{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JIHXEARUMKO2QNJDIFRNUPZEWP","short_pith_number":"pith:JIHXEARU","schema_version":"1.0","canonical_sha256":"4a0f720234629da835234162da3f24b3e9da7c54bf3c5871ec99195b41b0a0c7","source":{"kind":"arxiv","id":"2505.21514","version":1},"attestation_state":"computed","paper":{"title":"SIMCOPILOT: Evaluating Large Language Models for Copilot-Style Code Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.PL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Abhinav Jain, Chris Jermaine, Mingchao Jiang, Sophia Zorek","submitted_at":"2025-05-21T04:59:44Z","abstract_excerpt":"We introduce SIMCOPILOT, a benchmark that simulates the role of large language models (LLMs) as interactive, \"copilot\"-style coding assistants. Targeting both completion (finishing incomplete methods or code blocks) and infill tasks (filling missing segments within existing code), SIMCOPILOT provides a comprehensive framework for evaluating LLM coding capabilities. The benchmark comprises dedicated sub-benchmarks for Java (SIMCOPILOTJ) and Python (SIMCOPILOTP), covering diverse codebases varying in size and complexity. Our key contributions include: (a) establishing a realistic, detailed evalu"},"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":"2505.21514","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T04:59:44Z","cross_cats_sorted":["cs.PL","cs.SE"],"title_canon_sha256":"5e859635b9d856e88f761707c9c11b0182d4a26ca130c2680ad4f4d6173abc92","abstract_canon_sha256":"b816efa3bd51aa664bd1b08900534567367f436f7d85e4dc98941f70575c88a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:59.286857Z","signature_b64":"ivuHAJlqYkBxMmro98kqxZgOVAIZLQk6FtSO6HNSttd/FX5sm3W6TC3g2oP47gXXammLdIAqzvpaFfC+gtteAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a0f720234629da835234162da3f24b3e9da7c54bf3c5871ec99195b41b0a0c7","last_reissued_at":"2026-07-05T11:10:59.286356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:59.286356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SIMCOPILOT: Evaluating Large Language Models for Copilot-Style Code Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.PL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Abhinav Jain, Chris Jermaine, Mingchao Jiang, Sophia Zorek","submitted_at":"2025-05-21T04:59:44Z","abstract_excerpt":"We introduce SIMCOPILOT, a benchmark that simulates the role of large language models (LLMs) as interactive, \"copilot\"-style coding assistants. Targeting both completion (finishing incomplete methods or code blocks) and infill tasks (filling missing segments within existing code), SIMCOPILOT provides a comprehensive framework for evaluating LLM coding capabilities. The benchmark comprises dedicated sub-benchmarks for Java (SIMCOPILOTJ) and Python (SIMCOPILOTP), covering diverse codebases varying in size and complexity. Our key contributions include: (a) establishing a realistic, detailed evalu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21514","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/2505.21514/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":"2505.21514","created_at":"2026-07-05T11:10:59.286416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21514v1","created_at":"2026-07-05T11:10:59.286416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21514","created_at":"2026-07-05T11:10:59.286416+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIHXEARUMKO2","created_at":"2026-07-05T11:10:59.286416+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIHXEARUMKO2QNJD","created_at":"2026-07-05T11:10:59.286416+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIHXEARU","created_at":"2026-07-05T11:10:59.286416+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/JIHXEARUMKO2QNJDIFRNUPZEWP","json":"https://pith.science/pith/JIHXEARUMKO2QNJDIFRNUPZEWP.json","graph_json":"https://pith.science/api/pith-number/JIHXEARUMKO2QNJDIFRNUPZEWP/graph.json","events_json":"https://pith.science/api/pith-number/JIHXEARUMKO2QNJDIFRNUPZEWP/events.json","paper":"https://pith.science/paper/JIHXEARU"},"agent_actions":{"view_html":"https://pith.science/pith/JIHXEARUMKO2QNJDIFRNUPZEWP","download_json":"https://pith.science/pith/JIHXEARUMKO2QNJDIFRNUPZEWP.json","view_paper":"https://pith.science/paper/JIHXEARU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21514&json=true","fetch_graph":"https://pith.science/api/pith-number/JIHXEARUMKO2QNJDIFRNUPZEWP/graph.json","fetch_events":"https://pith.science/api/pith-number/JIHXEARUMKO2QNJDIFRNUPZEWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIHXEARUMKO2QNJDIFRNUPZEWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIHXEARUMKO2QNJDIFRNUPZEWP/action/storage_attestation","attest_author":"https://pith.science/pith/JIHXEARUMKO2QNJDIFRNUPZEWP/action/author_attestation","sign_citation":"https://pith.science/pith/JIHXEARUMKO2QNJDIFRNUPZEWP/action/citation_signature","submit_replication":"https://pith.science/pith/JIHXEARUMKO2QNJDIFRNUPZEWP/action/replication_record"}},"created_at":"2026-07-05T11:10:59.286416+00:00","updated_at":"2026-07-05T11:10:59.286416+00:00"}