{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UFXXMLQF2NWV6W65HWA5D2JFS3","short_pith_number":"pith:UFXXMLQF","schema_version":"1.0","canonical_sha256":"a16f762e05d36d5f5bdd3d81d1e92596ed97a2f12b8f5d8b032069102c2e87b6","source":{"kind":"arxiv","id":"2411.03417","version":2},"attestation_state":"computed","paper":{"title":"Usefulness of LLMs as an Author Checklist Assistant for Scientific Papers: NeurIPS'24 Experiment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL","cs.HC"],"primary_cat":"cs.CL","authors_text":"Alexander Goldberg, Benedictus Kent Rachmat, Ihsan Ullah, Isabelle Guyon, Nihar B. Shah, Thanh Gia Hieu Khuong, Zhen Xu","submitted_at":"2024-11-05T18:58:00Z","abstract_excerpt":"Large language models (LLMs) represent a promising, but controversial, tool in aiding scientific peer review. This study evaluates the usefulness of LLMs in a conference setting as a tool for vetting paper submissions against submission standards. We conduct an experiment at the 2024 Neural Information Processing Systems (NeurIPS) conference, where 234 papers were voluntarily submitted to an \"LLM-based Checklist Assistant.\" This assistant validates whether papers adhere to the author checklist used by NeurIPS, which includes questions to ensure compliance with research and manuscript preparati"},"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":"2411.03417","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-05T18:58:00Z","cross_cats_sorted":["cs.DL","cs.HC"],"title_canon_sha256":"8c4521160ed0f5c7db56004afccfbc554ffdf20dd3c029caccda2fe0e9a4810d","abstract_canon_sha256":"164661b66a03651193d3de5ed52b04452d804d3d92c879db33d96741edca1e7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:11.178485Z","signature_b64":"gCiXOt/fXGqt5tFWJG+3wm6GwD93DCJpxqqR2FfY24guAFe1jMubwgZSH8qwnxA61V0UwFvKmGQiNnd1qfWBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a16f762e05d36d5f5bdd3d81d1e92596ed97a2f12b8f5d8b032069102c2e87b6","last_reissued_at":"2026-07-05T09:33:11.177834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:11.177834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Usefulness of LLMs as an Author Checklist Assistant for Scientific Papers: NeurIPS'24 Experiment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DL","cs.HC"],"primary_cat":"cs.CL","authors_text":"Alexander Goldberg, Benedictus Kent Rachmat, Ihsan Ullah, Isabelle Guyon, Nihar B. Shah, Thanh Gia Hieu Khuong, Zhen Xu","submitted_at":"2024-11-05T18:58:00Z","abstract_excerpt":"Large language models (LLMs) represent a promising, but controversial, tool in aiding scientific peer review. This study evaluates the usefulness of LLMs in a conference setting as a tool for vetting paper submissions against submission standards. We conduct an experiment at the 2024 Neural Information Processing Systems (NeurIPS) conference, where 234 papers were voluntarily submitted to an \"LLM-based Checklist Assistant.\" This assistant validates whether papers adhere to the author checklist used by NeurIPS, which includes questions to ensure compliance with research and manuscript preparati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03417","kind":"arxiv","version":2},"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/2411.03417/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":"2411.03417","created_at":"2026-07-05T09:33:11.177901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03417v2","created_at":"2026-07-05T09:33:11.177901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03417","created_at":"2026-07-05T09:33:11.177901+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFXXMLQF2NWV","created_at":"2026-07-05T09:33:11.177901+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFXXMLQF2NWV6W65","created_at":"2026-07-05T09:33:11.177901+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFXXMLQF","created_at":"2026-07-05T09:33:11.177901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27687","citing_title":"Mitigating LLM-based p-Hacking by Preregistering for the Next LLM","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08586","citing_title":"Computer Science Conferences Should Require Nonrepudiable Experimental Results","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13940","citing_title":"AI-Assisted Peer Review at Scale: The AAAI-26 AI Review Pilot","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFXXMLQF2NWV6W65HWA5D2JFS3","json":"https://pith.science/pith/UFXXMLQF2NWV6W65HWA5D2JFS3.json","graph_json":"https://pith.science/api/pith-number/UFXXMLQF2NWV6W65HWA5D2JFS3/graph.json","events_json":"https://pith.science/api/pith-number/UFXXMLQF2NWV6W65HWA5D2JFS3/events.json","paper":"https://pith.science/paper/UFXXMLQF"},"agent_actions":{"view_html":"https://pith.science/pith/UFXXMLQF2NWV6W65HWA5D2JFS3","download_json":"https://pith.science/pith/UFXXMLQF2NWV6W65HWA5D2JFS3.json","view_paper":"https://pith.science/paper/UFXXMLQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03417&json=true","fetch_graph":"https://pith.science/api/pith-number/UFXXMLQF2NWV6W65HWA5D2JFS3/graph.json","fetch_events":"https://pith.science/api/pith-number/UFXXMLQF2NWV6W65HWA5D2JFS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFXXMLQF2NWV6W65HWA5D2JFS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFXXMLQF2NWV6W65HWA5D2JFS3/action/storage_attestation","attest_author":"https://pith.science/pith/UFXXMLQF2NWV6W65HWA5D2JFS3/action/author_attestation","sign_citation":"https://pith.science/pith/UFXXMLQF2NWV6W65HWA5D2JFS3/action/citation_signature","submit_replication":"https://pith.science/pith/UFXXMLQF2NWV6W65HWA5D2JFS3/action/replication_record"}},"created_at":"2026-07-05T09:33:11.177901+00:00","updated_at":"2026-07-05T09:33:11.177901+00:00"}