebcbea12c0794cbfa973e62e4f3","source":{"kind":"arxiv","id":"1612.06890","version":1},"attestation_state":"computed","paper":{"title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, C. Lawrence Zitnick, Justin Johnson, Laurens van der Maaten, Li Fei-Fei, Ross Girshick","submitted_at":"2016-12-20T21:40:40Z","abstract_excerpt":"When building artificial intelligence systems that can reason and answer questions about visual data, we need diagnostic tests to analyze our progress and discover shortcomings. Existing benchmarks for visual question answering can help, but have strong biases that models can exploit to correctly answer questions without reasoning. They also conflate multiple sources of error, making it hard to pinpoint model weaknesses. We present a diagnostic dataset that tests a range of visual reasoning abilities. It contains minimal biases and has detailed annotations describing the kind of reasoning each"},"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":"1612.06890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-20T21:40:40Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"68ea754ad010f383b5c7f6726413f1b643ca7c0a2e537788eaee73ca9c7668f9","abstract_canon_sha256":"e519d897e7f007c025253c5a3f4dfdeecc70ae6ce3f5e86c7a10739589556166"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:54:15.114171Z","signature_b64":"PSniQUGoxNCxjUlT1mCq8f6hFMZ3wgdIoyvNaxTY+AE1A2T4oPBVrLhQgyfs1VnBZoMg3cGhhaqimFgOZzBCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a09ce32b748f5b5b0c3bcae7e3f082fafd90ebcbea12c0794cbfa973e62e4f3","last_reissued_at":"2026-05-18T00:54:15.113488Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:54:15.113488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, C. Lawrence Zitnick, Justin Johnson, Laurens van der Maaten, Li Fei-Fei, Ross Girshick","submitted_at":"2016-12-20T21:40:40Z","abstract_excerpt":"When building artificial intelligence systems that can reason and answer questions about visual data, we need diagnostic tests to analyze our progress and discover shortcomings. Existing benchmarks for visual question answering can help, but have strong biases that models can exploit to correctly answer questions without reasoning. They also conflate multiple sources of error, making it hard to pinpoint model weaknesses. We present a diagnostic dataset that tests a range of visual reasoning abilities. It contains minimal biases and has detailed annotations describing the kind of reasoning each"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.06890","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":""},"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":"1612.06890","created_at":"2026-05-18T00:54:15.113596+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.06890v1","created_at":"2026-05-18T00:54:15.113596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.06890","created_at":"2026-05-18T00:54:15.113596+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIE44MVXJD23","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIE44MVXJD23LMGD","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIE44MVX","created_at":"2026-05-18T12:30:12.583610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.01685","citing_title":"How Do Language Models Compose Functions?","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02881","citing_title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02881","citing_title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05226","citing_title":"RoboPlayground: Democratizing Robotic Evaluation through Structured Physical Domains","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18803","citing_title":"LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DIE44MVXJD23LMGDXSXH4PYIF6","json":"https://pith.science/pith/DIE44MVXJD23LMGDXSXH4PYIF6.json","graph_json":"https://pith.science/api/pith-number/DIE44MVXJD23LMGDXSXH4PYIF6/graph.json","events_json":"https://pith.science/api/pith-number/DIE44MVXJD23LMGDXSXH4PYIF6/events.json","paper":"https://pith.science/paper/DIE44MVX"},"agent_actions":{"view_html":"https://pith.science/pith/DIE44MVXJD23LMGDXSXH4PYIF6","download_json":"https://pith.science/pith/DIE44MVXJD23LMGDXSXH4PYIF6.json","view_paper":"https://pith.science/paper/DIE44MVX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.06890&json=true","fetch_graph":"https://pith.science/api/pith-number/DIE44MVXJD23LMGDXSXH4PYIF6/graph.json","fetch_events":"https://pith.science/api/pith-number/DIE44MVXJD23LMGDXSXH4PYIF6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIE44MVXJD23LMGDXSXH4PYIF6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIE44MVXJD23LMGDXSXH4PYIF6/action/storage_attestation","attest_author":"https://pith.science/pith/DIE44MVXJD23LMGDXSXH4PYIF6/action/author_attestation","sign_citation":"https://pith.science/pith/DIE44MVXJD23LMGDXSXH4PYIF6/action/citation_signature","submit_replication":"https://pith.science/pith/DIE44MVXJD23LMGDXSXH4PYIF6/action/replication_record"}},"created_at":"2026-05-18T00:54:15.113596+00:00","updated_at":"2026-05-18T00:54:15.113596+00:00"}