{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:44QSEPZZAEAT4FMKFCYCEV32KT","short_pith_number":"pith:44QSEPZZ","schema_version":"1.0","canonical_sha256":"e721223f3901013e158a28b022577a54d2498fb318077da5d7eecdd18cd62dbe","source":{"kind":"arxiv","id":"2212.04755","version":3},"attestation_state":"computed","paper":{"title":"From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lidong Bing, Luo Si, Meng Zhou, Wai Lam, Weiwen Xu, Wenxuan Zhang, Xin Li","submitted_at":"2022-12-09T10:21:56Z","abstract_excerpt":"We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data. PMR can resolve the discrepancy between model pre-training and downstream fine-tuning of existing MLMs. To build the proposed PMR, we constructed a large volume of general-purpose and high-quality MRC-style training data by using Wikipedia hyperlinks and designed a Wiki Anchor Extraction task to guide the MRC-style pre-training. Apart from its simplicity, PMR effectively solves extraction"},"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":"2212.04755","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-09T10:21:56Z","cross_cats_sorted":[],"title_canon_sha256":"05c5732d1bbb87227631091dd544f7e92eca0afb358adda610b2197042c9428e","abstract_canon_sha256":"b0668fba8849e8fb49f3f9e8c350344be11f5bb567d962cfac1564e79cc159f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:57.980796Z","signature_b64":"SFfX6jnl1rBH6k4ZvKGpRwCfmDTTdMp5ugdMrL/2JALSdEj8f3g6QKYWssOG56eNOYqK7ScHZZe420llpODKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e721223f3901013e158a28b022577a54d2498fb318077da5d7eecdd18cd62dbe","last_reissued_at":"2026-07-05T07:00:57.980290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:57.980290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lidong Bing, Luo Si, Meng Zhou, Wai Lam, Weiwen Xu, Wenxuan Zhang, Xin Li","submitted_at":"2022-12-09T10:21:56Z","abstract_excerpt":"We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models without acquiring labeled data. PMR can resolve the discrepancy between model pre-training and downstream fine-tuning of existing MLMs. To build the proposed PMR, we constructed a large volume of general-purpose and high-quality MRC-style training data by using Wikipedia hyperlinks and designed a Wiki Anchor Extraction task to guide the MRC-style pre-training. Apart from its simplicity, PMR effectively solves extraction"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04755","kind":"arxiv","version":3},"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/2212.04755/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":"2212.04755","created_at":"2026-07-05T07:00:57.980356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.04755v3","created_at":"2026-07-05T07:00:57.980356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04755","created_at":"2026-07-05T07:00:57.980356+00:00"},{"alias_kind":"pith_short_12","alias_value":"44QSEPZZAEAT","created_at":"2026-07-05T07:00:57.980356+00:00"},{"alias_kind":"pith_short_16","alias_value":"44QSEPZZAEAT4FMK","created_at":"2026-07-05T07:00:57.980356+00:00"},{"alias_kind":"pith_short_8","alias_value":"44QSEPZZ","created_at":"2026-07-05T07:00:57.980356+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/44QSEPZZAEAT4FMKFCYCEV32KT","json":"https://pith.science/pith/44QSEPZZAEAT4FMKFCYCEV32KT.json","graph_json":"https://pith.science/api/pith-number/44QSEPZZAEAT4FMKFCYCEV32KT/graph.json","events_json":"https://pith.science/api/pith-number/44QSEPZZAEAT4FMKFCYCEV32KT/events.json","paper":"https://pith.science/paper/44QSEPZZ"},"agent_actions":{"view_html":"https://pith.science/pith/44QSEPZZAEAT4FMKFCYCEV32KT","download_json":"https://pith.science/pith/44QSEPZZAEAT4FMKFCYCEV32KT.json","view_paper":"https://pith.science/paper/44QSEPZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.04755&json=true","fetch_graph":"https://pith.science/api/pith-number/44QSEPZZAEAT4FMKFCYCEV32KT/graph.json","fetch_events":"https://pith.science/api/pith-number/44QSEPZZAEAT4FMKFCYCEV32KT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44QSEPZZAEAT4FMKFCYCEV32KT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44QSEPZZAEAT4FMKFCYCEV32KT/action/storage_attestation","attest_author":"https://pith.science/pith/44QSEPZZAEAT4FMKFCYCEV32KT/action/author_attestation","sign_citation":"https://pith.science/pith/44QSEPZZAEAT4FMKFCYCEV32KT/action/citation_signature","submit_replication":"https://pith.science/pith/44QSEPZZAEAT4FMKFCYCEV32KT/action/replication_record"}},"created_at":"2026-07-05T07:00:57.980356+00:00","updated_at":"2026-07-05T07:00:57.980356+00:00"}