{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LNRQJKWOE77FKO643UZAJOXDG5","short_pith_number":"pith:LNRQJKWO","schema_version":"1.0","canonical_sha256":"5b6304aace27fe553bdcdd3204bae3377bba8cac0a4ac9059e13599c52375009","source":{"kind":"arxiv","id":"2111.01243","version":1},"attestation_state":"computed","paper":{"title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amir Pouran Ben Veyseh, Bonan Min, Dan Roth, Elior Sulem, Eneko Agirre, Hayley Ross, Ilana Heinz, Oscar Sainz, Thien Huu Nguyen","submitted_at":"2021-11-01T20:08:05Z","abstract_excerpt":"Large, pre-trained transformer-based language models such as BERT have drastically changed the Natural Language Processing (NLP) field. We present a survey of recent work that uses these large language models to solve NLP tasks via pre-training then fine-tuning, prompting, or text generation approaches. We also present approaches that use pre-trained language models to generate data for training augmentation or other purposes. We conclude with discussions on limitations and suggested directions for future research."},"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":"2111.01243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-01T20:08:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d19802ae31a3dbce56a349c678f293684c0d457d77332228414736f4a90f473e","abstract_canon_sha256":"e14ed69830e031a466f36342d81f39309af953c2329e26cac643a7424d559f73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:28:00.657148Z","signature_b64":"0HkqJrxWAla4U+935eI3oE9O01a76zIxHbP/Jbivdg2+VB9/lHn89VyyZdLGZTyeaOhLRHcDAS125xNPxE4mDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b6304aace27fe553bdcdd3204bae3377bba8cac0a4ac9059e13599c52375009","last_reissued_at":"2026-07-05T03:28:00.656694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:28:00.656694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amir Pouran Ben Veyseh, Bonan Min, Dan Roth, Elior Sulem, Eneko Agirre, Hayley Ross, Ilana Heinz, Oscar Sainz, Thien Huu Nguyen","submitted_at":"2021-11-01T20:08:05Z","abstract_excerpt":"Large, pre-trained transformer-based language models such as BERT have drastically changed the Natural Language Processing (NLP) field. We present a survey of recent work that uses these large language models to solve NLP tasks via pre-training then fine-tuning, prompting, or text generation approaches. We also present approaches that use pre-trained language models to generate data for training augmentation or other purposes. We conclude with discussions on limitations and suggested directions for future research."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.01243","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/2111.01243/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":"2111.01243","created_at":"2026-07-05T03:28:00.656756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.01243v1","created_at":"2026-07-05T03:28:00.656756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.01243","created_at":"2026-07-05T03:28:00.656756+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNRQJKWOE77F","created_at":"2026-07-05T03:28:00.656756+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNRQJKWOE77FKO64","created_at":"2026-07-05T03:28:00.656756+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNRQJKWO","created_at":"2026-07-05T03:28:00.656756+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LNRQJKWOE77FKO643UZAJOXDG5","json":"https://pith.science/pith/LNRQJKWOE77FKO643UZAJOXDG5.json","graph_json":"https://pith.science/api/pith-number/LNRQJKWOE77FKO643UZAJOXDG5/graph.json","events_json":"https://pith.science/api/pith-number/LNRQJKWOE77FKO643UZAJOXDG5/events.json","paper":"https://pith.science/paper/LNRQJKWO"},"agent_actions":{"view_html":"https://pith.science/pith/LNRQJKWOE77FKO643UZAJOXDG5","download_json":"https://pith.science/pith/LNRQJKWOE77FKO643UZAJOXDG5.json","view_paper":"https://pith.science/paper/LNRQJKWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.01243&json=true","fetch_graph":"https://pith.science/api/pith-number/LNRQJKWOE77FKO643UZAJOXDG5/graph.json","fetch_events":"https://pith.science/api/pith-number/LNRQJKWOE77FKO643UZAJOXDG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNRQJKWOE77FKO643UZAJOXDG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNRQJKWOE77FKO643UZAJOXDG5/action/storage_attestation","attest_author":"https://pith.science/pith/LNRQJKWOE77FKO643UZAJOXDG5/action/author_attestation","sign_citation":"https://pith.science/pith/LNRQJKWOE77FKO643UZAJOXDG5/action/citation_signature","submit_replication":"https://pith.science/pith/LNRQJKWOE77FKO643UZAJOXDG5/action/replication_record"}},"created_at":"2026-07-05T03:28:00.656756+00:00","updated_at":"2026-07-05T03:28:00.656756+00:00"}