{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CWGKW7P5HGW5NIYU5QDPDB7OJO","short_pith_number":"pith:CWGKW7P5","schema_version":"1.0","canonical_sha256":"158cab7dfd39add6a314ec06f187ee4b9120f8c7abf2fcca4515c43f63c83e27","source":{"kind":"arxiv","id":"1910.10479","version":1},"attestation_state":"computed","paper":{"title":"XL-Editor: Post-editing Sentences with XLNet","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Wei-Cheng Chang, Yiming Yang, Yong-Siang Shih","submitted_at":"2019-10-19T21:39:03Z","abstract_excerpt":"While neural sequence generation models achieve initial success for many NLP applications, the canonical decoding procedure with left-to-right generation order (i.e., autoregressive) in one-pass can not reflect the true nature of human revising a sentence to obtain a refined result. In this work, we propose XL-Editor, a novel training framework that enables state-of-the-art generalized autoregressive pretraining methods, XLNet specifically, to revise a given sentence by the variable-length insertion probability. Concretely, XL-Editor can (1) estimate the probability of inserting a variable-len"},"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":"1910.10479","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-19T21:39:03Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"87f338a3fba10b3d25adee5e4bdf65ca33ddf4501660a889524cd4a3ad0efb86","abstract_canon_sha256":"5f24e1db6cc53c82c81dc944d7bfffa8cf3fee2ce4cb4fe80fe63f85982cbf89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:14:25.325344Z","signature_b64":"LR4yNtM59LwNjL3X+PtBe+7oSLNLXjiXONyYtsGMgUTNhaM9QYnW9KGSVX506ZchfzipdWvxU6G3zDVKbOZNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"158cab7dfd39add6a314ec06f187ee4b9120f8c7abf2fcca4515c43f63c83e27","last_reissued_at":"2026-07-05T00:14:25.324833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:14:25.324833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XL-Editor: Post-editing Sentences with XLNet","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Wei-Cheng Chang, Yiming Yang, Yong-Siang Shih","submitted_at":"2019-10-19T21:39:03Z","abstract_excerpt":"While neural sequence generation models achieve initial success for many NLP applications, the canonical decoding procedure with left-to-right generation order (i.e., autoregressive) in one-pass can not reflect the true nature of human revising a sentence to obtain a refined result. In this work, we propose XL-Editor, a novel training framework that enables state-of-the-art generalized autoregressive pretraining methods, XLNet specifically, to revise a given sentence by the variable-length insertion probability. Concretely, XL-Editor can (1) estimate the probability of inserting a variable-len"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.10479","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/1910.10479/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":"1910.10479","created_at":"2026-07-05T00:14:25.324895+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.10479v1","created_at":"2026-07-05T00:14:25.324895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.10479","created_at":"2026-07-05T00:14:25.324895+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWGKW7P5HGW5","created_at":"2026-07-05T00:14:25.324895+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWGKW7P5HGW5NIYU","created_at":"2026-07-05T00:14:25.324895+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWGKW7P5","created_at":"2026-07-05T00:14:25.324895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2204.05999","citing_title":"InCoder: A Generative Model for Code Infilling and Synthesis","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWGKW7P5HGW5NIYU5QDPDB7OJO","json":"https://pith.science/pith/CWGKW7P5HGW5NIYU5QDPDB7OJO.json","graph_json":"https://pith.science/api/pith-number/CWGKW7P5HGW5NIYU5QDPDB7OJO/graph.json","events_json":"https://pith.science/api/pith-number/CWGKW7P5HGW5NIYU5QDPDB7OJO/events.json","paper":"https://pith.science/paper/CWGKW7P5"},"agent_actions":{"view_html":"https://pith.science/pith/CWGKW7P5HGW5NIYU5QDPDB7OJO","download_json":"https://pith.science/pith/CWGKW7P5HGW5NIYU5QDPDB7OJO.json","view_paper":"https://pith.science/paper/CWGKW7P5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.10479&json=true","fetch_graph":"https://pith.science/api/pith-number/CWGKW7P5HGW5NIYU5QDPDB7OJO/graph.json","fetch_events":"https://pith.science/api/pith-number/CWGKW7P5HGW5NIYU5QDPDB7OJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWGKW7P5HGW5NIYU5QDPDB7OJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWGKW7P5HGW5NIYU5QDPDB7OJO/action/storage_attestation","attest_author":"https://pith.science/pith/CWGKW7P5HGW5NIYU5QDPDB7OJO/action/author_attestation","sign_citation":"https://pith.science/pith/CWGKW7P5HGW5NIYU5QDPDB7OJO/action/citation_signature","submit_replication":"https://pith.science/pith/CWGKW7P5HGW5NIYU5QDPDB7OJO/action/replication_record"}},"created_at":"2026-07-05T00:14:25.324895+00:00","updated_at":"2026-07-05T00:14:25.324895+00:00"}