{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4MU7EIC5HOKR33TF3YDSQP3UYG","short_pith_number":"pith:4MU7EIC5","schema_version":"1.0","canonical_sha256":"e329f2205d3b951dee65de07283f74c1a0e2c2b5c57e18bb3d6e37c9f8674608","source":{"kind":"arxiv","id":"2304.02020","version":1},"attestation_state":"computed","paper":{"title":"A Bibliometric Review of Large Language Models Research from 2017 to 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CY","cs.SI"],"primary_cat":"cs.DL","authors_text":"Huizi Yu, Libby Hemphill, Lingyao Li, Lizhou Fan, Sanggyu Lee, Zihui Ma","submitted_at":"2023-04-03T21:46:41Z","abstract_excerpt":"Large language models (LLMs) are a class of language models that have demonstrated outstanding performance across a range of natural language processing (NLP) tasks and have become a highly sought-after research area, because of their ability to generate human-like language and their potential to revolutionize science and technology. In this study, we conduct bibliometric and discourse analyses of scholarly literature on LLMs. Synthesizing over 5,000 publications, this paper serves as a roadmap for researchers, practitioners, and policymakers to navigate the current landscape of LLMs 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":"2304.02020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DL","submitted_at":"2023-04-03T21:46:41Z","cross_cats_sorted":["cs.CL","cs.CY","cs.SI"],"title_canon_sha256":"2be657f35847731485cb39d73323d41e578ae92f209149ac78a8c11fffa7d725","abstract_canon_sha256":"f595556c47bb209dfeb679e67cf529dd64472ee273e967a6f0b5e99e1572985d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:21.249236Z","signature_b64":"kv2Fh/6r5m6T/0AFu9ntExcu0C23CYqv5LwlcYIMaJgcO3hzePaJ76GPVviUPQJVeB76SZA/apYaOQec4H/BBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e329f2205d3b951dee65de07283f74c1a0e2c2b5c57e18bb3d6e37c9f8674608","last_reissued_at":"2026-07-05T05:58:21.248747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:21.248747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Bibliometric Review of Large Language Models Research from 2017 to 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CY","cs.SI"],"primary_cat":"cs.DL","authors_text":"Huizi Yu, Libby Hemphill, Lingyao Li, Lizhou Fan, Sanggyu Lee, Zihui Ma","submitted_at":"2023-04-03T21:46:41Z","abstract_excerpt":"Large language models (LLMs) are a class of language models that have demonstrated outstanding performance across a range of natural language processing (NLP) tasks and have become a highly sought-after research area, because of their ability to generate human-like language and their potential to revolutionize science and technology. In this study, we conduct bibliometric and discourse analyses of scholarly literature on LLMs. Synthesizing over 5,000 publications, this paper serves as a roadmap for researchers, practitioners, and policymakers to navigate the current landscape of LLMs research."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02020","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/2304.02020/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":"2304.02020","created_at":"2026-07-05T05:58:21.248806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.02020v1","created_at":"2026-07-05T05:58:21.248806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02020","created_at":"2026-07-05T05:58:21.248806+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MU7EIC5HOKR","created_at":"2026-07-05T05:58:21.248806+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MU7EIC5HOKR33TF","created_at":"2026-07-05T05:58:21.248806+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MU7EIC5","created_at":"2026-07-05T05:58:21.248806+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28345","citing_title":"Auditing LLM-Governed Social Robots with Culture-Specific Moral Gradients","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16714","citing_title":"GRID: Graph Representation of Intelligence Data for Security Text Knowledge Graph Construction","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25939","citing_title":"SoK: Honeypots & LLMs, More Than the Sum of Their Parts?","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08904","citing_title":"OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4MU7EIC5HOKR33TF3YDSQP3UYG","json":"https://pith.science/pith/4MU7EIC5HOKR33TF3YDSQP3UYG.json","graph_json":"https://pith.science/api/pith-number/4MU7EIC5HOKR33TF3YDSQP3UYG/graph.json","events_json":"https://pith.science/api/pith-number/4MU7EIC5HOKR33TF3YDSQP3UYG/events.json","paper":"https://pith.science/paper/4MU7EIC5"},"agent_actions":{"view_html":"https://pith.science/pith/4MU7EIC5HOKR33TF3YDSQP3UYG","download_json":"https://pith.science/pith/4MU7EIC5HOKR33TF3YDSQP3UYG.json","view_paper":"https://pith.science/paper/4MU7EIC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.02020&json=true","fetch_graph":"https://pith.science/api/pith-number/4MU7EIC5HOKR33TF3YDSQP3UYG/graph.json","fetch_events":"https://pith.science/api/pith-number/4MU7EIC5HOKR33TF3YDSQP3UYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MU7EIC5HOKR33TF3YDSQP3UYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MU7EIC5HOKR33TF3YDSQP3UYG/action/storage_attestation","attest_author":"https://pith.science/pith/4MU7EIC5HOKR33TF3YDSQP3UYG/action/author_attestation","sign_citation":"https://pith.science/pith/4MU7EIC5HOKR33TF3YDSQP3UYG/action/citation_signature","submit_replication":"https://pith.science/pith/4MU7EIC5HOKR33TF3YDSQP3UYG/action/replication_record"}},"created_at":"2026-07-05T05:58:21.248806+00:00","updated_at":"2026-07-05T05:58:21.248806+00:00"}