{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:EU54JLRJZ6XFMJLCP5PAGZW2CF","short_pith_number":"pith:EU54JLRJ","schema_version":"1.0","canonical_sha256":"253bc4ae29cfae5625627f5e0366da117957fab7a276877eb8ca4641dc187c63","source":{"kind":"arxiv","id":"1608.08716","version":1},"attestation_state":"computed","paper":{"title":"Measuring Machine Intelligence Through Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Aishwarya Agrawal, C. Lawrence Zitnick, Devi Parikh, Dhruv Batra, Margaret Mitchell, Stanislaw Antol","submitted_at":"2016-08-31T02:56:00Z","abstract_excerpt":"As machines have become more intelligent, there has been a renewed interest in methods for measuring their intelligence. A common approach is to propose tasks for which a human excels, but one which machines find difficult. However, an ideal task should also be easy to evaluate and not be easily gameable. We begin with a case study exploring the recently popular task of image captioning and its limitations as a task for measuring machine intelligence. An alternative and more promising task is Visual Question Answering that tests a machine's ability to reason about language and vision. We descr"},"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":"1608.08716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-08-31T02:56:00Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"9e41f53a33972da5eef6847de3bfa0b6eed154c489db67da7efb7a298af187ad","abstract_canon_sha256":"f4a6d519ecc211ccb02b0cac0506596495f1ed9cc1f63924a6b8b4de3f39b93e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:06:40.126032Z","signature_b64":"0OX6kz8Gc8ZlNW3Fg46XmDtex2QYdV3ViTes+NWfwrlCa2aPfdHYdNyhyacJ7KWPLD1yWXLNfO3x97CezWGeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"253bc4ae29cfae5625627f5e0366da117957fab7a276877eb8ca4641dc187c63","last_reissued_at":"2026-05-18T01:06:40.125515Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:06:40.125515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring Machine Intelligence Through Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Aishwarya Agrawal, C. Lawrence Zitnick, Devi Parikh, Dhruv Batra, Margaret Mitchell, Stanislaw Antol","submitted_at":"2016-08-31T02:56:00Z","abstract_excerpt":"As machines have become more intelligent, there has been a renewed interest in methods for measuring their intelligence. A common approach is to propose tasks for which a human excels, but one which machines find difficult. However, an ideal task should also be easy to evaluate and not be easily gameable. We begin with a case study exploring the recently popular task of image captioning and its limitations as a task for measuring machine intelligence. An alternative and more promising task is Visual Question Answering that tests a machine's ability to reason about language and vision. We descr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.08716","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":"1608.08716","created_at":"2026-05-18T01:06:40.125605+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.08716v1","created_at":"2026-05-18T01:06:40.125605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.08716","created_at":"2026-05-18T01:06:40.125605+00:00"},{"alias_kind":"pith_short_12","alias_value":"EU54JLRJZ6XF","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"EU54JLRJZ6XFMJLC","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"EU54JLRJ","created_at":"2026-05-18T12:30:15.759754+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/EU54JLRJZ6XFMJLCP5PAGZW2CF","json":"https://pith.science/pith/EU54JLRJZ6XFMJLCP5PAGZW2CF.json","graph_json":"https://pith.science/api/pith-number/EU54JLRJZ6XFMJLCP5PAGZW2CF/graph.json","events_json":"https://pith.science/api/pith-number/EU54JLRJZ6XFMJLCP5PAGZW2CF/events.json","paper":"https://pith.science/paper/EU54JLRJ"},"agent_actions":{"view_html":"https://pith.science/pith/EU54JLRJZ6XFMJLCP5PAGZW2CF","download_json":"https://pith.science/pith/EU54JLRJZ6XFMJLCP5PAGZW2CF.json","view_paper":"https://pith.science/paper/EU54JLRJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.08716&json=true","fetch_graph":"https://pith.science/api/pith-number/EU54JLRJZ6XFMJLCP5PAGZW2CF/graph.json","fetch_events":"https://pith.science/api/pith-number/EU54JLRJZ6XFMJLCP5PAGZW2CF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EU54JLRJZ6XFMJLCP5PAGZW2CF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EU54JLRJZ6XFMJLCP5PAGZW2CF/action/storage_attestation","attest_author":"https://pith.science/pith/EU54JLRJZ6XFMJLCP5PAGZW2CF/action/author_attestation","sign_citation":"https://pith.science/pith/EU54JLRJZ6XFMJLCP5PAGZW2CF/action/citation_signature","submit_replication":"https://pith.science/pith/EU54JLRJZ6XFMJLCP5PAGZW2CF/action/replication_record"}},"created_at":"2026-05-18T01:06:40.125605+00:00","updated_at":"2026-05-18T01:06:40.125605+00:00"}