diff --git a/.gitattributes b/.gitattributes index 8f245fb5c..cdc217240 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1,3 +1,3 @@ evaluation/java/verified/20250426_MopenHands_Gemini-2.5-Pro/all_preds.jsonl filter=lfs diff=lfs merge=lfs -text +evaluation/java/verified/20260429_kozuchi-mini-swe-agent_qwen3.5-27b/all_preds.jsonl filter=lfs diff=lfs merge=lfs -text evaluation/mini/20250426_MopenHands_Gemini-2.5-Pro/all_preds.jsonl filter=lfs diff=lfs merge=lfs -text - diff --git a/evaluation/java/verified/20260429_kozuchi-mini-swe-agent_qwen3.5-27b/all_preds.jsonl b/evaluation/java/verified/20260429_kozuchi-mini-swe-agent_qwen3.5-27b/all_preds.jsonl new file mode 100644 index 000000000..cc3784ef0 --- /dev/null +++ b/evaluation/java/verified/20260429_kozuchi-mini-swe-agent_qwen3.5-27b/all_preds.jsonl @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a40fea266e9a89686a1f54cf77c2818e2357262eeef6d64a6fb00a35469bd612 +size 266489582 diff --git a/evaluation/java/verified/20260429_kozuchi-mini-swe-agent_qwen3.5-27b/metadata.yaml b/evaluation/java/verified/20260429_kozuchi-mini-swe-agent_qwen3.5-27b/metadata.yaml new file mode 100644 index 000000000..274d4b5bf --- /dev/null +++ b/evaluation/java/verified/20260429_kozuchi-mini-swe-agent_qwen3.5-27b/metadata.yaml @@ -0,0 +1,4 @@ +name: kozuchi-mini-swe-agent + qwen3.5-27b xcheck@8 +oss: false +site: https://github.com/multi-swe-bench/experiments/tree/main/evaluation/java/verified/20260429_kozuchi-mini-swe-agent_qwen3.5-27b +verified: false diff --git a/evaluation/java/verified/20260429_kozuchi-mini-swe-agent_qwen3.5-27b/results/results.json b/evaluation/java/verified/20260429_kozuchi-mini-swe-agent_qwen3.5-27b/results/results.json new file mode 100644 index 000000000..d79e597dc --- /dev/null +++ b/evaluation/java/verified/20260429_kozuchi-mini-swe-agent_qwen3.5-27b/results/results.json @@ -0,0 +1,448 @@ +{ + "total_instances": 128, + "submitted_instances": 128, + "completed_instances": 128, + "incomplete_instances": 0, + "resolved_instances": 41, + "unresolved_instances": 87, + "empty_patch_instances": 0, + "error_instances": 0, + "submitted_ids": [ + "mockito__mockito-3133", + "googlecontainertools__jib-2688", + "googlecontainertools__jib-4144", + "googlecontainertools__jib-2536", + "google__gson-1391", + "google__gson-1555", + "google__gson-1093", + "fasterxml__jackson-dataformat-xml-638", + "fasterxml__jackson-databind-4641", + "fasterxml__jackson-databind-4469", + "fasterxml__jackson-databind-4338", + "fasterxml__jackson-databind-4486", + "fasterxml__jackson-databind-4426", + "fasterxml__jackson-databind-4311", + "fasterxml__jackson-databind-4230", + "fasterxml__jackson-databind-4189", + "fasterxml__jackson-databind-4320", + "fasterxml__jackson-databind-4304", + "fasterxml__jackson-databind-4219", + "fasterxml__jackson-databind-4015", + "fasterxml__jackson-databind-4048", + "fasterxml__jackson-databind-3851", + "fasterxml__jackson-databind-3860", + "fasterxml__jackson-databind-4072", + "fasterxml__jackson-databind-4050", + "fasterxml__jackson-databind-3701", + "fasterxml__jackson-databind-3625", + "fasterxml__jackson-databind-1923", + "fasterxml__jackson-core-1263", + "fasterxml__jackson-core-1208", + "fasterxml__jackson-core-1142", + "fasterxml__jackson-core-1053", + "fasterxml__jackson-core-964", + "fasterxml__jackson-core-891", + "fasterxml__jackson-core-183", + "fasterxml__jackson-core-370", + "apache__dubbo-10638", + "alibaba__fastjson2-82", + "alibaba__fastjson2-2559", + "alibaba__fastjson2-2285", + "alibaba__fastjson2-2775", + "mockito__mockito-3424", + "mockito__mockito-3129", + "mockito__mockito-3220", + "mockito__mockito-3173", + "mockito__mockito-3167", + "googlecontainertools__jib-4035", + "google__gson-1787", + "googlecontainertools__jib-2542", + "google__gson-1703", + "fasterxml__jackson-dataformat-xml-644", + "fasterxml__jackson-dataformat-xml-590", + "fasterxml__jackson-dataformat-xml-531", + "fasterxml__jackson-dataformat-xml-544", + "fasterxml__jackson-databind-4487", + "fasterxml__jackson-databind-4615", + "fasterxml__jackson-databind-4468", + "fasterxml__jackson-databind-4325", + "fasterxml__jackson-databind-4365", + "fasterxml__jackson-databind-4360", + "fasterxml__jackson-databind-4228", + "fasterxml__jackson-databind-4257", + "fasterxml__jackson-databind-4132", + "fasterxml__jackson-databind-4186", + "fasterxml__jackson-databind-4131", + "fasterxml__jackson-databind-4159", + "fasterxml__jackson-databind-4013", + "fasterxml__jackson-databind-4087", + "fasterxml__jackson-databind-3621", + "fasterxml__jackson-databind-3716", + "fasterxml__jackson-databind-2036", + "fasterxml__jackson-databind-3560", + "fasterxml__jackson-databind-3666", + "fasterxml__jackson-databind-3626", + "fasterxml__jackson-databind-3509", + "fasterxml__jackson-databind-3371", + "fasterxml__jackson-core-1309", + "fasterxml__jackson-core-1204", + "fasterxml__jackson-core-1182", + "fasterxml__jackson-core-922", + "fasterxml__jackson-core-980", + "fasterxml__jackson-core-1016", + "fasterxml__jackson-core-1172", + "fasterxml__jackson-core-566", + "fasterxml__jackson-core-729", + "fasterxml__jackson-core-174", + "elastic__logstash-17021", + "elastic__logstash-17020", + "elastic__logstash-16195", + "elastic__logstash-17019", + "elastic__logstash-16569", + "elastic__logstash-16579", + "elastic__logstash-16681", + "elastic__logstash-16968", + "elastic__logstash-16079", + "elastic__logstash-16482", + "elastic__logstash-15241", + "elastic__logstash-16094", + "elastic__logstash-15928", + "elastic__logstash-15697", + "elastic__logstash-15680", + "elastic__logstash-15969", + "elastic__logstash-15925", + "elastic__logstash-15964", + "elastic__logstash-15000", + "elastic__logstash-15008", + "elastic__logstash-15233", + "elastic__logstash-14898", + "elastic__logstash-14897", + "elastic__logstash-14027", + "elastic__logstash-14571", + "elastic__logstash-14058", + "elastic__logstash-14878", + "elastic__logstash-14045", + "elastic__logstash-14970", + "elastic__logstash-14000", + "elastic__logstash-14981", + "elastic__logstash-13931", + "elastic__logstash-13997", + "elastic__logstash-13914", + "elastic__logstash-13930", + "elastic__logstash-13902", + "elastic__logstash-13880", + "elastic__logstash-13825", + "apache__dubbo-11781", + "apache__dubbo-7041", + "alibaba__fastjson2-1245", + "alibaba__fastjson2-2097" + ], + "completed_ids": [ + "mockito__mockito-3133", + "googlecontainertools__jib-2688", + "googlecontainertools__jib-4144", + "googlecontainertools__jib-2536", + "google__gson-1391", + "google__gson-1555", + "google__gson-1093", + "fasterxml__jackson-dataformat-xml-638", + "fasterxml__jackson-databind-4641", + "fasterxml__jackson-databind-4469", + "fasterxml__jackson-databind-4338", + "fasterxml__jackson-databind-4486", + "fasterxml__jackson-databind-4426", + "fasterxml__jackson-databind-4311", + "fasterxml__jackson-databind-4230", + "fasterxml__jackson-databind-4189", + "fasterxml__jackson-databind-4320", + "fasterxml__jackson-databind-4304", + "fasterxml__jackson-databind-4219", + "fasterxml__jackson-databind-4015", + "fasterxml__jackson-databind-4048", + "fasterxml__jackson-databind-3851", + "fasterxml__jackson-databind-3860", + "fasterxml__jackson-databind-4072", + "fasterxml__jackson-databind-4050", + "fasterxml__jackson-databind-3701", + "fasterxml__jackson-databind-3625", + "fasterxml__jackson-databind-1923", + "fasterxml__jackson-core-1263", + "fasterxml__jackson-core-1208", + "fasterxml__jackson-core-1142", + "fasterxml__jackson-core-1053", + "fasterxml__jackson-core-964", + "fasterxml__jackson-core-891", + "fasterxml__jackson-core-183", + "fasterxml__jackson-core-370", + "apache__dubbo-10638", + "alibaba__fastjson2-82", + "alibaba__fastjson2-2559", + "alibaba__fastjson2-2285", + "alibaba__fastjson2-2775", + "mockito__mockito-3424", + "mockito__mockito-3129", + "mockito__mockito-3220", + "mockito__mockito-3173", + "mockito__mockito-3167", + "googlecontainertools__jib-4035", + "google__gson-1787", + "googlecontainertools__jib-2542", + "google__gson-1703", + "fasterxml__jackson-dataformat-xml-644", + "fasterxml__jackson-dataformat-xml-590", + "fasterxml__jackson-dataformat-xml-531", + "fasterxml__jackson-dataformat-xml-544", + "fasterxml__jackson-databind-4487", + "fasterxml__jackson-databind-4615", + "fasterxml__jackson-databind-4468", + "fasterxml__jackson-databind-4325", + "fasterxml__jackson-databind-4365", + "fasterxml__jackson-databind-4360", + "fasterxml__jackson-databind-4228", + "fasterxml__jackson-databind-4257", + "fasterxml__jackson-databind-4132", + "fasterxml__jackson-databind-4186", + "fasterxml__jackson-databind-4131", + "fasterxml__jackson-databind-4159", + "fasterxml__jackson-databind-4013", + "fasterxml__jackson-databind-4087", + "fasterxml__jackson-databind-3621", + "fasterxml__jackson-databind-3716", + "fasterxml__jackson-databind-2036", + "fasterxml__jackson-databind-3560", + "fasterxml__jackson-databind-3666", + "fasterxml__jackson-databind-3626", + "fasterxml__jackson-databind-3509", + "fasterxml__jackson-databind-3371", + "fasterxml__jackson-core-1309", + "fasterxml__jackson-core-1204", + "fasterxml__jackson-core-1182", + "fasterxml__jackson-core-922", + "fasterxml__jackson-core-980", + "fasterxml__jackson-core-1016", + "fasterxml__jackson-core-1172", + "fasterxml__jackson-core-566", + "fasterxml__jackson-core-729", + "fasterxml__jackson-core-174", + "elastic__logstash-17021", + "elastic__logstash-17020", + "elastic__logstash-16195", + "elastic__logstash-17019", + "elastic__logstash-16569", + "elastic__logstash-16579", + "elastic__logstash-16681", + "elastic__logstash-16968", + "elastic__logstash-16079", + "elastic__logstash-16482", + "elastic__logstash-15241", + "elastic__logstash-16094", + "elastic__logstash-15928", + "elastic__logstash-15697", + "elastic__logstash-15680", + "elastic__logstash-15969", + "elastic__logstash-15925", + "elastic__logstash-15964", + "elastic__logstash-15000", + "elastic__logstash-15008", + "elastic__logstash-15233", + "elastic__logstash-14898", + "elastic__logstash-14897", + "elastic__logstash-14027", + "elastic__logstash-14571", + "elastic__logstash-14058", + "elastic__logstash-14878", + "elastic__logstash-14045", + "elastic__logstash-14970", + "elastic__logstash-14000", + "elastic__logstash-14981", + "elastic__logstash-13931", + "elastic__logstash-13997", + "elastic__logstash-13914", + "elastic__logstash-13930", + "elastic__logstash-13902", + "elastic__logstash-13880", + "elastic__logstash-13825", + "apache__dubbo-11781", + "apache__dubbo-7041", + "alibaba__fastjson2-1245", + "alibaba__fastjson2-2097" + ], + "incomplete_ids": [], + "resolved": [ + "mockito__mockito-3133", + "googlecontainertools__jib-2688", + "googlecontainertools__jib-4144", + "googlecontainertools__jib-2536", + "google__gson-1391", + "google__gson-1555", + "google__gson-1093", + "fasterxml__jackson-dataformat-xml-638", + "fasterxml__jackson-databind-4641", + "fasterxml__jackson-databind-4469", + "fasterxml__jackson-databind-4338", + "fasterxml__jackson-databind-4486", + "fasterxml__jackson-databind-4426", + "fasterxml__jackson-databind-4311", + "fasterxml__jackson-databind-4230", + "fasterxml__jackson-databind-4189", + "fasterxml__jackson-databind-4320", + "fasterxml__jackson-databind-4304", + "fasterxml__jackson-databind-4219", + "fasterxml__jackson-databind-4015", + "fasterxml__jackson-databind-4048", + "fasterxml__jackson-databind-3851", + "fasterxml__jackson-databind-3860", + "fasterxml__jackson-databind-4072", + "fasterxml__jackson-databind-4050", + "fasterxml__jackson-databind-3701", + "fasterxml__jackson-databind-3625", + "fasterxml__jackson-databind-1923", + "fasterxml__jackson-core-1263", + "fasterxml__jackson-core-1208", + "fasterxml__jackson-core-1142", + "fasterxml__jackson-core-1053", + "fasterxml__jackson-core-964", + "fasterxml__jackson-core-891", + "fasterxml__jackson-core-183", + "fasterxml__jackson-core-370", + "apache__dubbo-10638", + "alibaba__fastjson2-82", + "alibaba__fastjson2-2559", + "alibaba__fastjson2-2285", + "alibaba__fastjson2-2775" + ], + "resolved_ids": [ + "mockito__mockito-3133", + "googlecontainertools__jib-2688", + "googlecontainertools__jib-4144", + "googlecontainertools__jib-2536", + "google__gson-1391", + "google__gson-1555", + "google__gson-1093", + "fasterxml__jackson-dataformat-xml-638", + "fasterxml__jackson-databind-4641", + "fasterxml__jackson-databind-4469", + "fasterxml__jackson-databind-4338", + "fasterxml__jackson-databind-4486", + "fasterxml__jackson-databind-4426", + "fasterxml__jackson-databind-4311", + "fasterxml__jackson-databind-4230", + "fasterxml__jackson-databind-4189", + "fasterxml__jackson-databind-4320", + "fasterxml__jackson-databind-4304", + "fasterxml__jackson-databind-4219", + "fasterxml__jackson-databind-4015", + "fasterxml__jackson-databind-4048", + "fasterxml__jackson-databind-3851", + "fasterxml__jackson-databind-3860", + "fasterxml__jackson-databind-4072", + "fasterxml__jackson-databind-4050", + "fasterxml__jackson-databind-3701", + "fasterxml__jackson-databind-3625", + "fasterxml__jackson-databind-1923", + "fasterxml__jackson-core-1263", + "fasterxml__jackson-core-1208", + "fasterxml__jackson-core-1142", + "fasterxml__jackson-core-1053", + "fasterxml__jackson-core-964", + "fasterxml__jackson-core-891", + "fasterxml__jackson-core-183", + "fasterxml__jackson-core-370", + "apache__dubbo-10638", + "alibaba__fastjson2-82", + "alibaba__fastjson2-2559", + "alibaba__fastjson2-2285", + "alibaba__fastjson2-2775" + ], + "unresolved_ids": [ + "mockito__mockito-3424", + "mockito__mockito-3129", + "mockito__mockito-3220", + "mockito__mockito-3173", + "mockito__mockito-3167", + "googlecontainertools__jib-4035", + "google__gson-1787", + "googlecontainertools__jib-2542", + "google__gson-1703", + "fasterxml__jackson-dataformat-xml-644", + "fasterxml__jackson-dataformat-xml-590", + "fasterxml__jackson-dataformat-xml-531", + "fasterxml__jackson-dataformat-xml-544", + "fasterxml__jackson-databind-4487", + "fasterxml__jackson-databind-4615", + "fasterxml__jackson-databind-4468", + "fasterxml__jackson-databind-4325", + "fasterxml__jackson-databind-4365", + "fasterxml__jackson-databind-4360", + "fasterxml__jackson-databind-4228", + "fasterxml__jackson-databind-4257", + "fasterxml__jackson-databind-4132", + "fasterxml__jackson-databind-4186", + "fasterxml__jackson-databind-4131", + "fasterxml__jackson-databind-4159", + "fasterxml__jackson-databind-4013", + "fasterxml__jackson-databind-4087", + "fasterxml__jackson-databind-3621", + "fasterxml__jackson-databind-3716", + "fasterxml__jackson-databind-2036", + "fasterxml__jackson-databind-3560", + "fasterxml__jackson-databind-3666", + "fasterxml__jackson-databind-3626", + "fasterxml__jackson-databind-3509", + "fasterxml__jackson-databind-3371", + "fasterxml__jackson-core-1309", + "fasterxml__jackson-core-1204", + "fasterxml__jackson-core-1182", + "fasterxml__jackson-core-922", + "fasterxml__jackson-core-980", + "fasterxml__jackson-core-1016", + "fasterxml__jackson-core-1172", + "fasterxml__jackson-core-566", + "fasterxml__jackson-core-729", + "fasterxml__jackson-core-174", + "elastic__logstash-17021", + "elastic__logstash-17020", + "elastic__logstash-16195", + "elastic__logstash-17019", + "elastic__logstash-16569", + "elastic__logstash-16579", + "elastic__logstash-16681", + "elastic__logstash-16968", + "elastic__logstash-16079", + "elastic__logstash-16482", + "elastic__logstash-15241", + "elastic__logstash-16094", + "elastic__logstash-15928", + "elastic__logstash-15697", + "elastic__logstash-15680", + "elastic__logstash-15969", + "elastic__logstash-15925", + "elastic__logstash-15964", + "elastic__logstash-15000", + "elastic__logstash-15008", + "elastic__logstash-15233", + "elastic__logstash-14898", + "elastic__logstash-14897", + "elastic__logstash-14027", + "elastic__logstash-14571", + "elastic__logstash-14058", + "elastic__logstash-14878", + "elastic__logstash-14045", + "elastic__logstash-14970", + "elastic__logstash-14000", + "elastic__logstash-14981", + "elastic__logstash-13931", + "elastic__logstash-13997", + "elastic__logstash-13914", + "elastic__logstash-13930", + "elastic__logstash-13902", + "elastic__logstash-13880", + "elastic__logstash-13825", + "apache__dubbo-11781", + "apache__dubbo-7041", + "alibaba__fastjson2-1245", + "alibaba__fastjson2-2097" + ], + "empty_patch_ids": [], + "error_ids": [] +}