{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BVNPT4Z3HNXVWRZRTXYZ6MNMPN","short_pith_number":"pith:BVNPT4Z3","schema_version":"1.0","canonical_sha256":"0d5af9f33b3b6f5b47319df19f31ac7b64515d9f9e923457a82aee192157f171","source":{"kind":"arxiv","id":"2502.09328","version":1},"attestation_state":"computed","paper":{"title":"Copilot Arena: A Platform for Code LLM Evaluation in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Aditya Mittal, Ameet Talwalkar, Anastasios Nikolas Angelopoulos, Chris Donahue, Ion Stoica, Naman Jain, Tianjun Zhang, Valerie Chen, Wayne Chi, Wei-Lin Chiang","submitted_at":"2025-02-13T13:40:52Z","abstract_excerpt":"Evaluating in-the-wild coding capabilities of large language models (LLMs) is a challenging endeavor with no clear solution. We introduce Copilot Arena, a platform to collect user preferences for code generation through native integration into a developer's working environment. Copilot Arena comprises a novel interface for comparing pairs of model outputs, a sampling strategy optimized to reduce latency, and a prompting scheme to enable code completion functionality. Copilot Arena has served over 4.5 million suggestions from 10 models and collected over 11k pairwise judgements. Our results hig"},"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":"2502.09328","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-13T13:40:52Z","cross_cats_sorted":[],"title_canon_sha256":"70a35b3108f2c2a2f6ba20c8ee0709947c26993363c6a29c4721f4f0e316e4e3","abstract_canon_sha256":"920ccdc064c02e765494f76d6a9b1f6c8c26d3739a3d56b77531235804bd638d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:55.682523Z","signature_b64":"Kn8w2WTqSQmFmxdC/lzojNqYuyWTVtu0poB0iEn/OMapRQat9dBYB6kd8zDcpVchuFxgAd6Ww5SyZMrxRgh5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d5af9f33b3b6f5b47319df19f31ac7b64515d9f9e923457a82aee192157f171","last_reissued_at":"2026-07-05T10:13:55.682040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:55.682040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Copilot Arena: A Platform for Code LLM Evaluation in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Aditya Mittal, Ameet Talwalkar, Anastasios Nikolas Angelopoulos, Chris Donahue, Ion Stoica, Naman Jain, Tianjun Zhang, Valerie Chen, Wayne Chi, Wei-Lin Chiang","submitted_at":"2025-02-13T13:40:52Z","abstract_excerpt":"Evaluating in-the-wild coding capabilities of large language models (LLMs) is a challenging endeavor with no clear solution. We introduce Copilot Arena, a platform to collect user preferences for code generation through native integration into a developer's working environment. Copilot Arena comprises a novel interface for comparing pairs of model outputs, a sampling strategy optimized to reduce latency, and a prompting scheme to enable code completion functionality. Copilot Arena has served over 4.5 million suggestions from 10 models and collected over 11k pairwise judgements. Our results hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09328","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/2502.09328/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":"2502.09328","created_at":"2026-07-05T10:13:55.682089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09328v1","created_at":"2026-07-05T10:13:55.682089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09328","created_at":"2026-07-05T10:13:55.682089+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVNPT4Z3HNXV","created_at":"2026-07-05T10:13:55.682089+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVNPT4Z3HNXVWRZR","created_at":"2026-07-05T10:13:55.682089+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVNPT4Z3","created_at":"2026-07-05T10:13:55.682089+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.17298","citing_title":"Mercury: Ultra-Fast Language Models Based on Diffusion","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01104","citing_title":"RECAP: An End-to-End Platform for Capturing, Replaying, and Analyzing AI-Assisted Programming Interactions","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05100","citing_title":"Edit, But Verify: An Empirical Audit of Instructed Code-Editing Benchmarks","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVNPT4Z3HNXVWRZRTXYZ6MNMPN","json":"https://pith.science/pith/BVNPT4Z3HNXVWRZRTXYZ6MNMPN.json","graph_json":"https://pith.science/api/pith-number/BVNPT4Z3HNXVWRZRTXYZ6MNMPN/graph.json","events_json":"https://pith.science/api/pith-number/BVNPT4Z3HNXVWRZRTXYZ6MNMPN/events.json","paper":"https://pith.science/paper/BVNPT4Z3"},"agent_actions":{"view_html":"https://pith.science/pith/BVNPT4Z3HNXVWRZRTXYZ6MNMPN","download_json":"https://pith.science/pith/BVNPT4Z3HNXVWRZRTXYZ6MNMPN.json","view_paper":"https://pith.science/paper/BVNPT4Z3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09328&json=true","fetch_graph":"https://pith.science/api/pith-number/BVNPT4Z3HNXVWRZRTXYZ6MNMPN/graph.json","fetch_events":"https://pith.science/api/pith-number/BVNPT4Z3HNXVWRZRTXYZ6MNMPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVNPT4Z3HNXVWRZRTXYZ6MNMPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVNPT4Z3HNXVWRZRTXYZ6MNMPN/action/storage_attestation","attest_author":"https://pith.science/pith/BVNPT4Z3HNXVWRZRTXYZ6MNMPN/action/author_attestation","sign_citation":"https://pith.science/pith/BVNPT4Z3HNXVWRZRTXYZ6MNMPN/action/citation_signature","submit_replication":"https://pith.science/pith/BVNPT4Z3HNXVWRZRTXYZ6MNMPN/action/replication_record"}},"created_at":"2026-07-05T10:13:55.682089+00:00","updated_at":"2026-07-05T10:13:55.682089+00:00"}