{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LC2ILO2IS2HQPZ2BINBRYJZKIK","short_pith_number":"pith:LC2ILO2I","schema_version":"1.0","canonical_sha256":"58b485bb48968f07e74143431c272a42acf72af48e24e3c9c4807f9c5cedeed1","source":{"kind":"arxiv","id":"1806.00857","version":3},"attestation_state":"computed","paper":{"title":"On the Flip Side: Identifying Counterexamples in Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Rush, Aron Szanto, Gabriel Grand, Yoon Kim","submitted_at":"2018-06-03T19:31:47Z","abstract_excerpt":"Visual question answering (VQA) models respond to open-ended natural language questions about images. While VQA is an increasingly popular area of research, it is unclear to what extent current VQA architectures learn key semantic distinctions between visually-similar images. To investigate this question, we explore a reformulation of the VQA task that challenges models to identify counterexamples: images that result in a different answer to the original question. We introduce two methods for evaluating existing VQA models against a supervised counterexample prediction task, VQA-CX. While our "},"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":"1806.00857","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-03T19:31:47Z","cross_cats_sorted":[],"title_canon_sha256":"d4ac6b1ca55f8d494691d8323dd3810d914cd3d7ab87d420d0a209ebcf91ea8a","abstract_canon_sha256":"4ee4e3b8c05ef045028df03acc64c23e333cca24181d10ff9af64a7a8f2265be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:58.820669Z","signature_b64":"iolWX4dU6mYy4e/wm2hlk3UlDQQYwlCul4GGsBuI12EfykQyuW0WvQkgtMIashMG2Jr5TpEkjSnsag5NIm9uCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58b485bb48968f07e74143431c272a42acf72af48e24e3c9c4807f9c5cedeed1","last_reissued_at":"2026-05-18T00:09:58.819967Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:58.819967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Flip Side: Identifying Counterexamples in Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Rush, Aron Szanto, Gabriel Grand, Yoon Kim","submitted_at":"2018-06-03T19:31:47Z","abstract_excerpt":"Visual question answering (VQA) models respond to open-ended natural language questions about images. While VQA is an increasingly popular area of research, it is unclear to what extent current VQA architectures learn key semantic distinctions between visually-similar images. To investigate this question, we explore a reformulation of the VQA task that challenges models to identify counterexamples: images that result in a different answer to the original question. We introduce two methods for evaluating existing VQA models against a supervised counterexample prediction task, VQA-CX. While our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00857","kind":"arxiv","version":3},"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":"1806.00857","created_at":"2026-05-18T00:09:58.820085+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.00857v3","created_at":"2026-05-18T00:09:58.820085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00857","created_at":"2026-05-18T00:09:58.820085+00:00"},{"alias_kind":"pith_short_12","alias_value":"LC2ILO2IS2HQ","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"LC2ILO2IS2HQPZ2B","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"LC2ILO2I","created_at":"2026-05-18T12:32:33.847187+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/LC2ILO2IS2HQPZ2BINBRYJZKIK","json":"https://pith.science/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK.json","graph_json":"https://pith.science/api/pith-number/LC2ILO2IS2HQPZ2BINBRYJZKIK/graph.json","events_json":"https://pith.science/api/pith-number/LC2ILO2IS2HQPZ2BINBRYJZKIK/events.json","paper":"https://pith.science/paper/LC2ILO2I"},"agent_actions":{"view_html":"https://pith.science/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK","download_json":"https://pith.science/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK.json","view_paper":"https://pith.science/paper/LC2ILO2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.00857&json=true","fetch_graph":"https://pith.science/api/pith-number/LC2ILO2IS2HQPZ2BINBRYJZKIK/graph.json","fetch_events":"https://pith.science/api/pith-number/LC2ILO2IS2HQPZ2BINBRYJZKIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK/action/storage_attestation","attest_author":"https://pith.science/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK/action/author_attestation","sign_citation":"https://pith.science/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK/action/citation_signature","submit_replication":"https://pith.science/pith/LC2ILO2IS2HQPZ2BINBRYJZKIK/action/replication_record"}},"created_at":"2026-05-18T00:09:58.820085+00:00","updated_at":"2026-05-18T00:09:58.820085+00:00"}