{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IW4FTQW5PZUTBKLTKNJIPRR4SV","short_pith_number":"pith:IW4FTQW5","schema_version":"1.0","canonical_sha256":"45b859c2dd7e6930a973535287c63c95416b1d663428f3589b1dbc1b47c00ac8","source":{"kind":"arxiv","id":"2502.17348","version":1},"attestation_state":"computed","paper":{"title":"How Scientists Use Large Language Models to Program","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.SE","authors_text":"Gabrielle O'Brien","submitted_at":"2025-02-24T17:23:12Z","abstract_excerpt":"Scientists across disciplines write code for critical activities like data collection and generation, statistical modeling, and visualization. As large language models that can generate code have become widely available, scientists may increasingly use these models during research software development. We investigate the characteristics of scientists who are early-adopters of code generating models and conduct interviews with scientists at a public, research-focused university. Through interviews and reviews of user interaction logs, we see that scientists often use code generating models as 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":"2502.17348","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-24T17:23:12Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"1a387265e315f086256b81da4b1b199d9cfad32fbfca5038790c96d90cb85c66","abstract_canon_sha256":"ec6d3e0b4cc66165374eb5f5d347e34fe8cd93d8e86bba51d883c1cf9706d9ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:09.216035Z","signature_b64":"G09eoo9vKGMcdezIWWw5rf24o0jKoZeVq1/+jRqCrmtJFElOIKQ9K4m/uJgH1RmfnaTNiZK73HmH8OQdCfarBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45b859c2dd7e6930a973535287c63c95416b1d663428f3589b1dbc1b47c00ac8","last_reissued_at":"2026-07-05T10:19:09.215524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:09.215524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Scientists Use Large Language Models to Program","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.SE","authors_text":"Gabrielle O'Brien","submitted_at":"2025-02-24T17:23:12Z","abstract_excerpt":"Scientists across disciplines write code for critical activities like data collection and generation, statistical modeling, and visualization. As large language models that can generate code have become widely available, scientists may increasingly use these models during research software development. We investigate the characteristics of scientists who are early-adopters of code generating models and conduct interviews with scientists at a public, research-focused university. Through interviews and reviews of user interaction logs, we see that scientists often use code generating models as a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17348","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/2502.17348/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":"2502.17348","created_at":"2026-07-05T10:19:09.215578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17348v1","created_at":"2026-07-05T10:19:09.215578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17348","created_at":"2026-07-05T10:19:09.215578+00:00"},{"alias_kind":"pith_short_12","alias_value":"IW4FTQW5PZUT","created_at":"2026-07-05T10:19:09.215578+00:00"},{"alias_kind":"pith_short_16","alias_value":"IW4FTQW5PZUTBKLT","created_at":"2026-07-05T10:19:09.215578+00:00"},{"alias_kind":"pith_short_8","alias_value":"IW4FTQW5","created_at":"2026-07-05T10:19:09.215578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10051","citing_title":"The Effects of GitHub Copilot on Computing Students' Programming Effectiveness, Efficiency, and Processes in Brownfield Programming Tasks","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IW4FTQW5PZUTBKLTKNJIPRR4SV","json":"https://pith.science/pith/IW4FTQW5PZUTBKLTKNJIPRR4SV.json","graph_json":"https://pith.science/api/pith-number/IW4FTQW5PZUTBKLTKNJIPRR4SV/graph.json","events_json":"https://pith.science/api/pith-number/IW4FTQW5PZUTBKLTKNJIPRR4SV/events.json","paper":"https://pith.science/paper/IW4FTQW5"},"agent_actions":{"view_html":"https://pith.science/pith/IW4FTQW5PZUTBKLTKNJIPRR4SV","download_json":"https://pith.science/pith/IW4FTQW5PZUTBKLTKNJIPRR4SV.json","view_paper":"https://pith.science/paper/IW4FTQW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17348&json=true","fetch_graph":"https://pith.science/api/pith-number/IW4FTQW5PZUTBKLTKNJIPRR4SV/graph.json","fetch_events":"https://pith.science/api/pith-number/IW4FTQW5PZUTBKLTKNJIPRR4SV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IW4FTQW5PZUTBKLTKNJIPRR4SV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IW4FTQW5PZUTBKLTKNJIPRR4SV/action/storage_attestation","attest_author":"https://pith.science/pith/IW4FTQW5PZUTBKLTKNJIPRR4SV/action/author_attestation","sign_citation":"https://pith.science/pith/IW4FTQW5PZUTBKLTKNJIPRR4SV/action/citation_signature","submit_replication":"https://pith.science/pith/IW4FTQW5PZUTBKLTKNJIPRR4SV/action/replication_record"}},"created_at":"2026-07-05T10:19:09.215578+00:00","updated_at":"2026-07-05T10:19:09.215578+00:00"}