actava-ai · ZhongZhi-Qiang · Sep 3, 2026
diff --git a/benchmarks/chi-bench/submissions/2026-09-03-u2med-u2medfellow-zzq/README.md b/benchmarks/chi-bench/submissions/2026-09-03-u2med-u2medfellow-zzq/README.md
@@ -0,0 +1,22 @@
+# chi-Bench submission
+
+- Submission ID: `u2med-u2medfellow-zzq`
+- Agent: `U2MedFellow`
+- Model: `U2Med`
+- Dataset: `chi-bench-v1.0.0`
+- Submitted at: `2026-09-03T03:01:09Z`
+
+## Results
+
+| Domain | Pass@1 | Trials | Tasks |
+|---|---:|---:|---:|
+| Overall | 0.586667 | 75 | 75 |
+| PA Provider | 0.520000 | 25 | 25 |
+| PA UM | 0.520000 | 25 | 25 |
+| CM | 0.720000 | 25 | 25 |
+
+## Selection
+
+The packet integrates the results for all three benchmark domains in the current submission directory.
+
+The packet uses the public identity `model=U2Med`, `agent=U2MedFellow`. Trial evidence and benchmark results are included in the submission packet.
diff --git a/benchmarks/chi-bench/submissions/2026-09-03-u2med-u2medfellow-zzq/provenance.json b/benchmarks/chi-bench/submissions/2026-09-03-u2med-u2medfellow-zzq/provenance.json
@@ -0,0 +1,9 @@
+{
+  "chi_bench_git_sha": null,
+  "image_digest": null,
+  "judge_model": "claude-opus-4-7",
+  "harness_version": "0.1.0",
+  "selection": {
+    "description": "Integrated results for all three benchmark domains in the current submission directory."
+  }
+}
diff --git a/benchmarks/chi-bench/submissions/2026-09-03-u2med-u2medfellow-zzq/results.csv b/benchmarks/chi-bench/submissions/2026-09-03-u2med-u2medfellow-zzq/results.csv
@@ -0,0 +1,5 @@
+benchmark,dataset_version,submission_id,team,agent,model,domain,pass_at_1,n_trials,n_tasks,mean_cost_usd,mean_walltime_s,submitted_at
+chi-bench,chi-bench-v1.0.0,u2med-u2medfellow-zzq,U2Med,U2MedFellow,U2Med,overall,0.5866666666666667,75,75,0.0,0.0,2026-09-03T03:01:09Z
+chi-bench,chi-bench-v1.0.0,u2med-u2medfellow-zzq,U2Med,U2MedFellow,U2Med,pa_provider,0.52,25,25,0.0,0.0,2026-09-03T03:01:09Z
+chi-bench,chi-bench-v1.0.0,u2med-u2medfellow-zzq,U2Med,U2MedFellow,U2Med,pa_um,0.52,25,25,0.0,0.0,2026-09-03T03:01:09Z
+chi-bench,chi-bench-v1.0.0,u2med-u2medfellow-zzq,U2Med,U2MedFellow,U2Med,cm,0.72,25,25,0.0,0.0,2026-09-03T03:01:09Z
diff --git a/benchmarks/chi-bench/submissions/2026-09-03-u2med-u2medfellow-zzq/sub.yaml b/benchmarks/chi-bench/submissions/2026-09-03-u2med-u2medfellow-zzq/sub.yaml
@@ -0,0 +1,29 @@
+schema: chi-bench/submission/v1
+
+submission:
+  id: u2med-u2medfellow-zzq
+  team: U2Med
+  contact: zhongzhiqiang-intern@example.com
+  agent: U2MedFellow
+  model: U2Med
+  notes: |
+    Leaderboard packet integrates the results for all three benchmark domains
+    in the current submission directory. The public leaderboard identity is
+    model U2Med with agent U2MedFellow. Trial evidence and benchmark results
+    are included in the submission packet.
+
+run:
+  environment: docker
+  n_attempts: 1
+  concurrency: 4
+  max_retries: 0
+  timeout_multiplier: 2.0
+  env_file: .env
+
+dataset:
+  version: chi-bench-v1.0.0
+  domains: [pa_provider, pa_um, cm]
+
+paths:
+  data_root: data
+  output_root: logs/submissions/2026-09-03-u2med-u2medfellow-zzq
diff --git a/benchmarks/chi-bench/submissions/2026-09-03-u2med-u2medfellow-zzq/submission.json b/benchmarks/chi-bench/submissions/2026-09-03-u2med-u2medfellow-zzq/submission.json
@@ -0,0 +1,64 @@
+{
+  "schema": "chi-bench/submission/v1",
+  "submission": {
+    "id": "u2med-u2medfellow-zzq",
+    "team": "U2Med",
+    "contact": "zhongzhiqiang-intern@example.com",
+    "agent": "U2MedFellow",
+    "model": "U2Med",
+    "notes": "Leaderboard packet integrates the results for all three benchmark domains in the current submission directory. The leaderboard identity is model U2Med with agent U2MedFellow. Trial evidence and benchmark results are included in the submission packet.",
+    "submitted_at": "2026-09-03T03:01:09Z"
+  },
+  "dataset": {
+    "name": "chi-bench",
+    "version": "chi-bench-v1.0.0",
+    "domains": [
+      "pa_provider",
+      "pa_um",
+      "cm"
+    ]
+  },
+  "results": {
+    "overall": {
+      "pass_at_1": 0.5866666666666667,
+      "n_trials": 75,
+      "n_tasks": 75,
+      "mean_cost_usd": 0.0,
+      "mean_walltime_s": 0.0
+    },
+    "per_domain": {
+      "pa_provider": {
+        "pass_at_1": 0.52,
+        "n_trials": 25,
+        "n_tasks": 25,
+        "mean_cost_usd": 0.0,
+        "mean_walltime_s": 0.0
+      },
+      "pa_um": {
+        "pass_at_1": 0.52,
+        "n_trials": 25,
+        "n_tasks": 25,
+        "mean_cost_usd": 0.0,
+        "mean_walltime_s": 0.0
+      },
+      "cm": {
+        "pass_at_1": 0.72,
+        "n_trials": 25,
+        "n_tasks": 25,
+        "mean_cost_usd": 0.0,
+        "mean_walltime_s": 0.0
+      }
+    },
+    "mean_cost_usd": 0.0,
+    "mean_walltime_s": 0.0
+  },
+  "provenance": {
+    "chi_bench_git_sha": null,
+    "image_digest": null,
+    "judge_model": "claude-opus-4-7",
+    "harness_version": "0.1.0",
+    "selection": {
+      "description": "Integrated results for all three benchmark domains in the current submission directory."
+    }
+  }
+}
diff --git a/...2medfellow-zzq/trials/cm/cm_afib_moderate_anxious_001__SEG6EVC/agent/trajectory.jsonl.zst b/...2medfellow-zzq/trials/cm/cm_afib_moderate_anxious_001__SEG6EVC/agent/trajectory.jsonl.zst
diff --git a/...6-09-03-u2med-u2medfellow-zzq/trials/cm/cm_afib_moderate_anxious_001__SEG6EVC/result.json b/...6-09-03-u2med-u2medfellow-zzq/trials/cm/cm_afib_moderate_anxious_001__SEG6EVC/result.json
@@ -0,0 +1,103 @@
+{
+    "id": "29bb92f3-097e-4834-abd2-489db18d1cf0",
+    "task_name": "actava-ai/cm_afib_moderate_anxious_001",
+    "trial_name": "cm_afib_moderate_anxious_001__SEG6EVC",
+    "trial_uri": "trials/cm/cm_afib_moderate_anxious_001__SEG6EVC",
+    "task_id": {
+        "path": "data/care_management/tasks/cm_afib_moderate_anxious_001"
+    },
+    "source": null,
+    "task_checksum": "a43c14fadec72f11c1de9af6ee038fd27d3c453ce78dd9de56d454e395e33846",
+    "config": {
+        "task": {
+            "path": "data/care_management/tasks/cm_afib_moderate_anxious_001",
+            "git_url": null,
+            "git_commit_id": null,
+            "name": null,
+            "ref": null,
+            "overwrite": false,
+            "download_dir": null,
+            "source": null
+        },
+        "trial_name": "cm_afib_moderate_anxious_001__SEG6EVC",
+        "trials_dir": "trials/cm",
+        "timeout_multiplier": 2.0,
+        "agent_timeout_multiplier": null,
+        "verifier_timeout_multiplier": null,
+        "agent_setup_timeout_multiplier": null,
+        "environment_build_timeout_multiplier": null,
+        "agent": {
+            "name": null,
+            "import_path": "chi_bench.experiment.agents.hermes_harness:HermesHarness",
+            "model_name": "openai/qwen3.5_27b_sft_0609",
+            "override_timeout_sec": null,
+            "override_setup_timeout_sec": null,
+            "max_timeout_sec": null,
+            "kwargs": {},
+            "env": {}
+        },
+        "environment": {
+            "type": null,
+            "import_path": "chi_bench.experiment.docker_env:ChiBenchDockerEnvironment",
+            "force_build": false,
+            "delete": true,
+            "override_cpus": null,
+            "override_memory_mb": null,
+            "override_storage_mb": null,
+            "override_gpus": null,
+            "suppress_override_warnings": false,
+            "mounts_json": null,
+            "env": {},
+            "kwargs": {}
+        },
+        "verifier": {
+            "override_timeout_sec": null,
+            "max_timeout_sec": null,
+            "env": {},
+            "disable": false
+        },
+        "artifacts": [],
+        "job_id": "c1dd117d-2a24-4340-8cac-98389c0ed26d"
+    },
+    "agent_info": {
+        "name": "hermes",
+        "version": "Hermes Agent v0.17.0 (2026.6.19)\nProject: /usr/local/lib/hermes-agent/venv/lib/python3.12/site-packages\nPython: 3.12.13\nOpenAI SDK: 2.24.0\nUpdate available: 1 commit behind — run 'uv pip install --upgrade hermes-agent'",
+        "model_info": {
+            "name": "qwen3.5_27b_sft_0609",
+            "provider": "openai"
+        }
+    },
+    "agent_result": {
+        "n_input_tokens": 0,
+        "n_cache_tokens": null,
+        "n_output_tokens": 0,
+        "cost_usd": null,
+        "rollout_details": null,
+        "metadata": null
+    },
+    "verifier_result": {
+        "rewards": {
+            "reward": 0.0
+        }
+    },
+    "exception_info": null,
+    "started_at": "2026-07-19T05:48:38.555475Z",
+    "finished_at": "2026-07-19T05:50:18.690223Z",
+    "environment_setup": {
+        "started_at": "2026-07-19T05:48:38.625730Z",
+        "finished_at": "2026-07-19T05:48:48.683974Z"
+    },
+    "agent_setup": {
+        "started_at": "2026-07-19T05:48:48.683988Z",
+        "finished_at": "2026-07-19T05:48:52.754655Z"
+    },
+    "agent_execution": {
+        "started_at": "2026-07-19T05:48:52.754737Z",
+        "finished_at": "2026-07-19T05:50:14.897896Z"
+    },
+    "verifier": {
+        "started_at": "2026-07-19T05:50:15.296800Z",
+        "finished_at": "2026-07-19T05:50:18.353967Z"
+    },
+    "step_results": null
+}
diff --git a/...2med-u2medfellow-zzq/trials/cm/cm_afib_moderate_anxious_001__SEG6EVC/verifier/reward.json b/...2med-u2medfellow-zzq/trials/cm/cm_afib_moderate_anxious_001__SEG6EVC/verifier/reward.json
@@ -0,0 +1 @@
+{"reward": 0.0}
diff --git a/...d-u2medfellow-zzq/trials/cm/cm_afib_moderate_anxious_001__SEG6EVC/verifier/scorecard.json b/...d-u2medfellow-zzq/trials/cm/cm_afib_moderate_anxious_001__SEG6EVC/verifier/scorecard.json
@@ -0,0 +1,132 @@
+{
+  "binary_reward": 0.0,
+  "fractional_reward": 0.3333333333333333,
+  "passed_checks": 2,
+  "total_checks": 6,
+  "check_scores": {
+    "cm.assessment.record_exists": 0.0,
+    "cm.assessment.completed": null,
+    "cm.assessment.required_sections_present": null,
+    "cm.care_plan.record_exists": 0.0,
+    "cm.care_plan.finalized": null,
+    "cm.care_plan.problem_count": null,
+    "cm.care_plan.goal_structure": null,
+    "cm.care_plan.intervention_structure": null,
+    "cm.care_plan.escalation_conditions_present": null,
+    "cm.care_plan.follow_up_cadence_present": null,
+    "cm.chart_review.record_exists": 1.0,
+    "cm.cross_stage.target_status": 0.0,
+    "cm.cross_stage.audit_actions": 0.0,
+    "cm.cross_stage.no_forbidden_mutations": 1.0,
+    "judge.cm.chart_review.quality": null,
+    "judge.cm.outreach.quality": null,
+    "judge.cm.assessment.quality": null,
+    "judge.cm.care_plan.quality": null,
+    "judge.cm.stage_coherence": null
+  },
+  "checks": {
+    "cm.assessment.record_exists": false,
+    "cm.assessment.completed": "not_applicable",
+    "cm.assessment.required_sections_present": "not_applicable",
+    "cm.care_plan.record_exists": false,
+    "cm.care_plan.finalized": "not_applicable",
+    "cm.care_plan.problem_count": "not_applicable",
+    "cm.care_plan.goal_structure": "not_applicable",
+    "cm.care_plan.intervention_structure": "not_applicable",
+    "cm.care_plan.escalation_conditions_present": "not_applicable",
+    "cm.care_plan.follow_up_cadence_present": "not_applicable",
+    "cm.chart_review.record_exists": true,
+    "cm.cross_stage.target_status": false,
+    "cm.cross_stage.audit_actions": false,
+    "cm.cross_stage.no_forbidden_mutations": true,
+    "judge.cm.chart_review.quality": "not_applicable",
+    "judge.cm.outreach.quality": "not_applicable",
+    "judge.cm.assessment.quality": "not_applicable",
+    "judge.cm.care_plan.quality": "not_applicable",
+    "judge.cm.stage_coherence": "not_applicable"
+  },
+  "failed_checks": [
+    "cm.assessment.record_exists",
+    "cm.care_plan.record_exists",
+    "cm.cross_stage.target_status",
+    "cm.cross_stage.audit_actions"
+  ],
+  "not_applicable_checks": [
+    "cm.assessment.completed",
+    "cm.assessment.required_sections_present",
+    "cm.care_plan.finalized",
+    "cm.care_plan.problem_count",
+    "cm.care_plan.goal_structure",
+    "cm.care_plan.intervention_structure",
+    "cm.care_plan.escalation_conditions_present",
+    "cm.care_plan.follow_up_cadence_present",
+    "judge.cm.chart_review.quality",
+    "judge.cm.outreach.quality",
+    "judge.cm.assessment.quality",
+    "judge.cm.care_plan.quality",
+    "judge.cm.stage_coherence"
+  ],
+  "stages": {
+    "cm_assessment": {
+      "passed": false,
+      "checks": {
+        "cm.assessment.record_exists": false,
+        "cm.assessment.completed": "not_applicable",
+        "cm.assessment.required_sections_present": "not_applicable"
+      },
+      "passed_count": 0,
+      "total_count": 1,
+      "not_applicable_count": 2,
+      "details": {
+        "case_id": "CM-CASE-CM_AFIB_MODERATE_ANXIOUS_001",
+        "record_count": 0
+      }
+    },
+    "cm_care_plan": {
+      "passed": false,
+      "checks": {
+        "cm.care_plan.record_exists": false,
+        "cm.care_plan.finalized": "not_applicable",
+        "cm.care_plan.problem_count": "not_applicable",
+        "cm.care_plan.goal_structure": "not_applicable",
+        "cm.care_plan.intervention_structure": "not_applicable",
+        "cm.care_plan.escalation_conditions_present": "not_applicable",
+        "cm.care_plan.follow_up_cadence_present": "not_applicable"
+      },
+      "passed_count": 0,
+      "total_count": 1,
+      "not_applicable_count": 6,
+      "details": {
+        "case_id": "CM-CASE-CM_AFIB_MODERATE_ANXIOUS_001",
+        "record_count": 0
+      }
+    },
+    "cm_chart_review": {
+      "passed": true,
+      "checks": {
+        "cm.chart_review.record_exists": true
+      },
+      "passed_count": 1,
+      "total_count": 1,
+      "not_applicable_count": 0,
+      "details": {
+        "case_id": "CM-CASE-CM_AFIB_MODERATE_ANXIOUS_001",
+        "record_count": 1
+      }
+    },
+    "cm_cross_stage": {
+      "passed": false,
+      "checks": {
+        "cm.cross_stage.target_status": false,
+        "cm.cross_stage.audit_actions": false,
+        "cm.cross_stage.no_forbidden_mutations": true
+      },
+      "passed_count": 1,
+      "total_count": 3,
+      "not_applicable_count": 0,
+      "details": {
+        "case_id": "CM-CASE-CM_AFIB_MODERATE_ANXIOUS_001"
+      }
+    }
+  }
+}
diff --git a/...2medfellow-zzq/trials/cm/cm_anorexia_hard_refuses_001__jmsB7HL/agent/trajectory.jsonl.zst b/...2medfellow-zzq/trials/cm/cm_anorexia_hard_refuses_001__jmsB7HL/agent/trajectory.jsonl.zst