{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LQE6WVJNAS5G54EXPH5RNQOLT3","short_pith_number":"pith:LQE6WVJN","schema_version":"1.0","canonical_sha256":"5c09eb552d04ba6ef09779fb16c1cb9ef528816067b9ff65a3bb9e7ca3852b71","source":{"kind":"arxiv","id":"2606.25747","version":1},"attestation_state":"computed","paper":{"title":"CodeChat-Eval: Evaluating Large Language Models in Multi-Turn Code Refinement Dialogues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Aldeida Aleti, Guoxiang (Aaron) Guo, Kla Tantithamthavorn, Neelofar Neelofar, Yuanyuan Qi","submitted_at":"2026-06-24T12:16:04Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used in software engineering to generate and refine code. In practice, developers often continue from an initial code generation request with follow-up refinement instructions, such as requests to improve style, restructure implementation, or change the execution strategy while preserving the intended behaviour. However, existing benchmarks generally omit this multi-turn code refinement dialogue setting and therefore cannot evaluate whether LLMs maintain functional correctness, i.e., whether the refined code still passes the test suite for the orig"},"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":"2606.25747","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-24T12:16:04Z","cross_cats_sorted":[],"title_canon_sha256":"e788afeb47324ac5af7bc380ffb8775d772ab121e1163ea604ddc0590d1c98f0","abstract_canon_sha256":"bcbaa5807dcffa6f57eea693f42ec5c4c92ec43f1388c85e709b9d8880cd751c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:14.201546Z","signature_b64":"XPItzCKhMQMr3IajFO9XUbRzVBkHZiy69bpx7nufAI/jtPg1sI8hXUtIIOjC2+CWIdqj/Kie4m1lpCZ+xfWACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c09eb552d04ba6ef09779fb16c1cb9ef528816067b9ff65a3bb9e7ca3852b71","last_reissued_at":"2026-06-25T01:18:14.201163Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:14.201163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeChat-Eval: Evaluating Large Language Models in Multi-Turn Code Refinement Dialogues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Aldeida Aleti, Guoxiang (Aaron) Guo, Kla Tantithamthavorn, Neelofar Neelofar, Yuanyuan Qi","submitted_at":"2026-06-24T12:16:04Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly used in software engineering to generate and refine code. In practice, developers often continue from an initial code generation request with follow-up refinement instructions, such as requests to improve style, restructure implementation, or change the execution strategy while preserving the intended behaviour. However, existing benchmarks generally omit this multi-turn code refinement dialogue setting and therefore cannot evaluate whether LLMs maintain functional correctness, i.e., whether the refined code still passes the test suite for the orig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25747","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/2606.25747/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":"2606.25747","created_at":"2026-06-25T01:18:14.201221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25747v1","created_at":"2026-06-25T01:18:14.201221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25747","created_at":"2026-06-25T01:18:14.201221+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQE6WVJNAS5G","created_at":"2026-06-25T01:18:14.201221+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQE6WVJNAS5G54EX","created_at":"2026-06-25T01:18:14.201221+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQE6WVJN","created_at":"2026-06-25T01:18:14.201221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQE6WVJNAS5G54EXPH5RNQOLT3","json":"https://pith.science/pith/LQE6WVJNAS5G54EXPH5RNQOLT3.json","graph_json":"https://pith.science/api/pith-number/LQE6WVJNAS5G54EXPH5RNQOLT3/graph.json","events_json":"https://pith.science/api/pith-number/LQE6WVJNAS5G54EXPH5RNQOLT3/events.json","paper":"https://pith.science/paper/LQE6WVJN"},"agent_actions":{"view_html":"https://pith.science/pith/LQE6WVJNAS5G54EXPH5RNQOLT3","download_json":"https://pith.science/pith/LQE6WVJNAS5G54EXPH5RNQOLT3.json","view_paper":"https://pith.science/paper/LQE6WVJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25747&json=true","fetch_graph":"https://pith.science/api/pith-number/LQE6WVJNAS5G54EXPH5RNQOLT3/graph.json","fetch_events":"https://pith.science/api/pith-number/LQE6WVJNAS5G54EXPH5RNQOLT3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQE6WVJNAS5G54EXPH5RNQOLT3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQE6WVJNAS5G54EXPH5RNQOLT3/action/storage_attestation","attest_author":"https://pith.science/pith/LQE6WVJNAS5G54EXPH5RNQOLT3/action/author_attestation","sign_citation":"https://pith.science/pith/LQE6WVJNAS5G54EXPH5RNQOLT3/action/citation_signature","submit_replication":"https://pith.science/pith/LQE6WVJNAS5G54EXPH5RNQOLT3/action/replication_record"}},"created_at":"2026-06-25T01:18:14.201221+00:00","updated_at":"2026-06-25T01:18:14.201221+00:00"}