{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G5ZALOF7CPC37H37IYRFWM253G","short_pith_number":"pith:G5ZALOF7","schema_version":"1.0","canonical_sha256":"377205b8bf13c5bf9f7f46225b335dd994b8f337b8350db30f08246a2cee2af0","source":{"kind":"arxiv","id":"2404.01268","version":1},"attestation_state":"computed","paper":{"title":"Mapping the Increasing Use of LLMs in Scientific Papers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.DL","cs.LG","cs.SI"],"primary_cat":"cs.CL","authors_text":"Christopher D Manning, Christopher Potts, Diyi Yang, Haley Lepp, Hancheng Cao, James Y. Zou, Sheng Liu, Siyu He, Weixin Liang, Wenlong Ji, Xuandong Zhao, Yaohui Zhang, Zhengxuan Wu, Zhi Huang","submitted_at":"2024-04-01T17:45:15Z","abstract_excerpt":"Scientific publishing lays the foundation of science by disseminating research findings, fostering collaboration, encouraging reproducibility, and ensuring that scientific knowledge is accessible, verifiable, and built upon over time. Recently, there has been immense speculation about how many people are using large language models (LLMs) like ChatGPT in their academic writing, and to what extent this tool might have an effect on global scientific practices. However, we lack a precise measure of the proportion of academic writing substantially modified or produced by LLMs. To address this gap,"},"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":"2404.01268","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-01T17:45:15Z","cross_cats_sorted":["cs.AI","cs.DL","cs.LG","cs.SI"],"title_canon_sha256":"8ce0e68516025def71d0baee925d477fae04ec91bc8902e078567bcba132054b","abstract_canon_sha256":"c152c043b0aa142bc17844020cb49bde7816f1358f3cccfa8c50156aff04dee1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:03.724566Z","signature_b64":"XmK6MXNt1VelePOxR37L01JZi+T8fM1lENjewg79On/SOCpwj+UpYEKG0onwSqDreo6ihcHZoItGEA9TyGcDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"377205b8bf13c5bf9f7f46225b335dd994b8f337b8350db30f08246a2cee2af0","last_reissued_at":"2026-07-05T08:03:03.724063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:03.724063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mapping the Increasing Use of LLMs in Scientific Papers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.DL","cs.LG","cs.SI"],"primary_cat":"cs.CL","authors_text":"Christopher D Manning, Christopher Potts, Diyi Yang, Haley Lepp, Hancheng Cao, James Y. Zou, Sheng Liu, Siyu He, Weixin Liang, Wenlong Ji, Xuandong Zhao, Yaohui Zhang, Zhengxuan Wu, Zhi Huang","submitted_at":"2024-04-01T17:45:15Z","abstract_excerpt":"Scientific publishing lays the foundation of science by disseminating research findings, fostering collaboration, encouraging reproducibility, and ensuring that scientific knowledge is accessible, verifiable, and built upon over time. Recently, there has been immense speculation about how many people are using large language models (LLMs) like ChatGPT in their academic writing, and to what extent this tool might have an effect on global scientific practices. However, we lack a precise measure of the proportion of academic writing substantially modified or produced by LLMs. To address this gap,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01268","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/2404.01268/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":"2404.01268","created_at":"2026-07-05T08:03:03.724123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.01268v1","created_at":"2026-07-05T08:03:03.724123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01268","created_at":"2026-07-05T08:03:03.724123+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5ZALOF7CPC3","created_at":"2026-07-05T08:03:03.724123+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5ZALOF7CPC37H37","created_at":"2026-07-05T08:03:03.724123+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5ZALOF7","created_at":"2026-07-05T08:03:03.724123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25152","citing_title":"Hitting a Moving Target: Test-Time Adaptation for AI Text Detection under Continual Distribution Shift","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07951","citing_title":"From `May' to `Is': Certainty Distortion in Language Model Rewriting","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00738","citing_title":"Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00334","citing_title":"Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27930","citing_title":"An LLM-Powered Semantic Alignment Framework for Journal Recommendation","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28277","citing_title":"Towards Automating Scientific Review with Google's Paper Assistant Tool","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08723","citing_title":"From Text to Discovery: How Large Language Models Are Reshaping Research Across Scientific and Humanistic Disciplines","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2502.11008","citing_title":"CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08568","citing_title":"Can We Still Hear the Accent? Investigating the Resilience of Native Language Signals in the LLM Era","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25860","citing_title":"Luminol-AIDetect: Fast Zero-shot Machine-Generated Text Detection based on Perplexity under Text Shuffling","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23136","citing_title":"How Researchers Navigate Accountability, Transparency, and Trust When Using AI Tools in Early-Stage Research: A Think-Aloud Study","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11261","citing_title":"Inspectable AI for Science: A Research Object Approach to Generative AI Governance","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07565","citing_title":"Have LLM-associated terms increased in article full texts in all fields?","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05714","citing_title":"Publish and Perish: How AI-Accelerated Writing Without Proportional Verification Investment Degrades Scientific Knowledge","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5ZALOF7CPC37H37IYRFWM253G","json":"https://pith.science/pith/G5ZALOF7CPC37H37IYRFWM253G.json","graph_json":"https://pith.science/api/pith-number/G5ZALOF7CPC37H37IYRFWM253G/graph.json","events_json":"https://pith.science/api/pith-number/G5ZALOF7CPC37H37IYRFWM253G/events.json","paper":"https://pith.science/paper/G5ZALOF7"},"agent_actions":{"view_html":"https://pith.science/pith/G5ZALOF7CPC37H37IYRFWM253G","download_json":"https://pith.science/pith/G5ZALOF7CPC37H37IYRFWM253G.json","view_paper":"https://pith.science/paper/G5ZALOF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.01268&json=true","fetch_graph":"https://pith.science/api/pith-number/G5ZALOF7CPC37H37IYRFWM253G/graph.json","fetch_events":"https://pith.science/api/pith-number/G5ZALOF7CPC37H37IYRFWM253G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5ZALOF7CPC37H37IYRFWM253G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5ZALOF7CPC37H37IYRFWM253G/action/storage_attestation","attest_author":"https://pith.science/pith/G5ZALOF7CPC37H37IYRFWM253G/action/author_attestation","sign_citation":"https://pith.science/pith/G5ZALOF7CPC37H37IYRFWM253G/action/citation_signature","submit_replication":"https://pith.science/pith/G5ZALOF7CPC37H37IYRFWM253G/action/replication_record"}},"created_at":"2026-07-05T08:03:03.724123+00:00","updated_at":"2026-07-05T08:03:03.724123+00:00"}