{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DU5RBK23V6WTJDSJZYBIQQMBF6","short_pith_number":"pith:DU5RBK23","schema_version":"1.0","canonical_sha256":"1d3b10ab5bafad348e49ce028841812f94556463846396b7227c68cc51c2b089","source":{"kind":"arxiv","id":"2509.10402","version":1},"attestation_state":"computed","paper":{"title":"Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bram Adams, Suzhen Zhong, Ying Zou","submitted_at":"2025-09-12T16:52:49Z","abstract_excerpt":"Large Language Models (LLMs) are becoming integral to modern software development workflows, assisting developers with code generation, API explanation, and iterative problem-solving through natural language conversations. Despite widespread adoption, there is limited understanding of how developers interact with LLMs in practice and how these conversational dynamics influence task outcomes, code quality, and software engineering workflows. To address this, we leverage CodeChat, a large dataset comprising 82,845 real-world developer-LLM conversations, containing 368,506 code snippets generated"},"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":"2509.10402","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-09-12T16:52:49Z","cross_cats_sorted":[],"title_canon_sha256":"c5b37f87b799e22b0c2d4083c4673bbb2126f71bfed6c6417b71b5d5296fb1b8","abstract_canon_sha256":"c7d1608420076a8bc4de63561a188bb7ea2fd2eca8c765730b47466ae3b22463"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:09.191690Z","signature_b64":"sBaE32jq2iUXMvM8CEpUPJsVE3KVuU4ICdt9ciUFFRVJPYqDd1+loF3U+roiIe+0CD9VYAWGuvnYRlXY3GIpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d3b10ab5bafad348e49ce028841812f94556463846396b7227c68cc51c2b089","last_reissued_at":"2026-07-05T12:11:09.191191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:09.191191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bram Adams, Suzhen Zhong, Ying Zou","submitted_at":"2025-09-12T16:52:49Z","abstract_excerpt":"Large Language Models (LLMs) are becoming integral to modern software development workflows, assisting developers with code generation, API explanation, and iterative problem-solving through natural language conversations. Despite widespread adoption, there is limited understanding of how developers interact with LLMs in practice and how these conversational dynamics influence task outcomes, code quality, and software engineering workflows. To address this, we leverage CodeChat, a large dataset comprising 82,845 real-world developer-LLM conversations, containing 368,506 code snippets generated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10402","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/2509.10402/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":"2509.10402","created_at":"2026-07-05T12:11:09.191254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.10402v1","created_at":"2026-07-05T12:11:09.191254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10402","created_at":"2026-07-05T12:11:09.191254+00:00"},{"alias_kind":"pith_short_12","alias_value":"DU5RBK23V6WT","created_at":"2026-07-05T12:11:09.191254+00:00"},{"alias_kind":"pith_short_16","alias_value":"DU5RBK23V6WTJDSJ","created_at":"2026-07-05T12:11:09.191254+00:00"},{"alias_kind":"pith_short_8","alias_value":"DU5RBK23","created_at":"2026-07-05T12:11:09.191254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25747","citing_title":"CodeChat-Eval: Evaluating Large Language Models in Multi-Turn Code Refinement Dialogues","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25747","citing_title":"CodeChat-Eval: Evaluating Large Language Models in Multi-Turn Code Refinement Dialogues","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DU5RBK23V6WTJDSJZYBIQQMBF6","json":"https://pith.science/pith/DU5RBK23V6WTJDSJZYBIQQMBF6.json","graph_json":"https://pith.science/api/pith-number/DU5RBK23V6WTJDSJZYBIQQMBF6/graph.json","events_json":"https://pith.science/api/pith-number/DU5RBK23V6WTJDSJZYBIQQMBF6/events.json","paper":"https://pith.science/paper/DU5RBK23"},"agent_actions":{"view_html":"https://pith.science/pith/DU5RBK23V6WTJDSJZYBIQQMBF6","download_json":"https://pith.science/pith/DU5RBK23V6WTJDSJZYBIQQMBF6.json","view_paper":"https://pith.science/paper/DU5RBK23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.10402&json=true","fetch_graph":"https://pith.science/api/pith-number/DU5RBK23V6WTJDSJZYBIQQMBF6/graph.json","fetch_events":"https://pith.science/api/pith-number/DU5RBK23V6WTJDSJZYBIQQMBF6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DU5RBK23V6WTJDSJZYBIQQMBF6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DU5RBK23V6WTJDSJZYBIQQMBF6/action/storage_attestation","attest_author":"https://pith.science/pith/DU5RBK23V6WTJDSJZYBIQQMBF6/action/author_attestation","sign_citation":"https://pith.science/pith/DU5RBK23V6WTJDSJZYBIQQMBF6/action/citation_signature","submit_replication":"https://pith.science/pith/DU5RBK23V6WTJDSJZYBIQQMBF6/action/replication_record"}},"created_at":"2026-07-05T12:11:09.191254+00:00","updated_at":"2026-07-05T12:11:09.191254+00:00"}