diff --git a/README.md b/README.md
index 2488f97..eda11e8 100644
--- a/README.md
+++ b/README.md
@@ -243,10 +243,108 @@ python train.py \
 选择额外信息变量：
 
 ```bash
-python train.py --extra_info_types 1 3 7
+python train.py --extra_info_types_file extra_info_types_smoking_alcohol_bmi.txt
 ```
 
-如果不传 `--extra_info_types`，默认使用全部 other-info type。
+`train.py` 只接受 `--extra_info_types_file` 指定变量列表，不接受在 CLI 里直接输入 type id。文件可以每行一个 type id，也可以带 `#` 注释；如果不传 `--extra_info_types_file`，默认使用全部 other-info type。
+
+训练输出的 `train_config.json` 会记录：
+
+- `extra_info_types_file`：训练时使用的列表文件名
+- `extra_info_types`：解析后的实际 type id 列表，用于评估脚本复现变量选择
+
+## 评估 AUC
+
+当前提供两个 AUC 评估入口，二者都已适配新的 `DeepHealth` 模型和统一的 other-info token 输入；AUC 的 DeLong 计算、病例/对照筛选和分层聚合逻辑保持原评估脚本口径。
+
+### `evaluate_auc.py`
+
+`evaluate_auc.py` 评估的是 **next-step / token-level 预测位置上的疾病 AUC**。
+
+核心流程：
+
+- 按训练配置重新构建 `HealthDataset` 和 `DeepHealth`。
+- 对评估 split 中的患者做一次模型推理，缓存每个 disease-token readout hidden。
+- 对疾病 token 分块投影到 `risk_head`，避免一次性保存全词表 logits。
+- 对每个疾病、性别、年龄段、prediction offset 分别计算 AUC。
+- 输出未池化分层结果和按疾病汇总后的结果。
+
+典型用法：
+
+```bash
+python evaluate_auc.py \
+  --run_path runs/your_run_dir \
+  --eval_split test \
+  --offsets 0.1,1,5,10
+```
+
+主要输出：
+
+- `df_auc_unpooled.csv`
+  - 疾病 token 在 sex、age bracket、offset 分层下的 AUC。
+- `df_both.csv`
+  - 按疾病 token 和 offset 聚合后的 AUC。
+
+适合回答的问题：
+
+- “模型在历史序列中的某个预测 token 上，提前 offset 年预测未来疾病的区分能力如何？”
+- “不同年龄段、性别、提前量下，next-step 训练模型的疾病预测 AUC 如何？”
+
+### `evaluate_auc_v2.py`
+
+`evaluate_auc_v2.py` 评估的是 **landmark fixed-horizon incident disease AUC**。
+
+它不是使用已有序列中的普通 readout 位置，而是在指定 landmark age 人工插入一个 `<NO_EVENT>` query token，然后评估该 landmark 后固定 horizon 内是否发生 incident disease。
+
+核心流程：
+
+- 为每个患者和 landmark age 构造 landmark query 样本。
+- 在 landmark age 插入 `<NO_EVENT>` token，取该位置 hidden。
+- 对疾病 token 分块投影到 `risk_head`。
+- 按疾病、性别、landmark age、horizon 计算 incident disease AUC。
+- 可选择排除 horizon 内先于目标疾病发生的死亡竞争风险。
+
+典型用法：
+
+```bash
+python evaluate_auc_v2.py \
+  --run_path runs/your_run_dir \
+  --eval_split test \
+  --landmark_start 40 \
+  --landmark_stop 80 \
+  --landmark_step 5 \
+  --horizons 1,5,10
+```
+
+主要输出：
+
+- `df_auc_landmark_unpooled.csv`
+  - 疾病 token 在 sex、landmark age、horizon 分层下的 AUC。
+- `df_auc_landmark.csv`
+  - 按疾病 token 和 horizon 聚合后的 landmark AUC。
+
+适合回答的问题：
+
+- “一个人在 40/45/50/... 岁这个固定年龄点，如果此前未患某病，未来 1/5/10 年内发生该病的风险区分能力如何？”
+- “模型能否作为 landmark risk prediction 模型使用？”
+
+### 两者区别
+
+| 项目 | `evaluate_auc.py` | `evaluate_auc_v2.py` |
+| --- | --- | --- |
+| 评估口径 | next-step/token-level 预测点 | landmark fixed-horizon incident risk |
+| 查询位置 | 原始序列中满足 offset 条件的最新 readout token | 人工插入的 `<NO_EVENT>` landmark token |
+| 时间参数 | `offsets`：预测点至少早于目标事件多少年 | `landmark_*` 和 `horizons`：固定年龄点与未来窗口 |
+| 病例定义 | target table 中出现目标疾病的患者/事件 | landmark 后 horizon 内首次发生目标疾病 |
+| 对照定义 | 从未出现该疾病的患者的 eligible target occurrence | landmark 时未患病，且 horizon 内未发病并有足够随访 |
+| 分层 | sex + age bracket + offset | sex + landmark age + horizon |
+| 输出文件 | `df_auc_unpooled.csv`, `df_both.csv` | `df_auc_landmark_unpooled.csv`, `df_auc_landmark.csv` |
+| 适用问题 | 提前若干年预测未来目标事件的 token-level AUC | 固定年龄点未来固定年限 incident disease risk AUC |
+
+简单选择：
+
+- 想复现/延续旧的 next-token Delphi 风格 AUC：用 `evaluate_auc.py`。
+- 想做临床上更像 “某年龄点未来 N 年发病风险” 的 landmark AUC：用 `evaluate_auc_v2.py`。
 
 ## 主要文件
 
@@ -278,3 +376,11 @@ python train.py --extra_info_types 1 3 7
   - token readout
   - same-time group readout
   - last-valid readout
+
+- `evaluate_auc.py`
+  - next-step/token-level 疾病 AUC 评估
+  - 使用 prediction offset、sex、age bracket 分层
+
+- `evaluate_auc_v2.py`
+  - landmark fixed-horizon incident disease AUC 评估
+  - 通过插入 `<NO_EVENT>` landmark token 查询固定年龄点风险
diff --git a/evaluate_auc.py b/evaluate_auc.py
index d96e70c..1449059 100644
--- a/evaluate_auc.py
+++ b/evaluate_auc.py
@@ -403,6 +403,32 @@ def make_eval_subset(dataset: HealthDataset, args: argparse.Namespace | Dict[str
     return Subset(dataset, indices.tolist()), np.asarray(indices, dtype=np.int64)
 
 
+def validate_dataset_metadata(dataset: HealthDataset, cfg: Dict[str, Any]) -> None:
+    meta = cfg.get("dataset_metadata")
+    if not isinstance(meta, dict):
+        return
+
+    actual: Dict[str, Any] = {
+        "vocab_size": int(dataset.vocab_size),
+        "n_types": int(dataset.n_types),
+        "n_cont_types": int(dataset.n_cont_types),
+        "n_categories": int(dataset.n_categories),
+        "cont_type_ids": [int(x) for x in dataset.cont_type_ids],
+        "extra_info_types": [int(x) for x in dataset.extra_info_types],
+    }
+    mismatches = [
+        f"{key}: train_config={meta.get(key)!r}, current_dataset={value!r}"
+        for key, value in actual.items()
+        if key in meta and meta.get(key) != value
+    ]
+    if mismatches:
+        raise RuntimeError(
+            "Current dataset metadata does not match train_config.json. "
+            "Use the same prepared data and extra_info_types as training. "
+            + "; ".join(mismatches)
+        )
+
+
 # ---------------------------------------------------------------------------
 # Batched inference + cached hidden states
 # ---------------------------------------------------------------------------
@@ -426,7 +452,6 @@ def infer_readout_hidden(
     model: DeepHealth,
     loader: DataLoader,
     device: torch.device,
-    attn_mask_mode: str,
     readout_name: str,
     readout_reduce: str,
     use_amp: bool,
@@ -736,7 +761,6 @@ def _init_auc_worker_flat(
     p_sex: np.ndarray,
     age_groups: np.ndarray,
     n_patients: int,
-    use_delong: bool,
 ):
     # Prevent BLAS/OpenMP oversubscription when many worker processes are active.
     os.environ.setdefault("OMP_NUM_THREADS", "1")
@@ -759,7 +783,6 @@ def _init_auc_worker_flat(
         "p_sex": p_sex,
         "age_groups": age_groups,
         "n_patients": int(n_patients),
-        "use_delong": bool(use_delong),
     })
 
 
@@ -793,7 +816,6 @@ def _calibration_auc_one_disease_flat(task: Tuple[int, int]) -> List[Dict[str, A
     p_sex = _WORKER["p_sex"]
     age_groups = _WORKER["age_groups"]
     n_patients = _WORKER["n_patients"]
-    use_delong = _WORKER["use_delong"]
 
     case_idx = _case_indices_for_token(int(token))
     if case_idx.size < 2:
@@ -838,12 +860,7 @@ def _calibration_auc_one_disease_flat(task: Tuple[int, int]) -> List[Dict[str, A
         if case_scores.size == 0 or control_scores.size == 0:
             continue
 
-        if use_delong:
-            auc_value, auc_var = get_auc_delong_var(
-                control_scores, case_scores)
-        else:
-            auc_value, auc_var = get_auc_delong_var(
-                control_scores, case_scores)
+        auc_value, auc_var = get_auc_delong_var(control_scores, case_scores)
 
         out.append({
             "token": int(token),
@@ -890,7 +907,6 @@ def compute_auc_chunk_parallel(
     offset: float,
     valid_target_min_id: int,
     num_workers: int,
-    use_delong: bool,
     auc_task_chunk_size: int = 0,
 ) -> List[Dict[str, Any]]:
     sex_mask = arrays["sex"] == sex_value
@@ -928,8 +944,7 @@ def compute_auc_chunk_parallel(
             flat["patient"], flat["target_event"], flat["pred_idx"], flat["age_bin"],
             flat["target_time"], flat["sort_order"], flat["sorted_target_event"],
             flat["raw_patient"], flat["raw_sort_order"], flat["raw_sorted_target_event"],
-            flat["p_sex"], flat["age_groups"], int(
-                flat["n_patients"]), use_delong,
+            flat["p_sex"], flat["age_groups"], int(flat["n_patients"]),
         )
         nested = [_calibration_auc_one_disease_flat(t) for t in tqdm(
             tasks, desc=f"AUC {sex_name}", leave=False, dynamic_ncols=True)]
@@ -946,8 +961,7 @@ def compute_auc_chunk_parallel(
                 flat["patient"], flat["target_event"], flat["pred_idx"], flat["age_bin"],
                 flat["target_time"], flat["sort_order"], flat["sorted_target_event"],
                 flat["raw_patient"], flat["raw_sort_order"], flat["raw_sorted_target_event"],
-                flat["p_sex"], flat["age_groups"], int(
-                    flat["n_patients"]), use_delong,
+                flat["p_sex"], flat["age_groups"], int(flat["n_patients"]),
             ),
         ) as ex:
             nested = list(tqdm(
@@ -985,7 +999,6 @@ def evaluate_auc_pipeline(
     age_groups: np.ndarray,
     offsets: Sequence[float],
     device: torch.device,
-    attn_mask_mode: str,
     readout_name: str,
     readout_reduce: str,
     num_workers_auc: int,
@@ -1045,7 +1058,6 @@ def evaluate_auc_pipeline(
         model=model,
         loader=loader,
         device=device,
-        attn_mask_mode=attn_mask_mode,
         readout_name=readout_name,
         readout_reduce=readout_reduce,
         use_amp=use_amp,
@@ -1075,7 +1087,6 @@ def evaluate_auc_pipeline(
                     offset=float(offset),
                     valid_target_min_id=valid_target_min_id,
                     num_workers=num_workers_auc,
-                    use_delong=True,
                     auc_task_chunk_size=auc_task_chunk_size,
                 )
                 for r in rows:
@@ -1131,6 +1142,14 @@ def parse_int_list(s: Any) -> Optional[List[int]]:
     text = str(s).strip()
     if text == "":
         return None
+    if text.startswith("["):
+        try:
+            values = json.loads(text)
+        except json.JSONDecodeError as exc:
+            raise ValueError(f"Invalid integer list: {text!r}") from exc
+        if not isinstance(values, list):
+            raise ValueError(f"Expected a JSON list, got {type(values).__name__}")
+        return [int(x) for x in values]
     return [int(x.strip()) for x in text.split(",") if x.strip()]
 
 
@@ -1142,6 +1161,14 @@ def parse_float_list(s: Any) -> Optional[List[float]]:
     text = str(s).strip()
     if text == "":
         return None
+    if text.startswith("["):
+        try:
+            values = json.loads(text)
+        except json.JSONDecodeError as exc:
+            raise ValueError(f"Invalid float list: {text!r}") from exc
+        if not isinstance(values, list):
+            raise ValueError(f"Expected a JSON list, got {type(values).__name__}")
+        return [float(x) for x in values]
     return [float(x.strip()) for x in text.split(",") if x.strip()]
 
 
@@ -1231,8 +1258,6 @@ def main() -> None:
 
     target_mode = cfg.get("target_mode", "uts")
     dist_mode_cfg = cfg.get("dist_mode", "exponential")
-    attn_mask_mode = cfg.get(
-        "attn_mask_mode", "non_strict_time" if target_mode == "uts" else "target_aware")
     readout_name = cfg.get(
         "readout_name", "same_time_group_end" if target_mode == "uts" else "token")
     readout_reduce = cfg.get("readout_reduce", "mean")
@@ -1250,6 +1275,7 @@ def main() -> None:
         include_no_event_in_uts_target=include_no_event,
         extra_info_types=parse_int_list(cfg.get("extra_info_types", None)),
     )
+    validate_dataset_metadata(dataset, cfg)
 
     subset, subset_indices = make_eval_subset(dataset, args, cfg)
     print(f"Dataset: {len(dataset)} samples, vocab_size={dataset.vocab_size}")
@@ -1309,7 +1335,6 @@ def main() -> None:
         age_groups=age_groups,
         offsets=auc_offsets,
         device=device,
-        attn_mask_mode=attn_mask_mode,
         readout_name=readout_name,
         readout_reduce=readout_reduce,
         num_workers_auc=int(cfg_get(args, cfg, "num_workers_auc", max(
diff --git a/evaluate_auc_v2.py b/evaluate_auc_v2.py
index a98cfce..e09b1d2 100644
--- a/evaluate_auc_v2.py
+++ b/evaluate_auc_v2.py
@@ -56,6 +56,14 @@ def parse_int_list(value: Any) -> Optional[List[int]]:
     text = str(value).strip()
     if text == "":
         return None
+    if text.startswith("["):
+        try:
+            values = json.loads(text)
+        except json.JSONDecodeError as exc:
+            raise ValueError(f"Invalid integer list: {text!r}") from exc
+        if not isinstance(values, list):
+            raise ValueError(f"Expected a JSON list, got {type(values).__name__}")
+        return [int(x) for x in values]
     return [int(x.strip()) for x in text.split(",") if x.strip()]
 
 
@@ -67,6 +75,14 @@ def parse_float_list(value: Any) -> Optional[List[float]]:
     text = str(value).strip()
     if text == "":
         return None
+    if text.startswith("["):
+        try:
+            values = json.loads(text)
+        except json.JSONDecodeError as exc:
+            raise ValueError(f"Invalid float list: {text!r}") from exc
+        if not isinstance(values, list):
+            raise ValueError(f"Expected a JSON list, got {type(values).__name__}")
+        return [float(x) for x in values]
     return [float(x.strip()) for x in text.split(",") if x.strip()]
 
 
@@ -155,6 +171,32 @@ def load_model_state(model: torch.nn.Module, state_dict: Dict[str, Any]) -> None
             f"[WARN] load_state_dict strict=False: missing={missing[:10]}, unexpected={unexpected[:10]}")
 
 
+def validate_dataset_metadata(dataset: HealthDataset, cfg: Dict[str, Any]) -> None:
+    meta = cfg.get("dataset_metadata")
+    if not isinstance(meta, dict):
+        return
+
+    actual: Dict[str, Any] = {
+        "vocab_size": int(dataset.vocab_size),
+        "n_types": int(dataset.n_types),
+        "n_cont_types": int(dataset.n_cont_types),
+        "n_categories": int(dataset.n_categories),
+        "cont_type_ids": [int(x) for x in dataset.cont_type_ids],
+        "extra_info_types": [int(x) for x in dataset.extra_info_types],
+    }
+    mismatches = [
+        f"{key}: train_config={meta.get(key)!r}, current_dataset={value!r}"
+        for key, value in actual.items()
+        if key in meta and meta.get(key) != value
+    ]
+    if mismatches:
+        raise RuntimeError(
+            "Current dataset metadata does not match train_config.json. "
+            "Use the same prepared data and extra_info_types as training. "
+            + "; ".join(mismatches)
+        )
+
+
 # ---------------------------------------------------------------------------
 # DeLong AUC utilities
 # ---------------------------------------------------------------------------
@@ -525,10 +567,8 @@ class LandmarkDataset(Dataset):
                         np.array([np.float32(landmark_age)], dtype=np.float32),
                     ]
                 )
-
-                target_time_seq = time_seq_landmark.copy()
                 if self.attn_mask_mode in _TARGET_AWARE_MODES:
-                    target_time_seq[-1] = np.nextafter(
+                    time_seq_landmark[-1] = np.nextafter(
                         np.float32(landmark_age), np.float32(np.inf), dtype=np.float32
                     )
 
@@ -546,7 +586,6 @@ class LandmarkDataset(Dataset):
                         "landmark_pos": int(len(event_seq_landmark) - 1),
                         "event_seq": event_seq_landmark,
                         "time_seq": time_seq_landmark,
-                        "target_time_seq": target_time_seq,
                         "readout_mask": readout_mask,
                         "other_type": np.asarray(s["other_type"], dtype=np.int64),
                         "other_value": np.asarray(s["other_value"], dtype=np.float32),
@@ -570,7 +609,6 @@ class LandmarkDataset(Dataset):
         return {
             "event_seq": torch.from_numpy(s["event_seq"]).long(),
             "time_seq": torch.from_numpy(s["time_seq"]).float(),
-            "target_time_seq": torch.from_numpy(s["target_time_seq"]).float(),
             "readout_mask": torch.from_numpy(s["readout_mask"]),
             "sex": torch.tensor(s["sex"], dtype=torch.long),
             "other_type": torch.from_numpy(s["other_type"]).long(),
@@ -590,8 +628,6 @@ def collate_landmark_fn(batch: List[Dict[str, torch.Tensor]]) -> Dict[str, torch
         [x["event_seq"] for x in batch], batch_first=True, padding_value=PAD_IDX)
     time_seq = pad_sequence([x["time_seq"]
                             for x in batch], batch_first=True, padding_value=0.0)
-    target_time_seq = pad_sequence(
-        [x["target_time_seq"] for x in batch], batch_first=True, padding_value=0.0)
     readout_mask = pad_sequence(
         [x["readout_mask"] for x in batch], batch_first=True, padding_value=False)
     other_type = pad_sequence(
@@ -606,7 +642,6 @@ def collate_landmark_fn(batch: List[Dict[str, torch.Tensor]]) -> Dict[str, torch
     return {
         "event_seq": event_seq,
         "time_seq": time_seq,
-        "target_time_seq": target_time_seq,
         "padding_mask": event_seq > PAD_IDX,
         "readout_mask": readout_mask,
         "sex": torch.stack([x["sex"] for x in batch]),
@@ -637,7 +672,6 @@ def infer_landmark_hidden(
     model: DeepHealth,
     loader: DataLoader,
     device: torch.device,
-    attn_mask_mode: str,
     readout_name: str,
     readout_reduce: str,
     use_amp: bool,
@@ -939,7 +973,6 @@ def evaluate_landmark_auc(
     score_mode: str,
     horizons: np.ndarray,
     device: torch.device,
-    attn_mask_mode: str,
     readout_name: str,
     readout_reduce: str,
     num_workers_auc: int,
@@ -957,7 +990,6 @@ def evaluate_landmark_auc(
         model=model,
         loader=loader,
         device=device,
-        attn_mask_mode=attn_mask_mode,
         readout_name=readout_name,
         readout_reduce=readout_reduce,
         use_amp=use_amp,
@@ -1193,6 +1225,7 @@ def main() -> None:
         include_no_event_in_uts_target=bool(include_no_event_in_uts_target),
         extra_info_types=parse_int_list(cfg.get("extra_info_types", None)),
     )
+    validate_dataset_metadata(dataset, cfg)
 
     has_no_event = (
         NO_EVENT_IDX in dataset.label_id_to_code
@@ -1381,7 +1414,6 @@ def main() -> None:
         score_mode=score_mode,
         horizons=horizons,
         device=device,
-        attn_mask_mode=attn_mask_mode,
         readout_name=readout_name,
         readout_reduce=readout_reduce,
         num_workers_auc=num_workers_auc,
diff --git a/extra_info_types_all.txt b/extra_info_types_all.txt
new file mode 100644
index 0000000..076e0b8
--- /dev/null
+++ b/extra_info_types_all.txt
@@ -0,0 +1,268 @@
+# All other-info variables (field_type=1 and field_type=2)
+# Generated from field_ids_enriched.csv using prepare_data.py other-info type ordering.
+# Format: <extra_info_type_id> # <var_name> | <full_name>
+1 # waist_circumference | Waist circumference
+2 # hip_circumference | Hip circumference
+3 # standing_height | Standing height
+4 # fasting_time | Fasting time
+5 # pulse_rate | Pulse rate automated reading
+6 # dbp | Diastolic blood pressure automated reading
+7 # sbp | Systolic blood pressure automated reading
+8 # fev1_best | Forced expiratory volume in 1-second (FEV1) Best measure
+9 # fvc_best | Forced vital capacity (FVC) Best measure
+10 # fev1_fvc_ratio | FEV1/ FVC ratio Z-score
+11 # bmi | Body mass index (BMI)
+12 # WBC | White blood cell (leukocyte) count
+13 # RBC | Red blood cell (erythrocyte) count
+14 # hemoglobin | Haemoglobin concentration
+15 # hematocrit | Haematocrit percentage
+16 # MCV | Mean corpuscular volume
+17 # MCH | Mean corpuscular haemoglobin
+18 # MCHC | Mean corpuscular haemoglobin concentration
+19 # Pc | Platelet count
+20 # MPV | Mean platelet (thrombocyte) volume
+21 # LymC | Lymphocyte count
+22 # MonC | Monocyte count
+23 # NeuC | Neutrophill count
+24 # EosC | Eosinophill count
+25 # BasC | Basophill count
+26 # nRBC | Nucleated red blood cell count
+27 # RC | Reticulocyte count
+28 # MRV | Mean reticulocyte volume
+29 # MSCV | Mean sphered cell volume
+30 # IRF | Immature reticulocyte fraction
+31 # HLSRC | High light scatter reticulocyte count
+32 # MicU | Microalbumin in urine
+33 # CreaU | Creatinine (enzymatic) in urine
+34 # PotU | Potassium in urine
+35 # SodU | Sodium in urine
+36 # Alb | Albumin
+37 # ALP | Alkaline phosphatase
+38 # Alanine | Alanine aminotransferase
+39 # ApoA | Apolipoprotein A
+40 # ApoB | Apolipoprotein B
+41 # AA | Aspartate aminotransferase
+42 # DBil | Direct bilirubin
+43 # Urea | Urea
+44 # Calcium | Calcium
+45 # Cholesterol | Cholesterol
+46 # Creatinine | Creatinine
+47 # CRP | C-reactive protein
+48 # CystatinC | Cystatin C
+49 # GGT | Gamma glutamyltransferase
+50 # Glu | Glucose
+51 # HbA1c | Glycated haemoglobin (HbA1c)
+52 # HDL | HDL cholesterol
+53 # IGF1 | IGF-1
+54 # LDL | LDL direct
+55 # LpA | Lipoprotein A
+56 # Oestradiol | Oestradiol
+57 # Phosphate | Phosphate
+58 # Rheu | Rheumatoid factor
+59 # SHBG | SHBG
+60 # TotalBil | Total bilirubin
+61 # Testosterone | Testosterone
+62 # TotalProtein | Total protein
+63 # Tri | Triglycerides
+64 # Urate | Urate
+65 # VitaminD | Vitamin D
+66 # smoking | Current tobacco smoking
+67 # alcohol | Alcohol intake frequency.
+68 # ipaq_activity_group | IPAQ activity group
+69 # moderate_activity_met_minutes_week | MET minutes per week for moderate activity
+70 # vigorous_activity_met_minutes_week | MET minutes per week for vigorous activity
+71 # walking_met_minutes_week | MET minutes per week for walking
+72 # total_activity_met_minutes_week | Summed MET minutes per week for all activity
+73 # total_activity_days | Summed days activity
+74 # total_activity_minutes | Summed minutes activity
+75 # heavy_diy_duration | Duration of heavy DIY
+76 # light_diy_duration | Duration of light DIY
+77 # moderate_activity_duration | Duration of moderate activity
+78 # other_exercise_duration | Duration of other exercises
+79 # strenuous_sport_duration | Duration of strenuous sports
+80 # vigorous_activity_duration | Duration of vigorous activity
+81 # walking_duration | Duration of walks
+82 # pleasure_walking_duration | Duration walking for pleasure
+83 # heavy_diy_frequency_4_weeks | Frequency of heavy DIY in last 4 weeks
+84 # light_diy_frequency_4_weeks | Frequency of light DIY in last 4 weeks
+85 # other_exercise_frequency_4_weeks | Frequency of other exercises in last 4 weeks
+86 # stair_climbing_frequency_4_weeks | Frequency of stair climbing in last 4 weeks
+87 # strenuous_sport_frequency_4_weeks | Frequency of strenuous sports in last 4 weeks
+88 # pleasure_walking_frequency_4_weeks | Frequency of walking for pleasure in last 4 weeks
+89 # moderate_activity_days_week_10min | Number of days/week of moderate physical activity 10+ minutes
+90 # vigorous_activity_days_week_10min | Number of days/week of vigorous physical activity 10+ minutes
+91 # walking_days_week_10min | Number of days/week walked 10+ minutes
+92 # driving_time | Time spent driving
+93 # computer_use_time | Time spent using computer
+94 # tv_watching_time | Time spent watching television (TV)
+95 # physical_activity_types_4_weeks | Types of physical activity in last 4 weeks
+96 # nonwork_transport_types | Types of transport used (excluding work)
+97 # usual_walking_pace | Usual walking pace
+98 # mobile_phone_use_duration | Length of mobile phone use
+99 # mobile_phone_use_weekly_3_months | Weekly usage of mobile phone in last 3 months
+100 # computer_game_playing | Plays computer games
+101 # sleep_duration | Sleep duration
+102 # chronotype | Morning/evening person (chronotype)
+103 # daytime_napping | Nap during day
+104 # insomnia | Sleeplessness / insomnia
+105 # daytime_dozing | Daytime dozing / sleeping
+106 # ever_smoked | Ever smoked
+107 # smoking_pack_years | Pack years of smoking
+108 # smoking_status | Smoking status
+109 # past_tobacco_smoking | Past tobacco smoking
+110 # lifetime_smoking_100_plus | Light smokers, at least 100 smokes in lifetime
+111 # current_tobacco_type | Type of tobacco currently smoked
+112 # current_cigarettes_per_day | Number of cigarettes currently smoked daily (current cigarette smokers)
+113 # previous_cigarettes_per_day_current_cigar_pipe_smokers | Number of cigarettes previously smoked daily (current cigar/pipe smokers)
+114 # time_to_first_cigarette | Time from waking to first cigarette
+115 # ever_tried_smoking_cessation | Ever tried to stop smoking
+116 # smoking_change_vs_10_years_ago | Smoking compared to 10 years previous
+117 # previous_tobacco_type | Type of tobacco previously smoked
+118 # previous_cigarettes_per_day | Number of cigarettes previously smoked daily
+119 # ever_stopped_smoking_6_months | Ever stopped smoking for 6+ months
+120 # household_smokers | Smoking/smokers in household
+121 # home_secondhand_smoke_exposure | Exposure to tobacco smoke at home
+122 # nonhome_secondhand_smoke_exposure | Exposure to tobacco smoke outside home
+123 # cooked_vegetable_intake | Cooked vegetable intake
+124 # raw_vegetable_intake | Salad / raw vegetable intake
+125 # fresh_fruit_intake | Fresh fruit intake
+126 # dried_fruit_intake | Dried fruit intake
+127 # oily_fish_intake | Oily fish intake
+128 # non_oily_fish_intake | Non-oily fish intake
+129 # processed_meat_intake | Processed meat intake
+130 # poultry_intake | Poultry intake
+131 # beef_intake | Beef intake
+132 # lamb_mutton_intake | Lamb/mutton intake
+133 # pork_intake | Pork intake
+134 # age_last_ate_meat | Age when last ate meat
+135 # food_avoidance_eggs_dairy_wheat_sugar | Never eat eggs, dairy, wheat, sugar
+136 # cheese_intake | Cheese intake
+137 # milk_type | Milk type used
+138 # spread_type | Spread type
+139 # bread_intake | Bread intake
+140 # bread_type | Bread type
+141 # cereal_intake | Cereal intake
+142 # cereal_type | Cereal type
+143 # added_salt | Salt added to food
+144 # tea_intake | Tea intake
+145 # coffee_intake | Coffee intake
+146 # coffee_type | Coffee type
+147 # hot_drink_temperature | Hot drink temperature
+148 # water_intake | Water intake
+149 # diet_variation | Variation in diet
+150 # alcohol_drinker_status | Alcohol drinker status
+151 # former_alcohol_drinker | Former alcohol drinker
+152 # red_wine_intake_monthly | Average monthly red wine intake
+153 # champagne_white_wine_intake_monthly | Average monthly champagne plus white wine intake
+154 # beer_cider_intake_monthly | Average monthly beer plus cider intake
+155 # spirits_intake_monthly | Average monthly spirits intake
+156 # fortified_wine_intake_monthly | Average monthly fortified wine intake
+157 # other_alcohol_intake_monthly | Average monthly intake of other alcoholic drinks
+158 # red_wine_intake_weekly | Average weekly red wine intake
+159 # champagne_white_wine_intake_weekly | Average weekly champagne plus white wine intake
+160 # beer_cider_intake_weekly | Average weekly beer plus cider intake
+161 # spirits_intake_weekly | Average weekly spirits intake
+162 # fortified_wine_intake_weekly | Average weekly fortified wine intake
+163 # other_alcohol_intake_weekly | Average weekly intake of other alcoholic drinks
+164 # alcohol_with_meals | Alcohol usually taken with meals
+165 # country_of_birth_uk_elsewhere | Country of birth (UK/elsewhere)
+166 # breastfed_in_infancy | Breastfed as a baby
+167 # comparative_body_size_age_10 | Comparative body size at age 10
+168 # comparative_height_age_10 | Comparative height size at age 10
+169 # handedness | Handedness (chirality/laterality)
+170 # adopted_as_child | Adopted as a child
+171 # multiple_birth | Part of a multiple birth
+172 # maternal_smoking_around_birth | Maternal smoking around birth
+173 # accommodation_type | Type of accommodation lived in
+174 # housing_tenure | Own or rent accommodation lived in
+175 # gas_solid_fuel_use | Gas or solid-fuel cooking/heating
+176 # home_heating_types | Heating type(s) in home
+177 # household_vehicle_count | Number of vehicles in household
+178 # household_income_before_tax | Average total household income before tax
+179 # current_employment_status | Current employment status
+180 # current_employment_status_corrected | Current employment status - corrected
+181 # home_work_distance | Distance between home and job workplace
+182 # main_job_hours_week | Length of working week for main job
+183 # commuting_frequency | Frequency of travelling from home to job workplace
+184 # commuting_transport_type | Transport type for commuting to job workplace
+185 # job_walking_standing | Job involves mainly walking or standing
+186 # job_heavy_manual_work | Job involves heavy manual or physical work
+187 # job_shift_work | Job involves shift work
+188 # job_night_shift_work | Job involves night shift work
+189 # educational_qualifications | Qualifications
+190 # age_completed_full_time_education | Age completed full time education
+191 # friend_family_visit_frequency | Frequency of friend/family visits
+192 # leisure_social_activities | Leisure/social activities
+193 # ability_to_confide | Able to confide
+194 # bipolar_major_depression_status | Bipolar and major depression status
+195 # neuroticism_score | Neuroticism score
+196 # mood_swings | Mood swings
+197 # miserableness | Miserableness
+198 # irritability | Irritability
+199 # sensitivity_hurt_feelings | Sensitivity / hurt feelings
+200 # fed_up_feelings | Fed-up feelings
+201 # nervous_feelings | Nervous feelings
+202 # worry_anxiety_feelings | Worrier / anxious feelings
+203 # tenseness_highly_strung | Tense / 'highly strung'
+204 # suffering_from_nerves | Suffer from 'nerves'
+205 # loneliness_isolation | Loneliness, isolation
+206 # guilty_feelings | Guilty feelings
+207 # risk_taking | Risk taking
+208 # happiness | Happiness
+209 # job_satisfaction | Work/job satisfaction
+210 # health_satisfaction | Health satisfaction
+211 # family_relationship_satisfaction | Family relationship satisfaction
+212 # friendship_satisfaction | Friendships satisfaction
+213 # financial_situation_satisfaction | Financial situation satisfaction
+214 # depressed_mood_frequency_2_weeks | Frequency of depressed mood in last 2 weeks
+215 # disinterest_frequency_2_weeks | Frequency of unenthusiasm / disinterest in last 2 weeks
+216 # tenseness_restlessness_frequency_2_weeks | Frequency of tenseness / restlessness in last 2 weeks
+217 # tiredness_lethargy_frequency_2_weeks | Frequency of tiredness / lethargy in last 2 weeks
+218 # ever_depressed_full_week | Ever depressed for a whole week
+219 # longest_depression_duration | Longest period of depression
+220 # depression_episode_count | Number of depression episodes
+221 # longest_disinterest_duration | Longest period of unenthusiasm / disinterest
+222 # disinterest_episode_count | Number of unenthusiastic/disinterested episodes
+223 # ever_manic_hyper_2_days | Ever manic/hyper for 2 days
+224 # ever_irritable_argumentative_2_days | Ever highly irritable/argumentative for 2 days
+225 # manic_hyper_symptoms | Manic/hyper symptoms
+226 # longest_manic_irritable_episode_duration | Length of longest manic/irritable episode
+227 # manic_irritable_episode_severity | Severity of manic/irritable episodes
+228 # adverse_life_events_2_years | Illness, injury, bereavement, stress in last 2 years
+229 # outdoor_time_summer | Time spend outdoors in summer
+230 # outdoor_time_winter | Time spent outdoors in winter
+231 # skin_tanning_ease | Ease of skin tanning
+232 # childhood_sunburn_frequency | Childhood sunburn occasions
+233 # sun_uv_protection_use | Use of sun/uv protection
+234 # solarium_sunlamp_frequency | Frequency of solarium/sunlamp use
+235 # proximity_to_major_road | Close to major road
+236 # inverse_distance_nearest_major_road | Inverse distance to the nearest major road
+237 # inverse_distance_nearest_road | Inverse distance to the nearest road
+238 # no2_2005 | Nitrogen dioxide air pollution; 2005
+239 # no2_2006 | Nitrogen dioxide air pollution; 2006
+240 # no2_2007 | Nitrogen dioxide air pollution; 2007
+241 # no2_2010 | Nitrogen dioxide air pollution; 2010
+242 # nox_2010 | Nitrogen oxides air pollution; 2010
+243 # pm10_2007 | Particulate matter air pollution (pm10); 2007
+244 # pm10_2010 | Particulate matter air pollution (pm10); 2010
+245 # pm25_absorbance_2010 | Particulate matter air pollution (pm2.5) absorbance; 2010
+246 # pm25_2010 | Particulate matter air pollution (pm2.5); 2010
+247 # pm25_10_2010 | Particulate matter air pollution 2.5-10um; 2010
+248 # major_road_length_100m | Sum of road length of major roads within 100m
+249 # major_road_traffic_load | Total traffic load on major roads
+250 # nearest_major_road_traffic_intensity | Traffic intensity on the nearest major road
+251 # nearest_road_traffic_intensity | Traffic intensity on the nearest road
+252 # noise_level_16h | Average 16-hour sound level of noise pollution
+253 # noise_level_24h | Average 24-hour sound level of noise pollution
+254 # noise_level_daytime | Average daytime sound level of noise pollution
+255 # noise_level_evening | Average evening sound level of noise pollution
+256 # noise_level_nighttime | Average night-time sound level of noise pollution
+257 # natural_environment_percent_1000m | Natural environment percentage, buffer 1000m
+258 # natural_environment_percent_300m | Natural environment percentage, buffer 300m
+259 # greenspace_percent_1000m | Greenspace percentage, buffer 1000m
+260 # greenspace_percent_300m | Greenspace percentage, buffer 300m
+261 # domestic_garden_percent_1000m | Domestic garden percentage, buffer 1000m
+262 # domestic_garden_percent_300m | Domestic garden percentage, buffer 300m
+263 # water_percent_1000m | Water percentage, buffer 1000m
+264 # water_percent_300m | Water percentage, buffer 300m
+265 # distance_to_coast | Distance (Euclidean) to coast
diff --git a/extra_info_types_assessment_only.txt b/extra_info_types_assessment_only.txt
new file mode 100644
index 0000000..7535941
--- /dev/null
+++ b/extra_info_types_assessment_only.txt
@@ -0,0 +1,68 @@
+# Only assessment/body-measurement variables (field_type=1)
+# Generated from field_ids_enriched.csv using prepare_data.py other-info type ordering.
+# Format: <extra_info_type_id> # <var_name> | <full_name>
+1 # waist_circumference | Waist circumference
+2 # hip_circumference | Hip circumference
+3 # standing_height | Standing height
+4 # fasting_time | Fasting time
+5 # pulse_rate | Pulse rate automated reading
+6 # dbp | Diastolic blood pressure automated reading
+7 # sbp | Systolic blood pressure automated reading
+8 # fev1_best | Forced expiratory volume in 1-second (FEV1) Best measure
+9 # fvc_best | Forced vital capacity (FVC) Best measure
+10 # fev1_fvc_ratio | FEV1/ FVC ratio Z-score
+11 # bmi | Body mass index (BMI)
+12 # WBC | White blood cell (leukocyte) count
+13 # RBC | Red blood cell (erythrocyte) count
+14 # hemoglobin | Haemoglobin concentration
+15 # hematocrit | Haematocrit percentage
+16 # MCV | Mean corpuscular volume
+17 # MCH | Mean corpuscular haemoglobin
+18 # MCHC | Mean corpuscular haemoglobin concentration
+19 # Pc | Platelet count
+20 # MPV | Mean platelet (thrombocyte) volume
+21 # LymC | Lymphocyte count
+22 # MonC | Monocyte count
+23 # NeuC | Neutrophill count
+24 # EosC | Eosinophill count
+25 # BasC | Basophill count
+26 # nRBC | Nucleated red blood cell count
+27 # RC | Reticulocyte count
+28 # MRV | Mean reticulocyte volume
+29 # MSCV | Mean sphered cell volume
+30 # IRF | Immature reticulocyte fraction
+31 # HLSRC | High light scatter reticulocyte count
+32 # MicU | Microalbumin in urine
+33 # CreaU | Creatinine (enzymatic) in urine
+34 # PotU | Potassium in urine
+35 # SodU | Sodium in urine
+36 # Alb | Albumin
+37 # ALP | Alkaline phosphatase
+38 # Alanine | Alanine aminotransferase
+39 # ApoA | Apolipoprotein A
+40 # ApoB | Apolipoprotein B
+41 # AA | Aspartate aminotransferase
+42 # DBil | Direct bilirubin
+43 # Urea | Urea
+44 # Calcium | Calcium
+45 # Cholesterol | Cholesterol
+46 # Creatinine | Creatinine
+47 # CRP | C-reactive protein
+48 # CystatinC | Cystatin C
+49 # GGT | Gamma glutamyltransferase
+50 # Glu | Glucose
+51 # HbA1c | Glycated haemoglobin (HbA1c)
+52 # HDL | HDL cholesterol
+53 # IGF1 | IGF-1
+54 # LDL | LDL direct
+55 # LpA | Lipoprotein A
+56 # Oestradiol | Oestradiol
+57 # Phosphate | Phosphate
+58 # Rheu | Rheumatoid factor
+59 # SHBG | SHBG
+60 # TotalBil | Total bilirubin
+61 # Testosterone | Testosterone
+62 # TotalProtein | Total protein
+63 # Tri | Triglycerides
+64 # Urate | Urate
+65 # VitaminD | Vitamin D
diff --git a/extra_info_types_exposure_only.txt b/extra_info_types_exposure_only.txt
new file mode 100644
index 0000000..0fd3f94
--- /dev/null
+++ b/extra_info_types_exposure_only.txt
@@ -0,0 +1,203 @@
+# Only environment/lifestyle exposure variables (field_type=2)
+# Generated from field_ids_enriched.csv using prepare_data.py other-info type ordering.
+# Format: <extra_info_type_id> # <var_name> | <full_name>
+66 # smoking | Current tobacco smoking
+67 # alcohol | Alcohol intake frequency.
+68 # ipaq_activity_group | IPAQ activity group
+69 # moderate_activity_met_minutes_week | MET minutes per week for moderate activity
+70 # vigorous_activity_met_minutes_week | MET minutes per week for vigorous activity
+71 # walking_met_minutes_week | MET minutes per week for walking
+72 # total_activity_met_minutes_week | Summed MET minutes per week for all activity
+73 # total_activity_days | Summed days activity
+74 # total_activity_minutes | Summed minutes activity
+75 # heavy_diy_duration | Duration of heavy DIY
+76 # light_diy_duration | Duration of light DIY
+77 # moderate_activity_duration | Duration of moderate activity
+78 # other_exercise_duration | Duration of other exercises
+79 # strenuous_sport_duration | Duration of strenuous sports
+80 # vigorous_activity_duration | Duration of vigorous activity
+81 # walking_duration | Duration of walks
+82 # pleasure_walking_duration | Duration walking for pleasure
+83 # heavy_diy_frequency_4_weeks | Frequency of heavy DIY in last 4 weeks
+84 # light_diy_frequency_4_weeks | Frequency of light DIY in last 4 weeks
+85 # other_exercise_frequency_4_weeks | Frequency of other exercises in last 4 weeks
+86 # stair_climbing_frequency_4_weeks | Frequency of stair climbing in last 4 weeks
+87 # strenuous_sport_frequency_4_weeks | Frequency of strenuous sports in last 4 weeks
+88 # pleasure_walking_frequency_4_weeks | Frequency of walking for pleasure in last 4 weeks
+89 # moderate_activity_days_week_10min | Number of days/week of moderate physical activity 10+ minutes
+90 # vigorous_activity_days_week_10min | Number of days/week of vigorous physical activity 10+ minutes
+91 # walking_days_week_10min | Number of days/week walked 10+ minutes
+92 # driving_time | Time spent driving
+93 # computer_use_time | Time spent using computer
+94 # tv_watching_time | Time spent watching television (TV)
+95 # physical_activity_types_4_weeks | Types of physical activity in last 4 weeks
+96 # nonwork_transport_types | Types of transport used (excluding work)
+97 # usual_walking_pace | Usual walking pace
+98 # mobile_phone_use_duration | Length of mobile phone use
+99 # mobile_phone_use_weekly_3_months | Weekly usage of mobile phone in last 3 months
+100 # computer_game_playing | Plays computer games
+101 # sleep_duration | Sleep duration
+102 # chronotype | Morning/evening person (chronotype)
+103 # daytime_napping | Nap during day
+104 # insomnia | Sleeplessness / insomnia
+105 # daytime_dozing | Daytime dozing / sleeping
+106 # ever_smoked | Ever smoked
+107 # smoking_pack_years | Pack years of smoking
+108 # smoking_status | Smoking status
+109 # past_tobacco_smoking | Past tobacco smoking
+110 # lifetime_smoking_100_plus | Light smokers, at least 100 smokes in lifetime
+111 # current_tobacco_type | Type of tobacco currently smoked
+112 # current_cigarettes_per_day | Number of cigarettes currently smoked daily (current cigarette smokers)
+113 # previous_cigarettes_per_day_current_cigar_pipe_smokers | Number of cigarettes previously smoked daily (current cigar/pipe smokers)
+114 # time_to_first_cigarette | Time from waking to first cigarette
+115 # ever_tried_smoking_cessation | Ever tried to stop smoking
+116 # smoking_change_vs_10_years_ago | Smoking compared to 10 years previous
+117 # previous_tobacco_type | Type of tobacco previously smoked
+118 # previous_cigarettes_per_day | Number of cigarettes previously smoked daily
+119 # ever_stopped_smoking_6_months | Ever stopped smoking for 6+ months
+120 # household_smokers | Smoking/smokers in household
+121 # home_secondhand_smoke_exposure | Exposure to tobacco smoke at home
+122 # nonhome_secondhand_smoke_exposure | Exposure to tobacco smoke outside home
+123 # cooked_vegetable_intake | Cooked vegetable intake
+124 # raw_vegetable_intake | Salad / raw vegetable intake
+125 # fresh_fruit_intake | Fresh fruit intake
+126 # dried_fruit_intake | Dried fruit intake
+127 # oily_fish_intake | Oily fish intake
+128 # non_oily_fish_intake | Non-oily fish intake
+129 # processed_meat_intake | Processed meat intake
+130 # poultry_intake | Poultry intake
+131 # beef_intake | Beef intake
+132 # lamb_mutton_intake | Lamb/mutton intake
+133 # pork_intake | Pork intake
+134 # age_last_ate_meat | Age when last ate meat
+135 # food_avoidance_eggs_dairy_wheat_sugar | Never eat eggs, dairy, wheat, sugar
+136 # cheese_intake | Cheese intake
+137 # milk_type | Milk type used
+138 # spread_type | Spread type
+139 # bread_intake | Bread intake
+140 # bread_type | Bread type
+141 # cereal_intake | Cereal intake
+142 # cereal_type | Cereal type
+143 # added_salt | Salt added to food
+144 # tea_intake | Tea intake
+145 # coffee_intake | Coffee intake
+146 # coffee_type | Coffee type
+147 # hot_drink_temperature | Hot drink temperature
+148 # water_intake | Water intake
+149 # diet_variation | Variation in diet
+150 # alcohol_drinker_status | Alcohol drinker status
+151 # former_alcohol_drinker | Former alcohol drinker
+152 # red_wine_intake_monthly | Average monthly red wine intake
+153 # champagne_white_wine_intake_monthly | Average monthly champagne plus white wine intake
+154 # beer_cider_intake_monthly | Average monthly beer plus cider intake
+155 # spirits_intake_monthly | Average monthly spirits intake
+156 # fortified_wine_intake_monthly | Average monthly fortified wine intake
+157 # other_alcohol_intake_monthly | Average monthly intake of other alcoholic drinks
+158 # red_wine_intake_weekly | Average weekly red wine intake
+159 # champagne_white_wine_intake_weekly | Average weekly champagne plus white wine intake
+160 # beer_cider_intake_weekly | Average weekly beer plus cider intake
+161 # spirits_intake_weekly | Average weekly spirits intake
+162 # fortified_wine_intake_weekly | Average weekly fortified wine intake
+163 # other_alcohol_intake_weekly | Average weekly intake of other alcoholic drinks
+164 # alcohol_with_meals | Alcohol usually taken with meals
+165 # country_of_birth_uk_elsewhere | Country of birth (UK/elsewhere)
+166 # breastfed_in_infancy | Breastfed as a baby
+167 # comparative_body_size_age_10 | Comparative body size at age 10
+168 # comparative_height_age_10 | Comparative height size at age 10
+169 # handedness | Handedness (chirality/laterality)
+170 # adopted_as_child | Adopted as a child
+171 # multiple_birth | Part of a multiple birth
+172 # maternal_smoking_around_birth | Maternal smoking around birth
+173 # accommodation_type | Type of accommodation lived in
+174 # housing_tenure | Own or rent accommodation lived in
+175 # gas_solid_fuel_use | Gas or solid-fuel cooking/heating
+176 # home_heating_types | Heating type(s) in home
+177 # household_vehicle_count | Number of vehicles in household
+178 # household_income_before_tax | Average total household income before tax
+179 # current_employment_status | Current employment status
+180 # current_employment_status_corrected | Current employment status - corrected
+181 # home_work_distance | Distance between home and job workplace
+182 # main_job_hours_week | Length of working week for main job
+183 # commuting_frequency | Frequency of travelling from home to job workplace
+184 # commuting_transport_type | Transport type for commuting to job workplace
+185 # job_walking_standing | Job involves mainly walking or standing
+186 # job_heavy_manual_work | Job involves heavy manual or physical work
+187 # job_shift_work | Job involves shift work
+188 # job_night_shift_work | Job involves night shift work
+189 # educational_qualifications | Qualifications
+190 # age_completed_full_time_education | Age completed full time education
+191 # friend_family_visit_frequency | Frequency of friend/family visits
+192 # leisure_social_activities | Leisure/social activities
+193 # ability_to_confide | Able to confide
+194 # bipolar_major_depression_status | Bipolar and major depression status
+195 # neuroticism_score | Neuroticism score
+196 # mood_swings | Mood swings
+197 # miserableness | Miserableness
+198 # irritability | Irritability
+199 # sensitivity_hurt_feelings | Sensitivity / hurt feelings
+200 # fed_up_feelings | Fed-up feelings
+201 # nervous_feelings | Nervous feelings
+202 # worry_anxiety_feelings | Worrier / anxious feelings
+203 # tenseness_highly_strung | Tense / 'highly strung'
+204 # suffering_from_nerves | Suffer from 'nerves'
+205 # loneliness_isolation | Loneliness, isolation
+206 # guilty_feelings | Guilty feelings
+207 # risk_taking | Risk taking
+208 # happiness | Happiness
+209 # job_satisfaction | Work/job satisfaction
+210 # health_satisfaction | Health satisfaction
+211 # family_relationship_satisfaction | Family relationship satisfaction
+212 # friendship_satisfaction | Friendships satisfaction
+213 # financial_situation_satisfaction | Financial situation satisfaction
+214 # depressed_mood_frequency_2_weeks | Frequency of depressed mood in last 2 weeks
+215 # disinterest_frequency_2_weeks | Frequency of unenthusiasm / disinterest in last 2 weeks
+216 # tenseness_restlessness_frequency_2_weeks | Frequency of tenseness / restlessness in last 2 weeks
+217 # tiredness_lethargy_frequency_2_weeks | Frequency of tiredness / lethargy in last 2 weeks
+218 # ever_depressed_full_week | Ever depressed for a whole week
+219 # longest_depression_duration | Longest period of depression
+220 # depression_episode_count | Number of depression episodes
+221 # longest_disinterest_duration | Longest period of unenthusiasm / disinterest
+222 # disinterest_episode_count | Number of unenthusiastic/disinterested episodes
+223 # ever_manic_hyper_2_days | Ever manic/hyper for 2 days
+224 # ever_irritable_argumentative_2_days | Ever highly irritable/argumentative for 2 days
+225 # manic_hyper_symptoms | Manic/hyper symptoms
+226 # longest_manic_irritable_episode_duration | Length of longest manic/irritable episode
+227 # manic_irritable_episode_severity | Severity of manic/irritable episodes
+228 # adverse_life_events_2_years | Illness, injury, bereavement, stress in last 2 years
+229 # outdoor_time_summer | Time spend outdoors in summer
+230 # outdoor_time_winter | Time spent outdoors in winter
+231 # skin_tanning_ease | Ease of skin tanning
+232 # childhood_sunburn_frequency | Childhood sunburn occasions
+233 # sun_uv_protection_use | Use of sun/uv protection
+234 # solarium_sunlamp_frequency | Frequency of solarium/sunlamp use
+235 # proximity_to_major_road | Close to major road
+236 # inverse_distance_nearest_major_road | Inverse distance to the nearest major road
+237 # inverse_distance_nearest_road | Inverse distance to the nearest road
+238 # no2_2005 | Nitrogen dioxide air pollution; 2005
+239 # no2_2006 | Nitrogen dioxide air pollution; 2006
+240 # no2_2007 | Nitrogen dioxide air pollution; 2007
+241 # no2_2010 | Nitrogen dioxide air pollution; 2010
+242 # nox_2010 | Nitrogen oxides air pollution; 2010
+243 # pm10_2007 | Particulate matter air pollution (pm10); 2007
+244 # pm10_2010 | Particulate matter air pollution (pm10); 2010
+245 # pm25_absorbance_2010 | Particulate matter air pollution (pm2.5) absorbance; 2010
+246 # pm25_2010 | Particulate matter air pollution (pm2.5); 2010
+247 # pm25_10_2010 | Particulate matter air pollution 2.5-10um; 2010
+248 # major_road_length_100m | Sum of road length of major roads within 100m
+249 # major_road_traffic_load | Total traffic load on major roads
+250 # nearest_major_road_traffic_intensity | Traffic intensity on the nearest major road
+251 # nearest_road_traffic_intensity | Traffic intensity on the nearest road
+252 # noise_level_16h | Average 16-hour sound level of noise pollution
+253 # noise_level_24h | Average 24-hour sound level of noise pollution
+254 # noise_level_daytime | Average daytime sound level of noise pollution
+255 # noise_level_evening | Average evening sound level of noise pollution
+256 # noise_level_nighttime | Average night-time sound level of noise pollution
+257 # natural_environment_percent_1000m | Natural environment percentage, buffer 1000m
+258 # natural_environment_percent_300m | Natural environment percentage, buffer 300m
+259 # greenspace_percent_1000m | Greenspace percentage, buffer 1000m
+260 # greenspace_percent_300m | Greenspace percentage, buffer 300m
+261 # domestic_garden_percent_1000m | Domestic garden percentage, buffer 1000m
+262 # domestic_garden_percent_300m | Domestic garden percentage, buffer 300m
+263 # water_percent_1000m | Water percentage, buffer 1000m
+264 # water_percent_300m | Water percentage, buffer 300m
+265 # distance_to_coast | Distance (Euclidean) to coast
diff --git a/extra_info_types_smoking_alcohol_bmi.txt b/extra_info_types_smoking_alcohol_bmi.txt
new file mode 100644
index 0000000..67f5532
--- /dev/null
+++ b/extra_info_types_smoking_alcohol_bmi.txt
@@ -0,0 +1,6 @@
+# Only smoking, alcohol, and BMI variables
+# Generated from field_ids_enriched.csv using prepare_data.py other-info type ordering.
+# Format: <extra_info_type_id> # <var_name> | <full_name>
+11 # bmi | Body mass index (BMI)
+66 # smoking | Current tobacco smoking
+67 # alcohol | Alcohol intake frequency.
\ No newline at end of file
diff --git a/models.py b/models.py
index 4026226..e74db4b 100644
--- a/models.py
+++ b/models.py
@@ -94,7 +94,7 @@ class DeepHealth(nn.Module):
             ])
             self.rope = None
             self.rbf = None
-        if time_mode == "relative":
+        elif time_mode == "relative":
             self.age_encoding = None
             self.blocks = nn.ModuleList([
                 GPTBlock(
@@ -154,6 +154,9 @@ class DeepHealth(nn.Module):
         other_time: torch.FloatTensor | None = None,
         **unused_kwargs,
     ) -> torch.Tensor:
+        if unused_kwargs:
+            unknown = ", ".join(sorted(unused_kwargs))
+            raise TypeError(f"Unexpected DeepHealth forward arguments: {unknown}")
         if mode not in {"next_token", "all_future"}:
             raise ValueError("mode must be either 'next_token' or 'all_future'")
         if mode == "all_future" and t_query is None:
diff --git a/train.py b/train.py
index 50b7c99..de2a947 100644
--- a/train.py
+++ b/train.py
@@ -20,7 +20,7 @@ import sys
 import time
 from datetime import datetime
 from pathlib import Path
-from typing import Any, Dict, Iterable, Tuple
+from typing import Any, Dict, Tuple
 
 import numpy as np
 import torch
@@ -135,22 +135,6 @@ def load_extra_info_types_file(path: str) -> list[int]:
     return parsed
 
 
-def merge_extra_info_types(*sources: Iterable[int] | None) -> list[int] | None:
-    """Merge optional type-id lists while preserving first-seen order."""
-    merged: list[int] = []
-    seen: set[int] = set()
-    for source in sources:
-        if source is None:
-            continue
-        for raw_type in source:
-            type_id = int(raw_type)
-            if type_id in seen:
-                continue
-            seen.add(type_id)
-            merged.append(type_id)
-    return merged or None
-
-
 def configure_torch_for_training(device: torch.device) -> None:
     """Enable backend settings that can improve training throughput on CUDA."""
     if device.type == "cuda":
@@ -573,19 +557,68 @@ def save_checkpoint(
     torch.save(model.state_dict(), checkpoint_path)
 
 
-def save_config(args: argparse.Namespace, config_path: Path) -> None:
+def save_config(
+    args: argparse.Namespace,
+    config_path: Path,
+    extra: Dict[str, Any] | None = None,
+) -> None:
     """Save training config as JSON."""
-    config_dict = vars(args)
-    # Convert non-serializable types
-    config_dict = {
-        k: str(v) if not isinstance(
-            v, (int, float, str, bool, type(None))) else v
-        for k, v in config_dict.items()
-    }
+    config_dict: Dict[str, Any] = {}
+    for key, value in vars(args).items():
+        if isinstance(value, tuple):
+            config_dict[key] = list(value)
+        elif isinstance(value, list):
+            config_dict[key] = value
+        elif isinstance(value, (int, float, str, bool, type(None))):
+            config_dict[key] = value
+        else:
+            config_dict[key] = str(value)
+    if extra:
+        config_dict.update(extra)
     with open(config_path, "w") as f:
         json.dump(config_dict, f, indent=2)
 
 
+def build_run_metadata(
+    args: argparse.Namespace,
+    dataset: HealthDataset,
+    train_subset: Subset,
+    val_subset: Subset,
+    test_subset: Subset,
+    run_name: str,
+) -> Dict[str, Any]:
+    """Collect resolved training facts needed to rebuild the model for evaluation."""
+    return {
+        "run_name": run_name,
+        "dataset_class": "NextStepHealthDataset",
+        "collate_fn": "next_step_collate_fn",
+        "model_class": "DeepHealth",
+        "model_target_mode": "next_token",
+        "dist_mode": "exponential",
+        "extra_info_types_file": (
+            Path(args.extra_info_types_file).name
+            if args.extra_info_types_file is not None
+            else None
+        ),
+        "extra_info_types": dataset.extra_info_types,
+        "dataset_metadata": {
+            "vocab_size": int(dataset.vocab_size),
+            "n_types": int(dataset.n_types),
+            "n_cont_types": int(dataset.n_cont_types),
+            "n_categories": int(dataset.n_categories),
+            "cont_type_ids": [int(x) for x in dataset.cont_type_ids],
+            "extra_info_types": [int(x) for x in dataset.extra_info_types],
+        },
+        "split_sizes": {
+            "train": int(len(train_subset)),
+            "val": int(len(val_subset)),
+            "test": int(len(test_subset)),
+        },
+        "resolved_readout_name": args.readout_name,
+        "resolved_loss_name": args.loss_name,
+    }
+
+
 def normalize_training_config(args: argparse.Namespace) -> None:
     """Fill in and validate training options that depend on other flags."""
     if args.target_mode not in {"delphi2m", "uts"}:
@@ -661,8 +694,6 @@ def main():
                         help="Time encoding mode for disease history")
     parser.add_argument("--dropout", type=float, default=0.0,
                         help="Dropout rate")
-    parser.add_argument("--extra_info_types", type=int, nargs="*", default=None,
-                        help="Optional list of other-information type ids to include")
     parser.add_argument("--extra_info_types_file", type=str, default=None,
                         help="Optional file containing other-information type ids to include")
 
@@ -715,15 +746,11 @@ def main():
                         help="Device to use for training: cpu, cuda, or cuda:<index>")
 
     args = parser.parse_args()
-    file_extra_info_types = (
+    args.extra_info_types = (
         load_extra_info_types_file(args.extra_info_types_file)
         if args.extra_info_types_file is not None
         else None
     )
-    args.extra_info_types = merge_extra_info_types(
-        args.extra_info_types,
-        file_extra_info_types,
-    )
 
     # ---- Setup ----
     set_seed(args.seed)
@@ -893,7 +920,18 @@ def main():
         raise ValueError(f"Unknown loss: {args.loss_name}")
 
     # ---- Save Config ----
-    save_config(args, run_dir / "train_config.json")
+    save_config(
+        args,
+        run_dir / "train_config.json",
+        extra=build_run_metadata(
+            args=args,
+            dataset=dataset,
+            train_subset=train_subset,
+            val_subset=val_subset,
+            test_subset=test_subset,
+            run_name=run_name,
+        ),
+    )
     logger.info(f"Config saved to {run_dir / 'train_config.json'}")
 
     # ---- Training Loop ----