{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BQONWY7EFXWQSMT4UDINA7YKS7","short_pith_number":"pith:BQONWY7E","schema_version":"1.0","canonical_sha256":"0c1cdb63e42ded09327ca0d0d07f0a97fd8be672a7e7d2f43f4c26b4c501a874","source":{"kind":"arxiv","id":"1904.02665","version":1},"attestation_state":"computed","paper":{"title":"Frustratingly Poor Performance of Reading Comprehension Models on Non-adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ananya B. Sai, Mitesh M. Khapra, Preksha Nema, Soham Parikh","submitted_at":"2019-04-04T17:00:48Z","abstract_excerpt":"When humans learn to perform a difficult task (say, reading comprehension (RC) over longer passages), it is typically the case that their performance improves significantly on an easier version of this task (say, RC over shorter passages). Ideally, we would want an intelligent agent to also exhibit such a behavior. However, on experimenting with state of the art RC models using the standard RACE dataset, we observe that this is not true. Specifically, we see counter-intuitive results wherein even when we show frustratingly easy examples to the model at test time, there is hardly any improvemen"},"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":"1904.02665","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-04T17:00:48Z","cross_cats_sorted":[],"title_canon_sha256":"88ee343c32067b934a6ad252bccf3b05725e5d03a594c185f4957e0cec8380b3","abstract_canon_sha256":"22a6edcf21aeefcffd81a4521f0b676bd5d1c87f45c9f20d85c81f528e7bf2b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:23.078273Z","signature_b64":"utPXkuZi8QScMfuse54ThUd/OtCOi1xCfDvhvKoA2hIP+r85EeveWSGqMpnrVxqy4tBBuEiHQAPGPcK+bCj4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c1cdb63e42ded09327ca0d0d07f0a97fd8be672a7e7d2f43f4c26b4c501a874","last_reissued_at":"2026-05-17T23:49:23.077732Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:23.077732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frustratingly Poor Performance of Reading Comprehension Models on Non-adversarial Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ananya B. Sai, Mitesh M. Khapra, Preksha Nema, Soham Parikh","submitted_at":"2019-04-04T17:00:48Z","abstract_excerpt":"When humans learn to perform a difficult task (say, reading comprehension (RC) over longer passages), it is typically the case that their performance improves significantly on an easier version of this task (say, RC over shorter passages). Ideally, we would want an intelligent agent to also exhibit such a behavior. However, on experimenting with state of the art RC models using the standard RACE dataset, we observe that this is not true. Specifically, we see counter-intuitive results wherein even when we show frustratingly easy examples to the model at test time, there is hardly any improvemen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02665","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":"1904.02665","created_at":"2026-05-17T23:49:23.077803+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02665v1","created_at":"2026-05-17T23:49:23.077803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02665","created_at":"2026-05-17T23:49:23.077803+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQONWY7EFXWQ","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQONWY7EFXWQSMT4","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQONWY7E","created_at":"2026-05-18T12:33:12.712433+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/BQONWY7EFXWQSMT4UDINA7YKS7","json":"https://pith.science/pith/BQONWY7EFXWQSMT4UDINA7YKS7.json","graph_json":"https://pith.science/api/pith-number/BQONWY7EFXWQSMT4UDINA7YKS7/graph.json","events_json":"https://pith.science/api/pith-number/BQONWY7EFXWQSMT4UDINA7YKS7/events.json","paper":"https://pith.science/paper/BQONWY7E"},"agent_actions":{"view_html":"https://pith.science/pith/BQONWY7EFXWQSMT4UDINA7YKS7","download_json":"https://pith.science/pith/BQONWY7EFXWQSMT4UDINA7YKS7.json","view_paper":"https://pith.science/paper/BQONWY7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02665&json=true","fetch_graph":"https://pith.science/api/pith-number/BQONWY7EFXWQSMT4UDINA7YKS7/graph.json","fetch_events":"https://pith.science/api/pith-number/BQONWY7EFXWQSMT4UDINA7YKS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQONWY7EFXWQSMT4UDINA7YKS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQONWY7EFXWQSMT4UDINA7YKS7/action/storage_attestation","attest_author":"https://pith.science/pith/BQONWY7EFXWQSMT4UDINA7YKS7/action/author_attestation","sign_citation":"https://pith.science/pith/BQONWY7EFXWQSMT4UDINA7YKS7/action/citation_signature","submit_replication":"https://pith.science/pith/BQONWY7EFXWQSMT4UDINA7YKS7/action/replication_record"}},"created_at":"2026-05-17T23:49:23.077803+00:00","updated_at":"2026-05-17T23:49:23.077803+00:00"}