{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LPAES6UMO272SRFR27ON6RGZ5F","short_pith_number":"pith:LPAES6UM","schema_version":"1.0","canonical_sha256":"5bc0497a8c76bfa944b1d7dcdf44d9e9762a7004d4f3cb5cb492f1edfcd95041","source":{"kind":"arxiv","id":"2211.05344","version":1},"attestation_state":"computed","paper":{"title":"LERT: A Linguistically-motivated Pre-trained Language Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Shijin Wang, Ting Liu, Wanxiang Che, Yiming Cui","submitted_at":"2022-11-10T05:09:16Z","abstract_excerpt":"Pre-trained Language Model (PLM) has become a representative foundation model in the natural language processing field. Most PLMs are trained with linguistic-agnostic pre-training tasks on the surface form of the text, such as the masked language model (MLM). To further empower the PLMs with richer linguistic features, in this paper, we aim to propose a simple but effective way to learn linguistic features for pre-trained language models. We propose LERT, a pre-trained language model that is trained on three types of linguistic features along with the original MLM pre-training task, using a li"},"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":"2211.05344","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-10T05:09:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2d04f9119d118472fd70c47fbc7a89ff0807e2a386435e1b2615cc5f54b9e7f5","abstract_canon_sha256":"2f43b212b8281220667da1032723c0ea9bb38bee149e0564bd822f4f71440435"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:03.492856Z","signature_b64":"/yMbLnJyI/KXoSa2upBgl342BBMdeCFssgj84o8R4pXM7lz1zLtXbNApzPQyraas6ilaXrJ0bG1C2nVOLegdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bc0497a8c76bfa944b1d7dcdf44d9e9762a7004d4f3cb5cb492f1edfcd95041","last_reissued_at":"2026-07-05T05:15:03.492387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:03.492387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LERT: A Linguistically-motivated Pre-trained Language Model","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Shijin Wang, Ting Liu, Wanxiang Che, Yiming Cui","submitted_at":"2022-11-10T05:09:16Z","abstract_excerpt":"Pre-trained Language Model (PLM) has become a representative foundation model in the natural language processing field. Most PLMs are trained with linguistic-agnostic pre-training tasks on the surface form of the text, such as the masked language model (MLM). To further empower the PLMs with richer linguistic features, in this paper, we aim to propose a simple but effective way to learn linguistic features for pre-trained language models. We propose LERT, a pre-trained language model that is trained on three types of linguistic features along with the original MLM pre-training task, using a li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05344","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/2211.05344/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":"2211.05344","created_at":"2026-07-05T05:15:03.492444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.05344v1","created_at":"2026-07-05T05:15:03.492444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05344","created_at":"2026-07-05T05:15:03.492444+00:00"},{"alias_kind":"pith_short_12","alias_value":"LPAES6UMO272","created_at":"2026-07-05T05:15:03.492444+00:00"},{"alias_kind":"pith_short_16","alias_value":"LPAES6UMO272SRFR","created_at":"2026-07-05T05:15:03.492444+00:00"},{"alias_kind":"pith_short_8","alias_value":"LPAES6UM","created_at":"2026-07-05T05:15:03.492444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.17001","citing_title":"Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03448","citing_title":"Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LPAES6UMO272SRFR27ON6RGZ5F","json":"https://pith.science/pith/LPAES6UMO272SRFR27ON6RGZ5F.json","graph_json":"https://pith.science/api/pith-number/LPAES6UMO272SRFR27ON6RGZ5F/graph.json","events_json":"https://pith.science/api/pith-number/LPAES6UMO272SRFR27ON6RGZ5F/events.json","paper":"https://pith.science/paper/LPAES6UM"},"agent_actions":{"view_html":"https://pith.science/pith/LPAES6UMO272SRFR27ON6RGZ5F","download_json":"https://pith.science/pith/LPAES6UMO272SRFR27ON6RGZ5F.json","view_paper":"https://pith.science/paper/LPAES6UM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.05344&json=true","fetch_graph":"https://pith.science/api/pith-number/LPAES6UMO272SRFR27ON6RGZ5F/graph.json","fetch_events":"https://pith.science/api/pith-number/LPAES6UMO272SRFR27ON6RGZ5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LPAES6UMO272SRFR27ON6RGZ5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LPAES6UMO272SRFR27ON6RGZ5F/action/storage_attestation","attest_author":"https://pith.science/pith/LPAES6UMO272SRFR27ON6RGZ5F/action/author_attestation","sign_citation":"https://pith.science/pith/LPAES6UMO272SRFR27ON6RGZ5F/action/citation_signature","submit_replication":"https://pith.science/pith/LPAES6UMO272SRFR27ON6RGZ5F/action/replication_record"}},"created_at":"2026-07-05T05:15:03.492444+00:00","updated_at":"2026-07-05T05:15:03.492444+00:00"}