{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EYNHOD27SOCK4JMYSD63SOKRCT","short_pith_number":"pith:EYNHOD27","schema_version":"1.0","canonical_sha256":"261a770f5f9384ae259890fdb9395114f8df93f162b2f64073bf6cca771aeedf","source":{"kind":"arxiv","id":"2304.03145","version":2},"attestation_state":"computed","paper":{"title":"Evaluating the Robustness of Machine Reading Comprehension Models to Low Resource Entity Renaming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Clemencia Siro, Tunde Oluwaseyi Ajayi","submitted_at":"2023-04-06T15:29:57Z","abstract_excerpt":"Question answering (QA) models have shown compelling results in the task of Machine Reading Comprehension (MRC). Recently these systems have proved to perform better than humans on held-out test sets of datasets e.g. SQuAD, but their robustness is not guaranteed. The QA model's brittleness is exposed when evaluated on adversarial generated examples by a performance drop. In this study, we explore the robustness of MRC models to entity renaming, with entities from low-resource regions such as Africa. We propose EntSwap, a method for test-time perturbations, to create a test set whose entities h"},"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":"2304.03145","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-06T15:29:57Z","cross_cats_sorted":[],"title_canon_sha256":"de91f2a0f96d72b0b102389ce017ec3a9a4209c64c671fbe8e0d46ee3338c7b4","abstract_canon_sha256":"737d8d9816e82c890db6eb32432ab8b77a6772849ed63134c18a6ae40a9ae8a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:48.206848Z","signature_b64":"iVNAF30/bD1h+2ly1sG/dr1VtjkH8pPvjXPPlLxQMpcNpwUNwTLEvZdFAuZOJjrcdVukrut9G63JZUGozJogCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"261a770f5f9384ae259890fdb9395114f8df93f162b2f64073bf6cca771aeedf","last_reissued_at":"2026-07-05T08:08:48.206399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:48.206399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Robustness of Machine Reading Comprehension Models to Low Resource Entity Renaming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Clemencia Siro, Tunde Oluwaseyi Ajayi","submitted_at":"2023-04-06T15:29:57Z","abstract_excerpt":"Question answering (QA) models have shown compelling results in the task of Machine Reading Comprehension (MRC). Recently these systems have proved to perform better than humans on held-out test sets of datasets e.g. SQuAD, but their robustness is not guaranteed. The QA model's brittleness is exposed when evaluated on adversarial generated examples by a performance drop. In this study, we explore the robustness of MRC models to entity renaming, with entities from low-resource regions such as Africa. We propose EntSwap, a method for test-time perturbations, to create a test set whose entities h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03145","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.03145/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2304.03145","created_at":"2026-07-05T08:08:48.206455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03145v2","created_at":"2026-07-05T08:08:48.206455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03145","created_at":"2026-07-05T08:08:48.206455+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYNHOD27SOCK","created_at":"2026-07-05T08:08:48.206455+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYNHOD27SOCK4JMY","created_at":"2026-07-05T08:08:48.206455+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYNHOD27","created_at":"2026-07-05T08:08:48.206455+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/EYNHOD27SOCK4JMYSD63SOKRCT","json":"https://pith.science/pith/EYNHOD27SOCK4JMYSD63SOKRCT.json","graph_json":"https://pith.science/api/pith-number/EYNHOD27SOCK4JMYSD63SOKRCT/graph.json","events_json":"https://pith.science/api/pith-number/EYNHOD27SOCK4JMYSD63SOKRCT/events.json","paper":"https://pith.science/paper/EYNHOD27"},"agent_actions":{"view_html":"https://pith.science/pith/EYNHOD27SOCK4JMYSD63SOKRCT","download_json":"https://pith.science/pith/EYNHOD27SOCK4JMYSD63SOKRCT.json","view_paper":"https://pith.science/paper/EYNHOD27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03145&json=true","fetch_graph":"https://pith.science/api/pith-number/EYNHOD27SOCK4JMYSD63SOKRCT/graph.json","fetch_events":"https://pith.science/api/pith-number/EYNHOD27SOCK4JMYSD63SOKRCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYNHOD27SOCK4JMYSD63SOKRCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYNHOD27SOCK4JMYSD63SOKRCT/action/storage_attestation","attest_author":"https://pith.science/pith/EYNHOD27SOCK4JMYSD63SOKRCT/action/author_attestation","sign_citation":"https://pith.science/pith/EYNHOD27SOCK4JMYSD63SOKRCT/action/citation_signature","submit_replication":"https://pith.science/pith/EYNHOD27SOCK4JMYSD63SOKRCT/action/replication_record"}},"created_at":"2026-07-05T08:08:48.206455+00:00","updated_at":"2026-07-05T08:08:48.206455+00:00"}