{"schema":"https://assignee.net/schemas/benchmark-evidence-v1","schema_version":"1.0","contract_version":"benchmark-evidence-v1.0","contract_updated":"2026-06-01","schema_documentation":"https://assignee.net/schemas","changelog_url":"https://assignee.net/changelog","publisher":{"name":"Assignee Research","url":"https://assignee.net"},"html_url":"https://assignee.net/benchmarks/evidence?model=GPT-4&bench=SWE-bench","json_url":"https://assignee.net/benchmarks/evidence.json?model=GPT-4&bench=SWE-bench","model":"GPT-4","benchmark":"SWE-bench","source_count":2,"source_coverage":{"record_count":2,"distinct_source_count":2,"coverage_level":"LIMITED","basis":"distinct public paper URLs or titles in this evidence cluster"},"source_profile":{"source_url_count":2,"missing_source_url_count":0,"domains":["arxiv.org"],"year_min":2025,"year_max":2026,"basis":"public source URLs, source titles, and reported publication years in this evidence cluster"},"reported_range":{"min_score_pct":72.0,"max_score_pct":78.8},"spread_pp":6.8,"severity":"MEDIUM","entries":[{"model":"GPT-4","benchmark":"SWE-bench","score_pct":78.8,"source_title":"SWE-ABS: Adversarial Benchmark Strengthening Exposes Inflated Success Rates on Test-based Benchmark","source_url":"http://arxiv.org/abs/2603.00520v1","source_domain":"arxiv.org","year":2026},{"model":"GPT-4","benchmark":"SWE-bench","score_pct":72.0,"source_title":"SWE-bench Goes Live!","source_url":"http://arxiv.org/abs/2505.23419v2","source_domain":"arxiv.org","year":2025}],"interpretation":"This record groups score claims extracted from papers for the same model and benchmark label. A nonzero spread means the public literature reports different values for this cluster.","limitations":["Differences are not automatically errors.","Reported values may differ because of prompts, dataset versions, evaluation protocols, scoring rules, preprocessing, fine-tuning, or reporting conventions.","Source papers remain authoritative for their own claims."]}