{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BVNPT4Z3HNXVWRZRTXYZ6MNMPN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"920ccdc064c02e765494f76d6a9b1f6c8c26d3739a3d56b77531235804bd638d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-13T13:40:52Z","title_canon_sha256":"70a35b3108f2c2a2f6ba20c8ee0709947c26993363c6a29c4721f4f0e316e4e3"},"schema_version":"1.0","source":{"id":"2502.09328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09328","created_at":"2026-07-05T10:13:55Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09328v1","created_at":"2026-07-05T10:13:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09328","created_at":"2026-07-05T10:13:55Z"},{"alias_kind":"pith_short_12","alias_value":"BVNPT4Z3HNXV","created_at":"2026-07-05T10:13:55Z"},{"alias_kind":"pith_short_16","alias_value":"BVNPT4Z3HNXVWRZR","created_at":"2026-07-05T10:13:55Z"},{"alias_kind":"pith_short_8","alias_value":"BVNPT4Z3","created_at":"2026-07-05T10:13:55Z"}],"graph_snapshots":[{"event_id":"sha256:5b0b63c8b6ee657e4f8795092b181d8d129820cf9de891e16563af61efc77740","target":"graph","created_at":"2026-07-05T10:13:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.09328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aditya Mittal, Ameet Talwalkar, Anastasios Nikolas Angelopoulos, Chris Donahue, Ion Stoica, Naman Jain, Tianjun Zhang, Valerie Chen, Wayne Chi, Wei-Lin Chiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-13T13:40:52Z","title":"Copilot Arena: A Platform for Code LLM Evaluation in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09328","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5f2968cf7ae69e2a32eea77d19b0b7a1867eefa5f3210c4d2daaf8061dc90e98","target":"record","created_at":"2026-07-05T10:13:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"920ccdc064c02e765494f76d6a9b1f6c8c26d3739a3d56b77531235804bd638d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-13T13:40:52Z","title_canon_sha256":"70a35b3108f2c2a2f6ba20c8ee0709947c26993363c6a29c4721f4f0e316e4e3"},"schema_version":"1.0","source":{"id":"2502.09328","kind":"arxiv","version":1}},"canonical_sha256":"0d5af9f33b3b6f5b47319df19f31ac7b64515d9f9e923457a82aee192157f171","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d5af9f33b3b6f5b47319df19f31ac7b64515d9f9e923457a82aee192157f171","first_computed_at":"2026-07-05T10:13:55.682040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:55.682040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kn8w2WTqSQmFmxdC/lzojNqYuyWTVtu0poB0iEn/OMapRQat9dBYB6kd8zDcpVchuFxgAd6Ww5SyZMrxRgh5BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:55.682523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f2968cf7ae69e2a32eea77d19b0b7a1867eefa5f3210c4d2daaf8061dc90e98","sha256:5b0b63c8b6ee657e4f8795092b181d8d129820cf9de891e16563af61efc77740"],"state_sha256":"c306ecafa1ba14ac1ee7c9a6279fa11e306689d862260594dbf7625fbea329f6"}