{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CHC2D6PDONQK6RI2FW7TT66XGH","short_pith_number":"pith:CHC2D6PD","schema_version":"1.0","canonical_sha256":"11c5a1f9e37360af451a2dbf39fbd731e389de144335a044d0259f684575b989","source":{"kind":"arxiv","id":"2412.13612","version":5},"attestation_state":"computed","paper":{"title":"Large Language Models for Automated Literature Review: An Evaluation of Reference Generation, Abstract Writing, and Review Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Xuemei Tang, Xufeng Duan, Zhenguang G. Cai","submitted_at":"2024-12-18T08:42:25Z","abstract_excerpt":"Large language models (LLMs) have emerged as a potential solution to automate the complex processes involved in writing literature reviews, such as literature collection, organization, and summarization. However, it is yet unclear how good LLMs are at automating comprehensive and reliable literature reviews. This study introduces a framework to automatically evaluate the performance of LLMs in three key tasks of literature writing: reference generation, literature summary, and literature review composition. We introduce multidimensional evaluation metrics that assess the hallucination rates in"},"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":"2412.13612","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T08:42:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1054d8ce82c96e2e59a3b0bf08f07d25500c269f757cf6fbb92c9d6dce6bd9ee","abstract_canon_sha256":"a19e31c783934703c75462df4d25057444c013d45c6363d18b8c7a71868f396c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:51.760140Z","signature_b64":"WjZjVkWJmGiDsKoQKEbGv5CX0M7pMfJl3li1jJxUjU4XRLyYb9bh7I4cMuAkNPX/ViHAabPm1yAys8Ac8rBdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11c5a1f9e37360af451a2dbf39fbd731e389de144335a044d0259f684575b989","last_reissued_at":"2026-07-05T11:56:51.759662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:51.759662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models for Automated Literature Review: An Evaluation of Reference Generation, Abstract Writing, and Review Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Xuemei Tang, Xufeng Duan, Zhenguang G. Cai","submitted_at":"2024-12-18T08:42:25Z","abstract_excerpt":"Large language models (LLMs) have emerged as a potential solution to automate the complex processes involved in writing literature reviews, such as literature collection, organization, and summarization. However, it is yet unclear how good LLMs are at automating comprehensive and reliable literature reviews. This study introduces a framework to automatically evaluate the performance of LLMs in three key tasks of literature writing: reference generation, literature summary, and literature review composition. We introduce multidimensional evaluation metrics that assess the hallucination rates in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13612","kind":"arxiv","version":5},"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/2412.13612/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":"2412.13612","created_at":"2026-07-05T11:56:51.759720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13612v5","created_at":"2026-07-05T11:56:51.759720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13612","created_at":"2026-07-05T11:56:51.759720+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHC2D6PDONQK","created_at":"2026-07-05T11:56:51.759720+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHC2D6PDONQK6RI2","created_at":"2026-07-05T11:56:51.759720+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHC2D6PD","created_at":"2026-07-05T11:56:51.759720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":201,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CHC2D6PDONQK6RI2FW7TT66XGH","json":"https://pith.science/pith/CHC2D6PDONQK6RI2FW7TT66XGH.json","graph_json":"https://pith.science/api/pith-number/CHC2D6PDONQK6RI2FW7TT66XGH/graph.json","events_json":"https://pith.science/api/pith-number/CHC2D6PDONQK6RI2FW7TT66XGH/events.json","paper":"https://pith.science/paper/CHC2D6PD"},"agent_actions":{"view_html":"https://pith.science/pith/CHC2D6PDONQK6RI2FW7TT66XGH","download_json":"https://pith.science/pith/CHC2D6PDONQK6RI2FW7TT66XGH.json","view_paper":"https://pith.science/paper/CHC2D6PD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13612&json=true","fetch_graph":"https://pith.science/api/pith-number/CHC2D6PDONQK6RI2FW7TT66XGH/graph.json","fetch_events":"https://pith.science/api/pith-number/CHC2D6PDONQK6RI2FW7TT66XGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHC2D6PDONQK6RI2FW7TT66XGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHC2D6PDONQK6RI2FW7TT66XGH/action/storage_attestation","attest_author":"https://pith.science/pith/CHC2D6PDONQK6RI2FW7TT66XGH/action/author_attestation","sign_citation":"https://pith.science/pith/CHC2D6PDONQK6RI2FW7TT66XGH/action/citation_signature","submit_replication":"https://pith.science/pith/CHC2D6PDONQK6RI2FW7TT66XGH/action/replication_record"}},"created_at":"2026-07-05T11:56:51.759720+00:00","updated_at":"2026-07-05T11:56:51.759720+00:00"}