{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MXJXPLGLK6L6VQXIS753DIUQEO","short_pith_number":"pith:MXJXPLGL","schema_version":"1.0","canonical_sha256":"65d377accb5797eac2e897fbb1a29023bc93f8fb1472103ae541961794ed2692","source":{"kind":"arxiv","id":"2403.16887","version":1},"attestation_state":"computed","paper":{"title":"ChatGPT \"contamination\": estimating the prevalence of LLMs in the scholarly literature","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DL","authors_text":"Andrew Gray","submitted_at":"2024-03-25T15:56:37Z","abstract_excerpt":"The use of ChatGPT and similar Large Language Model (LLM) tools in scholarly communication and academic publishing has been widely discussed since they became easily accessible to a general audience in late 2022. This study uses keywords known to be disproportionately present in LLM-generated text to provide an overall estimate for the prevalence of LLM-assisted writing in the scholarly literature. For the publishing year 2023, it is found that several of those keywords show a distinctive and disproportionate increase in their prevalence, individually and in combination. It is estimated that a"},"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":"2403.16887","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DL","submitted_at":"2024-03-25T15:56:37Z","cross_cats_sorted":[],"title_canon_sha256":"3768385ae118f1113f35be68eb4b4c164f0f1ff24fcf683f8acdbb54bf3e450a","abstract_canon_sha256":"97406d68892d3a1acca749b0a93807568195930b43a13a02f65f87867267152a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:22.102652Z","signature_b64":"zq9agJqazPrEem9vOv8gPW4/97xMEAV3RpZgixfzsv6sUhQHM9m5Me7TN7sM+HDQxbgA07nKW0hAMS721TCKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65d377accb5797eac2e897fbb1a29023bc93f8fb1472103ae541961794ed2692","last_reissued_at":"2026-07-05T08:00:22.102240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:22.102240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatGPT \"contamination\": estimating the prevalence of LLMs in the scholarly literature","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DL","authors_text":"Andrew Gray","submitted_at":"2024-03-25T15:56:37Z","abstract_excerpt":"The use of ChatGPT and similar Large Language Model (LLM) tools in scholarly communication and academic publishing has been widely discussed since they became easily accessible to a general audience in late 2022. This study uses keywords known to be disproportionately present in LLM-generated text to provide an overall estimate for the prevalence of LLM-assisted writing in the scholarly literature. For the publishing year 2023, it is found that several of those keywords show a distinctive and disproportionate increase in their prevalence, individually and in combination. It is estimated that a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16887","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/2403.16887/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":"2403.16887","created_at":"2026-07-05T08:00:22.102301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16887v1","created_at":"2026-07-05T08:00:22.102301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16887","created_at":"2026-07-05T08:00:22.102301+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXJXPLGLK6L6","created_at":"2026-07-05T08:00:22.102301+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXJXPLGLK6L6VQXI","created_at":"2026-07-05T08:00:22.102301+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXJXPLGL","created_at":"2026-07-05T08:00:22.102301+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00334","citing_title":"Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29815","citing_title":"PRAIB: Peer Review AI Benchmark of Behaviour of LLM-Assisted Reviewing","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19936","citing_title":"What Are LLMs Doing to Scientific Communication? Measuring Changes in Writing Practices and Reading Experience","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXJXPLGLK6L6VQXIS753DIUQEO","json":"https://pith.science/pith/MXJXPLGLK6L6VQXIS753DIUQEO.json","graph_json":"https://pith.science/api/pith-number/MXJXPLGLK6L6VQXIS753DIUQEO/graph.json","events_json":"https://pith.science/api/pith-number/MXJXPLGLK6L6VQXIS753DIUQEO/events.json","paper":"https://pith.science/paper/MXJXPLGL"},"agent_actions":{"view_html":"https://pith.science/pith/MXJXPLGLK6L6VQXIS753DIUQEO","download_json":"https://pith.science/pith/MXJXPLGLK6L6VQXIS753DIUQEO.json","view_paper":"https://pith.science/paper/MXJXPLGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16887&json=true","fetch_graph":"https://pith.science/api/pith-number/MXJXPLGLK6L6VQXIS753DIUQEO/graph.json","fetch_events":"https://pith.science/api/pith-number/MXJXPLGLK6L6VQXIS753DIUQEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXJXPLGLK6L6VQXIS753DIUQEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXJXPLGLK6L6VQXIS753DIUQEO/action/storage_attestation","attest_author":"https://pith.science/pith/MXJXPLGLK6L6VQXIS753DIUQEO/action/author_attestation","sign_citation":"https://pith.science/pith/MXJXPLGLK6L6VQXIS753DIUQEO/action/citation_signature","submit_replication":"https://pith.science/pith/MXJXPLGLK6L6VQXIS753DIUQEO/action/replication_record"}},"created_at":"2026-07-05T08:00:22.102301+00:00","updated_at":"2026-07-05T08:00:22.102301+00:00"}