PRobe / outputs /scripted_baseline.jsonl
Thakur, Mahipal
refactor: remove legacy architecture, promote clean structure to repo root
85fab7b
Raw
History Blame Contribute Delete
9.85 kB
{"agent": "keyword_spammer", "task_id": 0, "task_difficulty": "ultra-easy", "reward_total": -0.03, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.05, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "line_flooder", "task_id": 0, "task_difficulty": "ultra-easy", "reward_total": 0.02, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "perfect_oracle", "task_id": 0, "task_difficulty": "ultra-easy", "reward_total": 0.7867, "issue_reward": 0.4, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.15, "decision_score": 0.15}
{"agent": "random_agent", "task_id": 0, "task_difficulty": "ultra-easy", "reward_total": -0.23, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.1, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": -0.15}
{"agent": "keyword_spammer", "task_id": 1, "task_difficulty": "easy", "reward_total": -0.03, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.05, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "line_flooder", "task_id": 1, "task_difficulty": "easy", "reward_total": 0.02, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "perfect_oracle", "task_id": 1, "task_difficulty": "easy", "reward_total": 0.8, "issue_reward": 0.4, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.15, "decision_score": 0.15}
{"agent": "random_agent", "task_id": 1, "task_difficulty": "easy", "reward_total": -0.13, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.15, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "keyword_spammer", "task_id": 2, "task_difficulty": "medium", "reward_total": -0.03, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.05, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "line_flooder", "task_id": 2, "task_difficulty": "medium", "reward_total": 0.02, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "perfect_oracle", "task_id": 2, "task_difficulty": "medium", "reward_total": 0.7951, "issue_reward": 0.4001, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.15, "decision_score": 0.15}
{"agent": "random_agent", "task_id": 2, "task_difficulty": "medium", "reward_total": -0.38, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.25, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": -0.15}
{"agent": "keyword_spammer", "task_id": 3, "task_difficulty": "hard", "reward_total": -0.03, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.05, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "line_flooder", "task_id": 3, "task_difficulty": "hard", "reward_total": 0.02, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "perfect_oracle", "task_id": 3, "task_difficulty": "hard", "reward_total": 0.0, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.0, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "random_agent", "task_id": 3, "task_difficulty": "hard", "reward_total": -0.48, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.35, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": -0.15}
{"agent": "keyword_spammer", "task_id": 4, "task_difficulty": "medium", "reward_total": -0.03, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.05, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "line_flooder", "task_id": 4, "task_difficulty": "medium", "reward_total": 0.02, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "perfect_oracle", "task_id": 4, "task_difficulty": "medium", "reward_total": 0.795, "issue_reward": 0.4, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.15, "decision_score": 0.15}
{"agent": "random_agent", "task_id": 4, "task_difficulty": "medium", "reward_total": -0.38, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.25, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": -0.15}
{"agent": "keyword_spammer", "task_id": 5, "task_difficulty": "hard", "reward_total": -0.03, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.05, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "line_flooder", "task_id": 5, "task_difficulty": "hard", "reward_total": 0.02, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "perfect_oracle", "task_id": 5, "task_difficulty": "hard", "reward_total": 0.7998, "issue_reward": 0.3998, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.15, "decision_score": 0.15}
{"agent": "random_agent", "task_id": 5, "task_difficulty": "hard", "reward_total": -0.28, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.3, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "keyword_spammer", "task_id": 6, "task_difficulty": "hard", "reward_total": -0.03, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.05, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "line_flooder", "task_id": 6, "task_difficulty": "hard", "reward_total": 0.02, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "perfect_oracle", "task_id": 6, "task_difficulty": "hard", "reward_total": 0.8031, "issue_reward": 0.4002, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.15, "decision_score": 0.15}
{"agent": "random_agent", "task_id": 6, "task_difficulty": "hard", "reward_total": -0.28, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.3, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "keyword_spammer", "task_id": 7, "task_difficulty": "adversarial", "reward_total": -0.18, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.05, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": -0.15}
{"agent": "line_flooder", "task_id": 7, "task_difficulty": "adversarial", "reward_total": -0.13, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": -0.15}
{"agent": "perfect_oracle", "task_id": 7, "task_difficulty": "adversarial", "reward_total": 1.0, "issue_reward": 0.4, "classification_reward": 0.2, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.15, "decision_score": 0.15}
{"agent": "random_agent", "task_id": 7, "task_difficulty": "adversarial", "reward_total": -0.08, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.1, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "keyword_spammer", "task_id": 8, "task_difficulty": "adversarial", "reward_total": -0.18, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.05, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": -0.15}
{"agent": "line_flooder", "task_id": 8, "task_difficulty": "adversarial", "reward_total": -0.13, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": -0.15}
{"agent": "perfect_oracle", "task_id": 8, "task_difficulty": "adversarial", "reward_total": 1.0, "issue_reward": 0.4, "classification_reward": 0.2, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.15, "decision_score": 0.15}
{"agent": "random_agent", "task_id": 8, "task_difficulty": "adversarial", "reward_total": -0.08, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.1, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": 0.0}
{"agent": "keyword_spammer", "task_id": 9, "task_difficulty": "adversarial", "reward_total": -0.18, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.05, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": -0.15}
{"agent": "line_flooder", "task_id": 9, "task_difficulty": "adversarial", "reward_total": -0.13, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": -0.15}
{"agent": "perfect_oracle", "task_id": 9, "task_difficulty": "adversarial", "reward_total": 1.0, "issue_reward": 0.3999, "classification_reward": 0.2001, "false_positive_penalty": 0.0, "format_bonus": 0.02, "coverage_bonus": 0.15, "decision_score": 0.15}
{"agent": "random_agent", "task_id": 9, "task_difficulty": "adversarial", "reward_total": -0.28, "issue_reward": 0.0, "classification_reward": 0.0, "false_positive_penalty": -0.15, "format_bonus": 0.02, "coverage_bonus": 0.0, "decision_score": -0.15}