{
  "paper_id": "QP-SYS-001",
  "snapshot_date": "2026-10-23",
  "label_source": "prior_weak_supervision_plus_explicit_codex_ai_review_not_human_gold",
  "development_validation_not_untouched_test": true,
  "private_questions_included": false,
  "data_preparation": {
    "review": {
      "reviewed_questions": 361,
      "accepted_questions": 218,
      "rejected_questions": 143,
      "new_seed_representatives": 144,
      "accepted_split_counts": {
        "train": 163,
        "holdout": 55
      },
      "accepted_domain_counts": {
        "lost_found": 7,
        "career": 71,
        "relationship": 61,
        "finance": 5,
        "health": 2,
        "study": 50,
        "general": 13,
        "children": 1,
        "family": 4,
        "business": 1,
        "marriage": 1,
        "travel": 1,
        "migration": 1
      },
      "rejection_reasons": {
        "unintelligible_or_numeric_input": 21,
        "insufficient_context_or_multi_intent_needs_split": 53,
        "diagnostic_or_test_input": 27,
        "unsupported_factual_or_unmapped_intent": 19,
        "sports_domain_not_in_active_ontology": 15,
        "identity_context_quarantined": 8
      },
      "prior_holdout_preserved": true,
      "label_source": "prior_weak_supervision_plus_explicit_codex_ai_review_not_human_gold"
    },
    "positive_seed_policy": {
      "domain_seed_representatives": 93,
      "skipped_training_representatives": {
        "no_explicit_domain_anchor": 47,
        "too_little_context_after_redaction": 4
      },
      "domain_counts": {
        "lost_found": 4,
        "relationship": 19,
        "finance": 4,
        "career": 31,
        "study": 29,
        "general": 3,
        "children": 1,
        "marriage": 1,
        "migration": 1
      },
      "review_labels_unchanged": true,
      "holdout_unchanged": true
    },
    "rejection_partition": {
      "train": 61,
      "holdout": 18,
      "training_representatives": 55,
      "excluded_short_or_redacted": 64,
      "negative_group_overlap": false,
      "excluded_similar_to_accepted": 0
    }
  },
  "evaluation": {
    "case_count": 457,
    "partitions": {
      "public_regression": {
        "baseline": {
          "total": 75,
          "domain_scored": 70,
          "domain_correct": 69,
          "qtype_scored": 70,
          "qtype_correct": 70,
          "gate_scored": 75,
          "gate_correct": 74,
          "nlg_integrity_pass": 75,
          "direct_answers": 67,
          "unsafe_direct_answers": 0
        },
        "candidate": {
          "total": 75,
          "domain_scored": 70,
          "domain_correct": 69,
          "qtype_scored": 70,
          "qtype_correct": 70,
          "gate_scored": 75,
          "gate_correct": 74,
          "nlg_integrity_pass": 75,
          "direct_answers": 67,
          "unsafe_direct_answers": 0
        }
      },
      "train": {
        "baseline": {
          "total": 180,
          "domain_scored": 180,
          "domain_correct": 80,
          "qtype_scored": 179,
          "qtype_correct": 134,
          "nlg_integrity_pass": 180,
          "direct_answers": 72
        },
        "candidate": {
          "total": 180,
          "domain_scored": 180,
          "domain_correct": 136,
          "qtype_scored": 179,
          "qtype_correct": 134,
          "nlg_integrity_pass": 180,
          "direct_answers": 116
        }
      },
      "holdout": {
        "baseline": {
          "total": 59,
          "domain_scored": 59,
          "domain_correct": 23,
          "qtype_scored": 59,
          "qtype_correct": 35,
          "nlg_integrity_pass": 59,
          "direct_answers": 21
        },
        "candidate": {
          "total": 59,
          "domain_scored": 59,
          "domain_correct": 27,
          "qtype_scored": 59,
          "qtype_correct": 35,
          "nlg_integrity_pass": 59,
          "direct_answers": 21
        }
      },
      "pending": {
        "baseline": {
          "total": 143,
          "nlg_integrity_pass": 143,
          "direct_answers": 23
        },
        "candidate": {
          "total": 143,
          "nlg_integrity_pass": 143,
          "direct_answers": 4
        }
      }
    },
    "negative_partitions": {
      "train": {
        "baseline": {
          "total": 61,
          "nlg_integrity_pass": 61,
          "direct_answers": 19
        },
        "candidate": {
          "total": 61,
          "nlg_integrity_pass": 61,
          "direct_answers": 0
        }
      },
      "holdout": {
        "baseline": {
          "total": 18,
          "nlg_integrity_pass": 18,
          "direct_answers": 4
        },
        "candidate": {
          "total": 18,
          "nlg_integrity_pass": 18,
          "direct_answers": 4
        }
      },
      "excluded": {
        "baseline": {
          "total": 64,
          "nlg_integrity_pass": 64,
          "direct_answers": 0
        },
        "candidate": {
          "total": 64,
          "nlg_integrity_pass": 64,
          "direct_answers": 0
        }
      }
    },
    "per_language_regression": {
      "en": {
        "baseline": {
          "total": 16,
          "domain_scored": 15,
          "domain_correct": 15,
          "qtype_scored": 15,
          "qtype_correct": 15,
          "gate_scored": 16,
          "gate_correct": 16,
          "nlg_integrity_pass": 16,
          "direct_answers": 14,
          "unsafe_direct_answers": 0
        },
        "candidate": {
          "total": 16,
          "domain_scored": 15,
          "domain_correct": 15,
          "qtype_scored": 15,
          "qtype_correct": 15,
          "gate_scored": 16,
          "gate_correct": 16,
          "nlg_integrity_pass": 16,
          "direct_answers": 14,
          "unsafe_direct_answers": 0
        }
      },
      "ja": {
        "baseline": {
          "total": 14,
          "domain_scored": 13,
          "domain_correct": 13,
          "qtype_scored": 13,
          "qtype_correct": 13,
          "gate_scored": 14,
          "gate_correct": 14,
          "nlg_integrity_pass": 14,
          "direct_answers": 13,
          "unsafe_direct_answers": 0
        },
        "candidate": {
          "total": 14,
          "domain_scored": 13,
          "domain_correct": 13,
          "qtype_scored": 13,
          "qtype_correct": 13,
          "gate_scored": 14,
          "gate_correct": 14,
          "nlg_integrity_pass": 14,
          "direct_answers": 13,
          "unsafe_direct_answers": 0
        }
      },
      "ko": {
        "baseline": {
          "total": 14,
          "domain_scored": 13,
          "domain_correct": 13,
          "qtype_scored": 13,
          "qtype_correct": 13,
          "gate_scored": 14,
          "gate_correct": 14,
          "nlg_integrity_pass": 14,
          "direct_answers": 13,
          "unsafe_direct_answers": 0
        },
        "candidate": {
          "total": 14,
          "domain_scored": 13,
          "domain_correct": 13,
          "qtype_scored": 13,
          "qtype_correct": 13,
          "gate_scored": 14,
          "gate_correct": 14,
          "nlg_integrity_pass": 14,
          "direct_answers": 13,
          "unsafe_direct_answers": 0
        }
      },
      "vi": {
        "baseline": {
          "total": 16,
          "domain_scored": 15,
          "domain_correct": 14,
          "qtype_scored": 15,
          "qtype_correct": 15,
          "gate_scored": 16,
          "gate_correct": 15,
          "nlg_integrity_pass": 16,
          "direct_answers": 13,
          "unsafe_direct_answers": 0
        },
        "candidate": {
          "total": 16,
          "domain_scored": 15,
          "domain_correct": 14,
          "qtype_scored": 15,
          "qtype_correct": 15,
          "gate_scored": 16,
          "gate_correct": 15,
          "nlg_integrity_pass": 16,
          "direct_answers": 13,
          "unsafe_direct_answers": 0
        }
      },
      "zh": {
        "baseline": {
          "total": 13,
          "domain_scored": 12,
          "domain_correct": 12,
          "qtype_scored": 12,
          "qtype_correct": 12,
          "gate_scored": 13,
          "gate_correct": 13,
          "nlg_integrity_pass": 13,
          "direct_answers": 12,
          "unsafe_direct_answers": 0
        },
        "candidate": {
          "total": 13,
          "domain_scored": 12,
          "domain_correct": 12,
          "qtype_scored": 12,
          "qtype_correct": 12,
          "gate_scored": 13,
          "gate_correct": 13,
          "nlg_integrity_pass": 13,
          "direct_answers": 12,
          "unsafe_direct_answers": 0
        }
      },
      "zht": {
        "baseline": {
          "total": 2,
          "domain_scored": 2,
          "domain_correct": 2,
          "qtype_scored": 2,
          "qtype_correct": 2,
          "gate_scored": 2,
          "gate_correct": 2,
          "nlg_integrity_pass": 2,
          "direct_answers": 2
        },
        "candidate": {
          "total": 2,
          "domain_scored": 2,
          "domain_correct": 2,
          "qtype_scored": 2,
          "qtype_correct": 2,
          "gate_scored": 2,
          "gate_correct": 2,
          "nlg_integrity_pass": 2,
          "direct_answers": 2
        }
      }
    },
    "pending_guard": {
      "pending_questions_replayed": 143,
      "pending_new_direct_answers": 0,
      "pending_nlg_integrity_failures": 0
    },
    "eligible_to_deploy": true
  }
}
