{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:67PFI5BKEOPMTUPREYVBVN66RE","short_pith_number":"pith:67PFI5BK","schema_version":"1.0","canonical_sha256":"f7de54742a239ec9d1f1262a1ab7de8931c13718f6a4104c599f466e9c8c90d3","source":{"kind":"arxiv","id":"1904.09317","version":2},"attestation_state":"computed","paper":{"title":"Challenges and Prospects in Vision and Language Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Kanan, Kushal Kafle, Robik Shrestha","submitted_at":"2019-04-19T19:04:12Z","abstract_excerpt":"Language grounded image understanding tasks have often been proposed as a method for evaluating progress in artificial intelligence. Ideally, these tasks should test a plethora of capabilities that integrate computer vision, reasoning, and natural language understanding. However, rather than behaving as visual Turing tests, recent studies have demonstrated state-of-the-art systems are achieving good performance through flaws in datasets and evaluation procedures. We review the current state of affairs and outline a path forward."},"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":"1904.09317","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-19T19:04:12Z","cross_cats_sorted":["cs.CL","cs.CV","cs.NE","stat.ML"],"title_canon_sha256":"97268ffb93c640e7ee83cd5ebe4d33c4a05baab5e3ef1f9b1846c5ba5a9a2863","abstract_canon_sha256":"5e124a51d84d9aa6d6966bdbfbd2b50fba80f4407d513899c806dff580904d6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:08.960200Z","signature_b64":"L/nPOV4ApklF/jQrYSXK4MJdPogDwGhC4jXnrwFHtYhP7bZvsAahZRa/WEDl/ERllgoLaaM/S1VksGHyHTctBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7de54742a239ec9d1f1262a1ab7de8931c13718f6a4104c599f466e9c8c90d3","last_reissued_at":"2026-05-17T23:45:08.959647Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:08.959647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Challenges and Prospects in Vision and Language Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Kanan, Kushal Kafle, Robik Shrestha","submitted_at":"2019-04-19T19:04:12Z","abstract_excerpt":"Language grounded image understanding tasks have often been proposed as a method for evaluating progress in artificial intelligence. Ideally, these tasks should test a plethora of capabilities that integrate computer vision, reasoning, and natural language understanding. However, rather than behaving as visual Turing tests, recent studies have demonstrated state-of-the-art systems are achieving good performance through flaws in datasets and evaluation procedures. We review the current state of affairs and outline a path forward."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09317","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":"1904.09317","created_at":"2026-05-17T23:45:08.959738+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.09317v2","created_at":"2026-05-17T23:45:08.959738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09317","created_at":"2026-05-17T23:45:08.959738+00:00"},{"alias_kind":"pith_short_12","alias_value":"67PFI5BKEOPM","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"67PFI5BKEOPMTUPR","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"67PFI5BK","created_at":"2026-05-18T12:33:10.108867+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/67PFI5BKEOPMTUPREYVBVN66RE","json":"https://pith.science/pith/67PFI5BKEOPMTUPREYVBVN66RE.json","graph_json":"https://pith.science/api/pith-number/67PFI5BKEOPMTUPREYVBVN66RE/graph.json","events_json":"https://pith.science/api/pith-number/67PFI5BKEOPMTUPREYVBVN66RE/events.json","paper":"https://pith.science/paper/67PFI5BK"},"agent_actions":{"view_html":"https://pith.science/pith/67PFI5BKEOPMTUPREYVBVN66RE","download_json":"https://pith.science/pith/67PFI5BKEOPMTUPREYVBVN66RE.json","view_paper":"https://pith.science/paper/67PFI5BK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.09317&json=true","fetch_graph":"https://pith.science/api/pith-number/67PFI5BKEOPMTUPREYVBVN66RE/graph.json","fetch_events":"https://pith.science/api/pith-number/67PFI5BKEOPMTUPREYVBVN66RE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67PFI5BKEOPMTUPREYVBVN66RE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67PFI5BKEOPMTUPREYVBVN66RE/action/storage_attestation","attest_author":"https://pith.science/pith/67PFI5BKEOPMTUPREYVBVN66RE/action/author_attestation","sign_citation":"https://pith.science/pith/67PFI5BKEOPMTUPREYVBVN66RE/action/citation_signature","submit_replication":"https://pith.science/pith/67PFI5BKEOPMTUPREYVBVN66RE/action/replication_record"}},"created_at":"2026-05-17T23:45:08.959738+00:00","updated_at":"2026-05-17T23:45:08.959738+00:00"}