{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:APAIUZGPOPWG47FYMI3DBHHY2Q","short_pith_number":"pith:APAIUZGP","schema_version":"1.0","canonical_sha256":"03c08a64cf73ec6e7cb86236309cf8d4037e2528edacc7b0e60792e6ee3df61f","source":{"kind":"arxiv","id":"2010.01475","version":1},"attestation_state":"computed","paper":{"title":"Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dayiheng Liu, Jiancheng Lv, Jie Fu, Jiusheng Chen, Ming Zhou, Nan Duan, Yeyun Gong, Yu Yan","submitted_at":"2020-10-04T03:13:46Z","abstract_excerpt":"In this paper, we propose a novel data augmentation method, referred to as Controllable Rewriting based Question Data Augmentation (CRQDA), for machine reading comprehension (MRC), question generation, and question-answering natural language inference tasks. We treat the question data augmentation task as a constrained question rewriting problem to generate context-relevant, high-quality, and diverse question data samples. CRQDA utilizes a Transformer autoencoder to map the original discrete question into a continuous embedding space. It then uses a pre-trained MRC model to revise the question"},"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":"2010.01475","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-04T03:13:46Z","cross_cats_sorted":[],"title_canon_sha256":"721ffc4e68abb052bf01525db7eb320a08c586ea9b769aebc4476b20c0852a28","abstract_canon_sha256":"fcc5767345f656bd70383af8ae48bc37341403825e5d9260f7e9d116988f9103"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:05.851825Z","signature_b64":"v/73Jm3mxwn6mejao1Hki6MMBR4Qw8vuSosTvGPSu5qGU3GTHugH81pzWu4YKTtmPyJu/DDt1tU8TiHmqZjvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03c08a64cf73ec6e7cb86236309cf8d4037e2528edacc7b0e60792e6ee3df61f","last_reissued_at":"2026-07-05T01:40:05.851359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:05.851359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dayiheng Liu, Jiancheng Lv, Jie Fu, Jiusheng Chen, Ming Zhou, Nan Duan, Yeyun Gong, Yu Yan","submitted_at":"2020-10-04T03:13:46Z","abstract_excerpt":"In this paper, we propose a novel data augmentation method, referred to as Controllable Rewriting based Question Data Augmentation (CRQDA), for machine reading comprehension (MRC), question generation, and question-answering natural language inference tasks. We treat the question data augmentation task as a constrained question rewriting problem to generate context-relevant, high-quality, and diverse question data samples. CRQDA utilizes a Transformer autoencoder to map the original discrete question into a continuous embedding space. It then uses a pre-trained MRC model to revise the question"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01475","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.01475/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":"2010.01475","created_at":"2026-07-05T01:40:05.851419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01475v1","created_at":"2026-07-05T01:40:05.851419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01475","created_at":"2026-07-05T01:40:05.851419+00:00"},{"alias_kind":"pith_short_12","alias_value":"APAIUZGPOPWG","created_at":"2026-07-05T01:40:05.851419+00:00"},{"alias_kind":"pith_short_16","alias_value":"APAIUZGPOPWG47FY","created_at":"2026-07-05T01:40:05.851419+00:00"},{"alias_kind":"pith_short_8","alias_value":"APAIUZGP","created_at":"2026-07-05T01:40:05.851419+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/APAIUZGPOPWG47FYMI3DBHHY2Q","json":"https://pith.science/pith/APAIUZGPOPWG47FYMI3DBHHY2Q.json","graph_json":"https://pith.science/api/pith-number/APAIUZGPOPWG47FYMI3DBHHY2Q/graph.json","events_json":"https://pith.science/api/pith-number/APAIUZGPOPWG47FYMI3DBHHY2Q/events.json","paper":"https://pith.science/paper/APAIUZGP"},"agent_actions":{"view_html":"https://pith.science/pith/APAIUZGPOPWG47FYMI3DBHHY2Q","download_json":"https://pith.science/pith/APAIUZGPOPWG47FYMI3DBHHY2Q.json","view_paper":"https://pith.science/paper/APAIUZGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01475&json=true","fetch_graph":"https://pith.science/api/pith-number/APAIUZGPOPWG47FYMI3DBHHY2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/APAIUZGPOPWG47FYMI3DBHHY2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APAIUZGPOPWG47FYMI3DBHHY2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APAIUZGPOPWG47FYMI3DBHHY2Q/action/storage_attestation","attest_author":"https://pith.science/pith/APAIUZGPOPWG47FYMI3DBHHY2Q/action/author_attestation","sign_citation":"https://pith.science/pith/APAIUZGPOPWG47FYMI3DBHHY2Q/action/citation_signature","submit_replication":"https://pith.science/pith/APAIUZGPOPWG47FYMI3DBHHY2Q/action/replication_record"}},"created_at":"2026-07-05T01:40:05.851419+00:00","updated_at":"2026-07-05T01:40:05.851419+00:00"}