{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6NLLA23UAZ3O4KB2MO2GGB5OCF","short_pith_number":"pith:6NLLA23U","schema_version":"1.0","canonical_sha256":"f356b06b740676ee283a63b46307ae114a4c6456e4f6c85d9b751a5866c8f09a","source":{"kind":"arxiv","id":"2311.07361","version":2},"attestation_state":"computed","paper":{"title":"The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Microsoft Azure Quantum, Microsoft Research AI4Science","submitted_at":"2023-11-13T14:26:12Z","abstract_excerpt":"In recent years, groundbreaking advancements in natural language processing have culminated in the emergence of powerful large language models (LLMs), which have showcased remarkable capabilities across a vast array of domains, including the understanding, generation, and translation of natural language, and even tasks that extend beyond language processing. In this report, we delve into the performance of LLMs within the context of scientific discovery, focusing on GPT-4, the state-of-the-art language model. Our investigation spans a diverse range of scientific areas encompassing drug discove"},"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":"2311.07361","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T14:26:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"12e5ca8e57171458283b87dabf4ebf8ca2da64139e8c392c4d0e016bcc9747f2","abstract_canon_sha256":"e72ebf90a0d58a977f4832f215ece5582abd3f680ecdd54138c3322cb10fe1c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:46.070527Z","signature_b64":"fFFYPWP+EFCBRBGHLygk/gOANBBPzV3orSxZ9DJqa1gEwiRBqk9u+qAKX1Q8H2pBt8N4g3sozp0XVVoMSIB0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f356b06b740676ee283a63b46307ae114a4c6456e4f6c85d9b751a5866c8f09a","last_reissued_at":"2026-07-05T07:21:46.070042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:46.070042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Microsoft Azure Quantum, Microsoft Research AI4Science","submitted_at":"2023-11-13T14:26:12Z","abstract_excerpt":"In recent years, groundbreaking advancements in natural language processing have culminated in the emergence of powerful large language models (LLMs), which have showcased remarkable capabilities across a vast array of domains, including the understanding, generation, and translation of natural language, and even tasks that extend beyond language processing. In this report, we delve into the performance of LLMs within the context of scientific discovery, focusing on GPT-4, the state-of-the-art language model. Our investigation spans a diverse range of scientific areas encompassing drug discove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07361","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/2311.07361/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":"2311.07361","created_at":"2026-07-05T07:21:46.070096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07361v2","created_at":"2026-07-05T07:21:46.070096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07361","created_at":"2026-07-05T07:21:46.070096+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NLLA23UAZ3O","created_at":"2026-07-05T07:21:46.070096+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NLLA23UAZ3O4KB2","created_at":"2026-07-05T07:21:46.070096+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NLLA23U","created_at":"2026-07-05T07:21:46.070096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25039","citing_title":"LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Search","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00531","citing_title":"Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24043","citing_title":"LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2407.13059","citing_title":"Prioritizing High-Consequence Biological Capabilities in Evaluations of Artificial Intelligence Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2510.06824","citing_title":"Efficient numeracy in language models through single-token number embeddings","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08804","citing_title":"MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23106","citing_title":"No Test Cases, No Problem: Distillation-Driven Code Generation for Scientific Workflows","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12973","citing_title":"An Engineering Journey Training Large Language Models at Scale on Alps: The Apertus Experience","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NLLA23UAZ3O4KB2MO2GGB5OCF","json":"https://pith.science/pith/6NLLA23UAZ3O4KB2MO2GGB5OCF.json","graph_json":"https://pith.science/api/pith-number/6NLLA23UAZ3O4KB2MO2GGB5OCF/graph.json","events_json":"https://pith.science/api/pith-number/6NLLA23UAZ3O4KB2MO2GGB5OCF/events.json","paper":"https://pith.science/paper/6NLLA23U"},"agent_actions":{"view_html":"https://pith.science/pith/6NLLA23UAZ3O4KB2MO2GGB5OCF","download_json":"https://pith.science/pith/6NLLA23UAZ3O4KB2MO2GGB5OCF.json","view_paper":"https://pith.science/paper/6NLLA23U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07361&json=true","fetch_graph":"https://pith.science/api/pith-number/6NLLA23UAZ3O4KB2MO2GGB5OCF/graph.json","fetch_events":"https://pith.science/api/pith-number/6NLLA23UAZ3O4KB2MO2GGB5OCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NLLA23UAZ3O4KB2MO2GGB5OCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NLLA23UAZ3O4KB2MO2GGB5OCF/action/storage_attestation","attest_author":"https://pith.science/pith/6NLLA23UAZ3O4KB2MO2GGB5OCF/action/author_attestation","sign_citation":"https://pith.science/pith/6NLLA23UAZ3O4KB2MO2GGB5OCF/action/citation_signature","submit_replication":"https://pith.science/pith/6NLLA23UAZ3O4KB2MO2GGB5OCF/action/replication_record"}},"created_at":"2026-07-05T07:21:46.070096+00:00","updated_at":"2026-07-05T07:21:46.070096+00:00"}