Upload 3 files

assignment_2.ipynb

@@ -0,0 +1,1321 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "4312be94",
+   "metadata": {},
+   "source": [
+    "# Part A"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "499c83de",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Data already exists in 'patents_data_raw'. Skipping download.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "from huggingface_hub import snapshot_download\n",
+    "\n",
+    "# Check if the folder already exists and is not empty\n",
+    "folder_name = \"patents_data_raw\"\n",
+    "\n",
+    "# Check if folder exists and if it has any files inside\n",
+    "if os.path.exists(folder_name) and any(os.scandir(folder_name)):\n",
+    "    print(f\"Data already exists in '{folder_name}'. Skipping download.\")\n",
+    "    local_folder = os.path.abspath(folder_name)\n",
+    "else:\n",
+    "    #Download only if missing\n",
+    "    print(f\"Downloading dataset files to '{folder_name}'... (This may take a few minutes)\")\n",
+    "    try:\n",
+    "        local_folder = snapshot_download(\n",
+    "            repo_id=\"AI-Growth-Lab/patents_claims_1.5m_traim_test\", \n",
+    "            repo_type=\"dataset\",\n",
+    "            local_dir=folder_name,\n",
+    "            ignore_patterns=[\"*.git*\"]\n",
+    "        )\n",
+    "        print(f\"Success! Files downloaded to: {local_folder}\")\n",
+    "    except Exception as e:\n",
+    "        print(f\"Download failed: {e}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "2a1e5f1b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Found existing processed file: patents_50k_green.parquet\n",
+      "   Skipping filtering and merging to save time.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from datasets import load_dataset, concatenate_datasets, disable_progress_bar\n",
+    "import pandas as pd\n",
+    "import datasets\n",
+    "\n",
+    "# Silience Hugging Face logs for cleaner output\n",
+    "disable_progress_bar()\n",
+    "datasets.utils.logging.set_verbosity_error()\n",
+    "\n",
+    "output_filename = \"patents_50k_green.parquet\"\n",
+    "\n",
+    "# Check if we already did this work\n",
+    "if os.path.exists(output_filename):\n",
+    "    print(f\"Found existing processed file: {output_filename}\")\n",
+    "    print(f\"   Skipping filtering and merging to save time.\")\n",
+    "else:\n",
+    "    print(\"1. Loading dataset from local cache...\")\n",
+    "    # Point to the local folder\n",
+    "    dataset_full = load_dataset(\"./patents_data_raw\", split=\"train\")\n",
+    "\n",
+    "    print(f\"   Dataset loaded. Total rows: {len(dataset_full):,}\")\n",
+    "\n",
+    "    # Identify Green Columns\n",
+    "    all_cols = dataset_full.column_names\n",
+    "    y02_cols = [c for c in all_cols if c.startswith(\"Y02\")]\n",
+    "    print(f\"   Found {len(y02_cols)} Green Patent (Y02) indicator columns.\")\n",
+    "\n",
+    "    # Filtering Logic\n",
+    "    print(\"2. Filtering for 25,000 Green patents...\")\n",
+    "    dataset_green = dataset_full.filter(\n",
+    "        lambda x: any(x[col] == 1 for col in y02_cols),\n",
+    "        num_proc=1\n",
+    "    ).shuffle(seed=42).select(range(25000))\n",
+    "\n",
+    "    print(\"3. Filtering for 25,000 Non-Green patents...\")\n",
+    "    dataset_not_green = dataset_full.filter(\n",
+    "        lambda x: all(x[col] == 0 for col in y02_cols),\n",
+    "        num_proc=1\n",
+    "    ).shuffle(seed=42).select(range(25000))\n",
+    "\n",
+    "    # 4. Add \"is_green_silver\" Labels\n",
+    "    print(\"4. Adding silver labels (0/1)...\")\n",
+    "    dataset_green = dataset_green.map(lambda x: {\"is_green_silver\": 1})\n",
+    "    dataset_not_green = dataset_not_green.map(lambda x: {\"is_green_silver\": 0})\n",
+    "\n",
+    "    # 5. Combine and Save\n",
+    "    print(\"5. Merging and saving final Parquet...\")\n",
+    "    final_dataset = concatenate_datasets([dataset_green, dataset_not_green]).shuffle(seed=42)\n",
+    "    final_dataset.to_parquet(output_filename)\n",
+    "\n",
+    "    print(f\"Success! File saved: {output_filename}\")\n",
+    "    print(f\"Total Balanced Rows: {len(final_dataset):,}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "784cf7cb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Loading patents_50k_green.parquet...\n",
+      " Data Setup Complete\n",
+      "   - train_silver:   2000 rows\n",
+      "   - eval_silver:    5000 rows\n",
+      "   - pool_unlabeled: 43000 rows\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "# 1. Loading the balanced 50k file\n",
+    "print(\"Loading patents_50k_green.parquet...\")\n",
+    "df = pd.read_parquet(\"patents_50k_green.parquet\")\n",
+    "\n",
+    "# Creating the Splits\n",
+    "# - train_silver: Small initial labeled set to train the baseline (e.g., 2,000 - 5,000 rows)\n",
+    "# - eval_silver: Validation set to test performance (e.g., 5,000 rows)\n",
+    "# - pool_unlabeled: The rest, which you will \"mine\" for high-risk examples.\n",
+    "\n",
+    "# Reserve 5,000 for evaluation\n",
+    "df_eval = df.sample(n=5000, random_state=42)\n",
+    "df_remaining = df.drop(df_eval.index)\n",
+    "\n",
+    "# Reserve 2,000 for the initial \"train_silver\"\n",
+    "df_train_silver = df_remaining.sample(n=2000, random_state=42)\n",
+    "df_pool_unlabeled = df_remaining.drop(df_train_silver.index)\n",
+    "\n",
+    "print(\" Data Setup Complete\")\n",
+    "print(f\"   - train_silver:   {len(df_train_silver)} rows\")\n",
+    "print(f\"   - eval_silver:    {len(df_eval)} rows\")\n",
+    "print(f\"   - pool_unlabeled: {len(df_pool_unlabeled)} rows\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "d56051b7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Starting Part A: Baseline Model Training...\n",
+      "   - Loading 50k dataset...\n",
+      "   - Splits created: Train=2000, Eval=5000, Pool=43000\n",
+      "   - Loading PatentSBERTa model...\n",
+      "   - Generating Training embeddings...\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "2c18d825d370452ca1eadd3788063e0c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "      Encoding:   0%|          | 0/63 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "   - Generating Evaluation embeddings...\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "fd3be50181a348c8b8e8688ae3568157",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "      Encoding:   0%|          | 0/157 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "   - Training Logistic Regression...\n",
+      "\n",
+      "=============================================\n",
+      "PART A RESULTS: BASELINE MODEL\n",
+      "=============================================\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "   Not Green       0.74      0.76      0.75      2493\n",
+      "       Green       0.75      0.74      0.75      2507\n",
+      "\n",
+      "    accuracy                           0.75      5000\n",
+      "   macro avg       0.75      0.75      0.75      5000\n",
+      "weighted avg       0.75      0.75      0.75      5000\n",
+      "\n",
+      "---------------------------------------------\n",
+      "Part A Baseline F1-Score: 0.7488\n",
+      "=============================================\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "import torch\n",
+    "from transformers import AutoTokenizer, AutoModel, logging\n",
+    "from sklearn.linear_model import LogisticRegression\n",
+    "from sklearn.metrics import classification_report\n",
+    "from tqdm.auto import tqdm\n",
+    "\n",
+    "# Silence logs\n",
+    "logging.set_verbosity_error()\n",
+    "\n",
+    "print(\"Starting Part A: Baseline Model Training...\")\n",
+    "\n",
+    "# Check for the source file\n",
+    "parquet_file = \"patents_50k_green.parquet\"\n",
+    "if not os.path.exists(parquet_file):\n",
+    "    print(f\"Error: {parquet_file} not found. Please run the Filtering script first.\")\n",
+    "else:\n",
+    "    # Load Data & Create Splits\n",
+    "    print(\"   - Loading 50k dataset...\")\n",
+    "    df = pd.read_parquet(parquet_file)\n",
+    "\n",
+    "    # Creating the Splits (train_silver, eval_silver, pool_unlabeled)\n",
+    "    df_eval = df.sample(n=5000, random_state=42)\n",
+    "    df_remaining = df.drop(df_eval.index)\n",
+    "    df_train = df_remaining.sample(n=2000, random_state=42)\n",
+    "    df_pool = df_remaining.drop(df_train.index)\n",
+    "\n",
+    "    print(f\"   - Splits created: Train={len(df_train)}, Eval={len(df_eval)}, Pool={len(df_pool)}\")\n",
+    "\n",
+    "    # Load PatentSBERTa\n",
+    "    print(\"   - Loading PatentSBERTa model...\")\n",
+    "    model_name = \"AI-Growth-Lab/PatentSBERTa\"\n",
+    "    tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
+    "    model = AutoModel.from_pretrained(model_name)\n",
+    "\n",
+    "    device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
+    "    model.to(device); model.eval()\n",
+    "\n",
+    "    # Helper function with clean progress tracking\n",
+    "    def get_embeddings(text_list, batch_size=32):\n",
+    "        all_embeddings = []\n",
+    "        # We keep the tqdm bar small and clean\n",
+    "        for i in tqdm(range(0, len(text_list), batch_size), desc=\"      Encoding\", leave=False):\n",
+    "            batch_texts = text_list[i:i+batch_size]\n",
+    "            inputs = tokenizer(batch_texts, padding=True, truncation=True, max_length=128, return_tensors=\"pt\").to(device)\n",
+    "            with torch.no_grad():\n",
+    "                outputs = model(**inputs)\n",
+    "                embeddings = outputs.last_hidden_state[:, 0, :].cpu().numpy()\n",
+    "                all_embeddings.append(embeddings)\n",
+    "        return np.vstack(all_embeddings)\n",
+    "\n",
+    "    # Generate Embeddings\n",
+    "    print(\"   - Generating Training embeddings...\")\n",
+    "    X_train = get_embeddings(df_train['text'].tolist())\n",
+    "    y_train = df_train['is_green_silver'].values\n",
+    "\n",
+    "    print(\"   - Generating Evaluation embeddings...\")\n",
+    "    X_eval = get_embeddings(df_eval['text'].tolist())\n",
+    "    y_eval = df_eval['is_green_silver'].values\n",
+    "\n",
+    "    # Train Baseline Classifier\n",
+    "    print(\"   - Training Logistic Regression...\")\n",
+    "    clf = LogisticRegression(max_iter=1000, random_state=42)\n",
+    "    clf.fit(X_train, y_train)\n",
+    "\n",
+    "    # FINAL REPORT OUTPUT\n",
+    "    print(\"\\n\" + \"=\"*45)\n",
+    "    print(\"PART A RESULTS: BASELINE MODEL\")\n",
+    "    print(\"=\"*45)\n",
+    "    y_pred = clf.predict(X_eval)\n",
+    "    report = classification_report(y_eval, y_pred, target_names=['Not Green', 'Green'])\n",
+    "    print(report)\n",
+    "    \n",
+    "    # Store Macro F1 for par D\n",
+    "    report_dict = classification_report(y_eval, y_pred, output_dict=True)\n",
+    "    macro_f1 = report_dict['macro avg']['f1-score']\n",
+    "    \n",
+    "    print(\"-\" * 45)\n",
+    "    print(f\"Part A Baseline F1-Score: {macro_f1:.4f}\")\n",
+    "    print(\"=\"*45)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "99b2f0f6",
+   "metadata": {},
+   "source": [
+    "# Part B"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9a46f788",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--- Starting Part B: Safe Reproduction of Outputs ---\n",
+      "Generating baseline training embeddings...\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "2fc0f419d2aa404ab6e86ca8e20ce7d0",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Encoding:   0%|          | 0/63 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Generating embeddings for 43000 unlabeled examples...\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0d80d393db8542b8af12f15c1d92fddf",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Encoding:   0%|          | 0/1344 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Calculating uncertainty scores...\n",
+      "\n",
+      "========================================\n",
+      "✅ Part B Complete! Outputs successfully shown.\n",
+      "File saved to: hitl_green_100_REPRODUCED.csv\n",
+      "   - Min Uncertainty: 0.9959\n",
+      "   - Max Uncertainty: 1.0000\n",
+      "========================================\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"--- Starting Part B: Safe Reproduction of Outputs ---\")\n",
+    "\n",
+    "# Re-initialize Data & Model\n",
+    "df = pd.read_parquet(\"patents_50k_green.parquet\")\n",
+    "df_eval = df.sample(n=5000, random_state=42)\n",
+    "df_remaining = df.drop(df_eval.index)\n",
+    "df_train = df_remaining.sample(n=2000, random_state=42)\n",
+    "df_pool = df_remaining.drop(df_train.index) #unlabeled pool\n",
+    "\n",
+    "# Re-initialize PatentSBERTa\n",
+    "model_name = \"AI-Growth-Lab/PatentSBERTa\"\n",
+    "tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
+    "model = AutoModel.from_pretrained(model_name)\n",
+    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
+    "model.to(device); model.eval()\n",
+    "\n",
+    "def get_embeddings(text_list, batch_size=32):\n",
+    "    all_embeddings = []\n",
+    "    for i in tqdm(range(0, len(text_list), batch_size), desc=\"Encoding\"):\n",
+    "        batch_texts = text_list[i:i+batch_size]\n",
+    "        inputs = tokenizer(batch_texts, padding=True, truncation=True, max_length=128, return_tensors=\"pt\").to(device)\n",
+    "        with torch.no_grad():\n",
+    "            outputs = model(**inputs)\n",
+    "            all_embeddings.append(outputs.last_hidden_state[:, 0, :].cpu().numpy())\n",
+    "    return np.vstack(all_embeddings)\n",
+    "\n",
+    "# Re-train the Baseline Classifier\n",
+    "print(\"Generating baseline training embeddings...\")\n",
+    "X_train = get_embeddings(df_train['text'].tolist())\n",
+    "clf = LogisticRegression(max_iter=1000, random_state=42)\n",
+    "clf.fit(X_train, df_train['is_green_silver'].values)\n",
+    "\n",
+    "# Generate Embeddings for the Unlabeled Pool\n",
+    "print(f\"Generating embeddings for {len(df_pool)} unlabeled examples...\")\n",
+    "X_pool = get_embeddings(df_pool['text'].tolist())\n",
+    "\n",
+    "# Predict Probabilities and Uncertainty\n",
+    "print(\"Calculating uncertainty scores...\")\n",
+    "probs = clf.predict_proba(X_pool)[:, 1]\n",
+    "uncertainty_scores = 1 - 2 * np.abs(probs - 0.5)\n",
+    "\n",
+    "df_pool['p_green'] = probs\n",
+    "df_pool['u'] = uncertainty_scores\n",
+    "\n",
+    "# Select Top 100\n",
+    "df_high_risk = df_pool.sort_values(by='u', ascending=False).head(100)\n",
+    "\n",
+    "# Format for Export (Changed filename to be safe)\n",
+    "if 'id' in df_high_risk.columns:\n",
+    "    df_high_risk = df_high_risk.rename(columns={'id': 'doc_id'})\n",
+    "else:\n",
+    "    df_high_risk['doc_id'] = df_high_risk.index\n",
+    "\n",
+    "for col in ['llm_green_suggested', 'llm_confidence', 'llm_rationale', 'is_green_human', 'notes']:\n",
+    "    df_high_risk[col] = \"\"\n",
+    "\n",
+    "final_columns = ['doc_id', 'text', 'p_green', 'u', 'llm_green_suggested', 'llm_confidence', 'llm_rationale', 'is_green_human', 'notes']\n",
+    "\n",
+    "# Due to keral restart, a second file which is not used in the next steps is created to avoid confusion. The file is named \"hitl_green_100_REPRODUCED.csv\" to indicate that it is a reproduction of the original \"hitl_green_100.csv\" file, but with a different name to prevent any accidental overwriting or confusion with the original file that may have been generated before the kernel restart.\n",
+    "safe_filename = \"hitl_green_100_REPRODUCED.csv\"\n",
+    "df_high_risk[final_columns].to_csv(safe_filename, index=False)\n",
+    "\n",
+    "print(\"\\n\" + \"=\"*40)\n",
+    "print(f\"Part B Complete! Outputs successfully shown.\")\n",
+    "print(f\"File saved to: {safe_filename}\")\n",
+    "print(f\"   - Min Uncertainty: {df_high_risk['u'].min():.4f}\")\n",
+    "print(f\"   - Max Uncertainty: {df_high_risk['u'].max():.4f}\")\n",
+    "print(\"=\"*40)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6317d3a4",
+   "metadata": {},
+   "source": [
+    "# Part C"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8a7f1e12",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--- Part C: HITL Labeling ---\n",
+      "Remaining rows: 68\n",
+      "-----------------------------\n",
+      "\n",
+      "[Row 33] (Uncertainty: 0.9984)\n",
+      "CLAIM: 1. A method of increasing light extraction from a light-emitting diode (LED) device comprising; forming a first n-doped layer on a carrier substrate; forming a Si forming a second n-doped layer on the Si forming an active layer configured to emit light on the second n-doped layer; forming a p-doped ...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim concerns LED light‑emission enhancement, not climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 34] (Uncertainty: 0.9984)\n",
+      "CLAIM: 1. A method comprising: identifying valuation data comprising a plurality of estimated asset values corresponding to one or more of location information and property type; identifying a group of two or more characteristics, wherein for each respective real estate investment trust of a plurality of r...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim concerns financial weighting of real estate trusts, not climate mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 35] (Uncertainty: 0.9983)\n",
+      "CLAIM: 1. A construction machine, comprising: a lower travel body; an upper slewing body mounted on the lower travel body and having an engine compartment; an engine compartment cover which covers the engine compartment of the upper slewing body; an air filter which collects dust included in outside air ta...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes an air filter system for a construction machine, which does not relate to green or climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 36] (Uncertainty: 0.9983)\n",
+      "CLAIM: 1. A semiconductor device including a plurality of operation circuits executing operation in synchronization with a clock signal comprising: a control unit for outputting first operation control information and second operation control information for controlling operation executed by the plurality ...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a generic semiconductor device architecture without any reference to environmental impact or climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 37] (Uncertainty: 0.9983)\n",
+      "CLAIM: 1. A method of forming a layer over a substrate, the method comprising: receiving data identifying a desired thickness of the layer; using a processor to generate instructions for a printing mechanism to deposit droplets of ink onto the substrate according to the data, the ink carrying material to f...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a printing method for depositing ink layers, unrelated to climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 38] (Uncertainty: 0.9982)\n",
+      "CLAIM: 1. An insulated-gate bipolar transistor (IGBT) in a semiconductor substrate, said IGBT comprising: a collector at a bottom surface of said semiconductor substrate, a drift region having a first conductivity type situated over said collector, and a base layer having a second conductivity type opposit...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a semiconductor device structure, not a technology for greenhouse gas mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 39] (Uncertainty: 0.9981)\n",
+      "CLAIM: 1. A method of joining two or more articles via slender nanomaterials embedded in a joining medium and interlinked together, the method involving: (i) dispersion of nanomaterials comprising at least one of carbon nanotubes and nanofibers within a solvent, with the weight percent of said nanomaterial...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a nanomaterial-based joining method, which is unrelated to greenhouse‑gas reduction or climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 40] (Uncertainty: 0.9981)\n",
+      "CLAIM: 1. A compound having a structure represented by a chemical formula described below:...\n",
+      "------------------------------------------------------------\n",
+      "Asking LM Studio...\n",
+      "LLM output invalid JSON: <|channel|>final <|constrain|>JSON<|message|>{\"suggestion\":0,\"confidence\":\"Low\",\"rationale\":\"The claim merely describes a chemical compound without indicating any environmental or climate‑related application.\"}\n",
+      "LLM Failed (Check settings or Label Manually)\n",
+      "Saved.\n",
+      "\n",
+      "[Row 41] (Uncertainty: 0.9981)\n",
+      "CLAIM: 1. A computer-implemented process comprising: executing, by a computer processor, at least two read threads to read a block of data from a database, each of the read threads having a first wait stat and a second wait stat, the read threads configured to compress data using a dynamic compression rati...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a data compression and backup process, unrelated to climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 42] (Uncertainty: 0.9980)\n",
+      "CLAIM: 1. A rotor for a Wankel engine comprising: two axially spaced apart end faces having a generally triangular profile with outwardly arched sides and three circumferentially spaced apex portions; a peripheral face extending between the end faces and defining three flanks, each flank extending between ...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a mechanical component for a Wankel engine and does not relate to greenhouse gas mitigation or climate change technologies.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 43] (Uncertainty: 0.9980)\n",
+      "CLAIM: 1. A housing apparatus, comprising: a housing casing which surrounds a first cavity and which has multiple side surfaces; a volute housing arranged in an interior of the housing casing, said volute housing having a central through opening for accommodating a compressor wheel of a rotor and for suppl...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (Medium) | Rationale: The claim describes a housing apparatus for a compressor wheel, which is unrelated to green or climate change mitigation technologies.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 44] (Uncertainty: 0.9979)\n",
+      "CLAIM: 1. A biodegradable container for a semi-solid composition, comprising: a tube portion comprising a first paper that defines first, second, and third plies forming an open end and a closed end, and a lumen containing the semi-solid composition, wherein the tube portion further comprises a continuous ...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 1 (High) | Rationale: The claim describes a fully biodegradable container, indicating an environmental benefit aligned with Green/Climate Change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 45] (Uncertainty: 0.9979)\n",
+      "CLAIM: 1. An isolated green sulfur bacterium Chlorobaculum limnaeum strain RK-j-1 deposited at National Institute of Technology and Evaluation Patent Microorganisms Depositary (NPMD) as accession number NITE BP-1202....\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (Medium) | Rationale: The claim merely describes isolation of a microorganism without any stated application to climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 46] (Uncertainty: 0.9979)\n",
+      "CLAIM: 1. A method for communicating over allocated resources, comprising: receiving a resource allocation comprising a portion of a resource block over a plurality of bundled transmission time intervals, wherein the portion of the resource block comprises a subset of subcarriers in the resource block with...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a telecommunications resource allocation method, unrelated to Green/Climate Change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 47] (Uncertainty: 0.9979)\n",
+      "CLAIM: 1. A switch system, comprising: a plurality of nodes, wherein each node includes a computational processor and an embedded switch; a plurality of links associated with each node, wherein the plurality of links are configured to connect nodes in the plurality of nodes to create a topology of a switch...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a network switch architecture, unrelated to climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 48] (Uncertainty: 0.9977)\n",
+      "CLAIM: 1. A seed of soybean cultivar S100323, wherein a representative of sample seed of said cultivar is deposited under ATCC Accession No. PTA-12317....\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim concerns a soybean seed deposit, not climate‑change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 49] (Uncertainty: 0.9976)\n",
+      "CLAIM: 1. A method to accelerate particles into a chamber, comprising: distributing a fluidic substance between electrodes configured at a location proximate a chamber, the electrodes comprising a low work function material; generating a current of ionized particles by applying an electric field between th...\n",
+      "------------------------------------------------------------\n",
+      "Asking LM Studio...\n",
+      "LLM output invalid JSON: <|channel|>final <|constrain|>JSON<|message|>{\"suggestion\":0,\"confidence\":\"High\",\"rationale\":\"The claim describes a particle acceleration method unrelated to greenhouse gas reduction.\"}\n",
+      "LLM Failed (Check settings or Label Manually)\n",
+      "Saved.\n",
+      "\n",
+      "[Row 50] (Uncertainty: 0.9976)\n",
+      "CLAIM: 1. A biogenic flocculant composition for CEPT sludge conditioning comprising a) a first flocculant component which comprises at least one acidophilic auto-trophic iron-oxidizing bacterium and at least one species of acid tolerant organotrophic microbes which are grown in medium containing iron (II) ...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (Medium) | Rationale: The claim focuses on sludge conditioning using microbial flocculants, which is a wastewater treatment application rather than a direct climate‑change mitigation technology.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 51] (Uncertainty: 0.9975)\n",
+      "CLAIM: 1. A nuclear reactor comprising: an elongated reactor vessel enclosed at a lower end and having an open upper end on which an annular flange is formed and a central axis extending, along an elongated dimension; a reactor vessel head having an annular portion on an underside of the bead that is machi...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a nuclear reactor component, not a climate‑change mitigation technology.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 52] (Uncertainty: 0.9975)\n",
+      "CLAIM: 1. A steam reforming system comprising: a) a kiln, comprising a susceptor tube; a kiln inlet for receiving a feedstock; a conveyor for transporting said feedstock through said kiln; b) a steam reforming reactor comprising a reformer tube; a reactor inlet in fluid communication with said first kiln o...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (Medium) | Rationale: The claim describes a steam reforming system for gas production, which is a general chemical process and does not explicitly address greenhouse gas reduction or climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 53] (Uncertainty: 0.9975)\n",
+      "CLAIM: 1. A pest trap reporting system, comprising: a plurality of pest traps, wherein each pest trap encloses, retains or kills one or more non-human pests; a pest report database that includes pest activity information for the plurality of pest traps; a plurality of sensors, each of the plurality of sens...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a pest monitoring system, not related to greenhouse gas mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 54] (Uncertainty: 0.9974)\n",
+      "CLAIM: 1. A motor vehicle comprising: a body; a wheel rotatably supported on the body; an occupant riding portion supported by the body for tilting relative to the body and mounted with an occupant; occupant attitude detection means for detecting an attitude of the occupant riding portion; body attitude de...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a vehicle tilt-control system unrelated to greenhouse‑gas reduction or climate mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 55] (Uncertainty: 0.9973)\n",
+      "CLAIM: 1. A compound having Formula (III) or a therapeutically acceptable salt thereof, wherein...\n",
+      "------------------------------------------------------------\n",
+      "Asking LM Studio...\n",
+      "LLM output invalid JSON: <|channel|>final <|constrain|>JSON<|message|>{\"suggestion\":0,\"confidence\":\"High\",\"rationale\":\"The claim describes a chemical compound for therapeutic use, not related to green or climate change mitigation.\"}\n",
+      "LLM Failed (Check settings or Label Manually)\n",
+      "Saved.\n",
+      "\n",
+      "[Row 56] (Uncertainty: 0.9973)\n",
+      "CLAIM: 1. A method for fabricating a semiconductor device, comprising: forming a conductive layer over first and second regions of a semiconductor substrate; forming a trench extended in the first region of the semiconductor substrate through the conductive layer; forming a first gate electrode in the tren...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes semiconductor fabrication steps, unrelated to Green/Climate Change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 57] (Uncertainty: 0.9972)\n",
+      "CLAIM: 1. A method for installation of an offshore wind turbine, characterized in comprising the steps of: prefabrication of a foundation, including: fabricating the foundation which includes a plurality of tanks providing buoyant force and uprighting force to the foundation so as to keep the foundation up...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 1 (High) | Rationale: The claim describes a method for installing an offshore wind turbine, which is a renewable energy technology that mitigates climate change.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 58] (Uncertainty: 0.9972)\n",
+      "CLAIM: 1. An airfoil comprising: an airfoil body made of a first material with a leading edge, trailing edge, pressure side and suction side; a sheath with first and second flanks made of a second material; a first shim disposed between a portion of an end of the first flank and the airfoil body and extend...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (Medium) | Rationale: The claim describes structural components of an airfoil without reference to energy efficiency, emissions reduction, or other climate‑change mitigation measures.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 59] (Uncertainty: 0.9972)\n",
+      "CLAIM: 1. An electric storage system comprising: a plurality of electric storage blocks connected in series, each of the plurality of electric storage blocks including a plurality of electric storage elements connected in parallel; a plurality of current breakers, each of the plurality of current breakers ...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (Medium) | Rationale: The claim describes a battery management system, not a direct green or climate change mitigation technology.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 60] (Uncertainty: 0.9972)\n",
+      "CLAIM: 1. A method for performing operations on a stainer in a stainer network comprising: providing a robotic arm coupled to the stainer, the robotic arm having a reagent dispenser; establishing a network connection between a computer and a stainer in the stainer network; sending requests from the compute...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes laboratory automation for sample processing, not a technology related to greenhouse gas mitigation or climate change.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 61] (Uncertainty: 0.9971)\n",
+      "CLAIM: 1. A Group III nitride semiconductor light-emitting device, comprising: a conductive support; a p-electrode disposed on the support; a semiconductor layer disposed on the p-electrode, the semiconductor layer comprising at least a p-layer, a light-emitting layer, and an n-layer disposed in this order...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a semiconductor light-emitting device, which is unrelated to green or climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 62] (Uncertainty: 0.9971)\n",
+      "CLAIM: 1. A plate heat exchanger in a sealed design, with: a stacked arrangement comprising: a front-side and a rear-side end plate, wherein at least one end plate is constituted as a connection plate having at least one connection, heat exchanger plates which are arranged and stacked between the front-sid...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a mechanical design for a plate heat exchanger and does not address energy efficiency or climate‑change mitigation technologies.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 63] (Uncertainty: 0.9971)\n",
+      "CLAIM: 1. A vehicle braking/driving force control system comprising: a braking/driving force generating mechanism that causes each wheel of a vehicle to generate driving force or braking force independently of one another; a suspension mechanism that couples each of the wheels that are not supported by spr...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a vehicle braking and driving force control system, which is unrelated to greenhouse gas mitigation or climate change technologies.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 64] (Uncertainty: 0.9970)\n",
+      "CLAIM: 1. A detector apparatus configured to receive light and generate electrical signals, the detector apparatus comprising: a light sensor having a light incidence side, the light sensor including at least one photocathode; a cooling component, the cooling component being in direct contact, on the light...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a light detection device, not related to climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 65] (Uncertainty: 0.9970)\n",
+      "CLAIM: 1. A flexible display device comprising: a display panel configured to generate an image; and a window member on the display panel, the window member comprising: wherein a width of each of the second parts is smaller than a width of the first part at a bending area....\n",
+      "------------------------------------------------------------\n",
+      "Asking LM Studio...\n",
+      "LLM output invalid JSON: <|channel|>final <|constrain|>JSON<|message|>{\"suggestion\":0,\"confidence\":\"High\",\"rationale\":\"The claim describes a flexible display device, which is unrelated to Green/Climate Change mitigation.\"}\n",
+      "LLM Failed (Check settings or Label Manually)\n",
+      "Saved.\n",
+      "\n",
+      "[Row 66] (Uncertainty: 0.9969)\n",
+      "CLAIM: 1. A conductive film comprising: a substrate; a transparent electrode layer provided on the substrate; and a conductive pattern layer provided on the transparent electrode layer, wherein the conductive pattern layer includes a metal nitride pattern layer including CuNx, x is a mass ratio of N with r...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a conductive film for electronic applications, with no indication of greenhouse gas reduction or climate mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 67] (Uncertainty: 0.9969)\n",
+      "CLAIM: 1. A hydrolysable linker selected from a compound of formula V, VI, VII, and VIII: wherein: R′ and R″ are each independently a C each a is independently an integer from 0 to 6; each b is independently an integer from 1 to 6; each X is independently: each X each Y is independently: each Y each m, n, ...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (Low) | Rationale: The claim describes a chemical linker, with no indication of climate‑change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 68] (Uncertainty: 0.9968)\n",
+      "CLAIM: 1. A substrate bearing a stack of layers as the back contact in a molybdenum photovoltaic device, said back contact comprising in order from the substrate: a barrier layer comprising at least one of: Si a primer layer; a layer of ZnO; and a layer of molybdenum, wherein the molybdenum is deposited di...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 1 (High) | Rationale: The claim describes a photovoltaic device structure, which is directly relevant to solar energy technology for climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 69] (Uncertainty: 0.9968)\n",
+      "CLAIM: 1. A system comprising: a foil including a leading inlet for fluid to enter, a forward chamber within the foil downstream of the leading inlet, a rearward chamber within the foil downstream of the forward chamber, and a constriction formed by the foil between the forward and rearward chambers; at le...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a fluid flow device without any explicit reference to environmental or climate‑change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 70] (Uncertainty: 0.9967)\n",
+      "CLAIM: 1. A method for passivating a surface of crystalline iron disulfide, comprising: sputtering iron disulfide to form a layer of crystalline iron disulfide on a substrate, wherein the layer has a surface comprising crystal surfaces; and depositing a capping layer of epitaxial zinc sulfide onto the surf...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim concerns surface passivation of iron disulfide, not a technology for greenhouse gas mitigation or climate change.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 71] (Uncertainty: 0.9967)\n",
+      "CLAIM: 1. A brake control apparatus, comprising: a frictional braking unit configured to generate frictional braking force by supplying operating fluid to a wheel cylinder provided on each wheel of a vehicle to press a frictional member against the wheel; a regenerative braking unit configured to generate ...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a brake control apparatus for vehicles, which is unrelated to Green/Climate Change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 72] (Uncertainty: 0.9966)\n",
+      "CLAIM: 1. A circuit for recording a magnitude of an electrostatic discharge (ESD) event during semiconductor assembly, the circuit comprising: a voltage divider connected between a first potential and a second potential, the voltage divider configured to provide a first node having a discrete voltage level...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes an ESD recording circuit for semiconductor manufacturing, which does not pertain to greenhouse gas mitigation or climate change technologies.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 73] (Uncertainty: 0.9966)\n",
+      "CLAIM: 1. A rectifier, comprising: a first rectification unit having an anode and a cathode, the anode being connected to a negative radio frequency (RF) port, and the cathode being connected to a positive direct current (DC) port; a second rectification unit having an anode and a cathode, the anode being ...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a rectifier circuit, unrelated to climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 74] (Uncertainty: 0.9966)\n",
+      "CLAIM: 1. An apparatus comprising: a first electronic device to communicate with a second electronic device, the first device comprising:...\n",
+      "------------------------------------------------------------\n",
+      "Asking LM Studio...\n",
+      "LLM output invalid JSON: <|channel|>final <|constrain|>JSON<|message|>{\"suggestion\":0,\"confidence\":\"High\",\"rationale\":\"The claim describes a generic communication apparatus between electronic devices, with no reference to environmental or climate-related functions.\"}\n",
+      "LLM Failed (Check settings or Label Manually)\n",
+      "Saved.\n",
+      "\n",
+      "[Row 75] (Uncertainty: 0.9966)\n",
+      "CLAIM: 1. A process-based method of detecting a CO 2 gas leak in a deep geologic gas storage reservoir, the method comprising: constructing a gas sampling station in a vadose zone proximal to the deep geologic gas storage reservoir; measuring a CO measuring an O measuring a CH measuring a N determining a H...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 1 (High) | Rationale: The method detects CO₂ leaks from a geological storage site, directly supporting carbon sequestration efforts.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 76] (Uncertainty: 0.9965)\n",
+      "CLAIM: 1. A self-supporting reflector for a parabolic trough: (a) having a reflectance of at least 90%, based on the solar spectrum; (b) comprising at least one layer of a transparent plastic material facing a light source and having a layer thickness within a range of from 0.1 mm to 8 mm; and (c) at least...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 1 (High) | Rationale: The claim describes a component for a parabolic trough solar collector, which is a renewable energy technology used to mitigate climate change.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 77] (Uncertainty: 0.9965)\n",
+      "CLAIM: 1. A valve train system for an internal combustion engine having a combustion chamber with a piston which reciprocates therewithin between a top-dead-center position and a bottom-dead-center position, said valve train system comprising: an intake valve which moves between an intake closed position a...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a conventional valve train for an internal combustion engine, which is unrelated to Green/Climate Change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 78] (Uncertainty: 0.9965)\n",
+      "CLAIM: 1. An organic light-emitting diode (OLED) display, comprising: a first plastic layer; a first barrier layer formed over the first plastic layer; a first intermediate layer formed over the first barrier layer, wherein the first intermediate layer comprises amorphous silicon; a second plastic layer fo...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes an OLED display structure, which does not relate to Green/Climate Change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 79] (Uncertainty: 0.9965)\n",
+      "CLAIM: 1. A wave activated power generating device, comprising: a support frame; a buoy vertically positioned to rise and fall relative to motion of waves impacting the buoy and the support frame, the buoy being formed with a hollow interior space; a rack and pinion structure operatively connected between ...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 1 (High) | Rationale: The claim describes a wave‑powered generator that converts ocean wave motion into electricity, which is a renewable energy technology for climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 80] (Uncertainty: 0.9964)\n",
+      "CLAIM: 1. A method for reducing an amount of unwanted living organisms within an algae cultivation fluid, the algae cultivation fluid including wanted living algae of genus Nannochloropsis , the method comprising: subjecting the algae cultivation fluid, the algae cultivation fluid including the wanted livi...\n",
+      "------------------------------------------------------------\n",
+      "Asking LM Studio...\n",
+      "LLM output invalid JSON: <|channel|>final <|constrain|>JSON<|message|>{\"suggestion\":1,\"confidence\":\"Medium\",\"rationale\":\"The\n",
+      "LLM Failed (Check settings or Label Manually)\n",
+      "Saved.\n",
+      "\n",
+      "[Row 81] (Uncertainty: 0.9964)\n",
+      "CLAIM: 1. A compound having Formula (I): wherein, R R b) —(CH R X is —O, NH or S; Y is a cleavable or non-cleavable linker group; and Z is an antigen derived from an infectious agent or a tumor antigen or a pharmaceutically acceptable salt thereof....\n",
+      "------------------------------------------------------------\n",
+      "Asking LM Studio...\n",
+      "LLM output invalid JSON: <|channel|>final <|constrain|>json<|message|>{\"suggestion\":0,\"confidence\":\"High\",\"rationale\":\"The claim concerns a pharmaceutical compound for medical use, not related to climate change mitigation.\"}\n",
+      "LLM Failed (Check settings or Label Manually)\n",
+      "Saved.\n",
+      "\n",
+      "[Row 82] (Uncertainty: 0.9964)\n",
+      "CLAIM: 1. A memory controller comprising: driver circuitry to output a first timing signal to a memory device, the first timing signal to time transmission of a data signal from the memory device to the memory controller; control circuitry to enable oscillation of the first timing signal at a first frequen...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a memory controller’s timing and clock circuitry, unrelated to climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 83] (Uncertainty: 0.9964)\n",
+      "CLAIM: 1. A rubber composition, comprising, based on 100% by mass of a rubber component: 5 to 55% by mass of a copolymer (A) of an aromatic vinyl compound and a conjugated diene compound, the copolymer (A) having an aromatic vinyl compound content of 5-14% by mass and a vinyl bond content in the conjugated...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a rubber composition and silica filler, not a technology for greenhouse gas mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 84] (Uncertainty: 0.9963)\n",
+      "CLAIM: 1. A method of preparing a metal suboxide, comprising: preparing a mixture including a metal suboxide precursor, an aromatic compound substituted with a hydroxy group, and a linking precursor including one selected from a C1 to C30 aldehyde, a C3 to C30 ketone, and a combination thereof; reacting th...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (Low) | Rationale: The claim describes a chemical synthesis method, not directly related to climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 85] (Uncertainty: 0.9963)\n",
+      "CLAIM: 1. A vehicle hydraulic control device including: an oil pump that is driven by a driving force source for wheels; and an oil passage that guides oil discharged from the oil pump to a rotating electrical machine that forms at least a part of the driving force source and a gear mechanism to which driv...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (Medium) | Rationale: The claim describes a hydraulic control system for a vehicle, which does not directly address greenhouse gas reduction or climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 86] (Uncertainty: 0.9963)\n",
+      "CLAIM: 1. A method for the production of a human or animal nutrition product comprising producing an adsorbate suitable for human or animal nutrition comprising applying a component to a carrier using at least one stabilizer such that the component is adsorbed to the carrier, wherein the carrier has a mean...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim concerns a nutritional adsorbate production method, not a technology for greenhouse gas reduction or climate mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 87] (Uncertainty: 0.9963)\n",
+      "CLAIM: 1. An automated driving system, comprising: one or more sensors disposed on an autonomous vehicle; and a computing device in communication with the one or more sensors, comprising:...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (Low) | Rationale: The claim describes a general automated driving system without explicit reference to environmental or climate mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 88] (Uncertainty: 0.9963)\n",
+      "CLAIM: 1. A memory device, comprising: an array of memory cells, the memory cells in the array being programmable to at least two different charge levels; and a control logic unit coupled to the array of memory cells and configured to program the memory cells in each of a plurality of groups with a respect...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a memory device and programming logic, unrelated to climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 89] (Uncertainty: 0.9963)\n",
+      "CLAIM: 1. An adjustable solar panel mounting assembly comprising: a. a first clamp further comprising an upper and lower portion wherein the lower portion further comprises a cavity; b. a first mounting plate extending outward from the lower portion of the first clamp to an end; c. a first flange extending...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 1 (High) | Rationale: The claim describes a solar panel mounting assembly, which supports renewable energy generation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 90] (Uncertainty: 0.9963)\n",
+      "CLAIM: 1. A method of planting or seeding multiple types of seed in a single planting pass during row-crop planting or seeding of an agricultural field with an agricultural implement, the method comprising: storing seeds of multiple types including at least a first type and a second type in multiple compar...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (Medium) | Rationale: The claim describes a multi‑seed planting method, which is an agricultural technique but does not directly address greenhouse gas reduction or climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 91] (Uncertainty: 0.9963)\n",
+      "CLAIM: 1. A method to update a cache in a multi-core processor, the method comprising: receiving a notification of a cache miss associated with a process or a thread running on a single core of the multi-core processor, the single core including: determining that an address associated with the cache miss c...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim concerns processor cache management, unrelated to climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 92] (Uncertainty: 0.9962)\n",
+      "CLAIM: 1. A driving method of a liquid crystal display device comprising a liquid crystal element, the driving method comprising the steps of: applying a first voltage to the liquid crystal element in a first subframe period of a first frame period; making transmittance of the liquid crystal element at the...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a technical method for controlling liquid crystal display operation, with no reference to energy efficiency or climate‑change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 93] (Uncertainty: 0.9962)\n",
+      "CLAIM: 1. A compound of Formula IA: wherein X R R wherein each R each R where Z wherein the alkyl, alkenyl, alkynyl, cycloalkyl, aryl, heterocyclic, or heteroaryl groups of Z wherein Y indicates one or more optional double bonds; and n is 0, 1, 2, or 3; R each R wherein the alkyl, alkenyl, alkynyl, cycloal...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a generic chemical structure for a potential pharmaceutical compound with no reference to environmental or climate‑change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 94] (Uncertainty: 0.9962)\n",
+      "CLAIM: 1. A valve for a fuel cell comprising: a housing; a first pressure chamber and a second pressure chamber provided in the housing; two supply/discharge tubes connected to the housing, and supplying and discharging fluid to and from the first pressure chamber and the second pressure chamber, respectiv...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 1 (Medium) | Rationale: The claim describes a valve for a fuel cell, which is a technology used in clean energy generation and thus relates to green/climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 95] (Uncertainty: 0.9962)\n",
+      "CLAIM: 1. A wing comprising: an airfoil section including a leading edge, a trailing edge, an upper surface and a lower surface, wherein a region within the airfoil section immediately adjacent the leading edge is ventilated via one or more vent openings which open in the upper surface to establish a sub-s...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a wing ventilation system for aerodynamic performance, not climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 96] (Uncertainty: 0.9962)\n",
+      "CLAIM: 1. An input device comprising: a touch panel that includes M (where M is a natural number of 5 or more) driving electrodes, and a plurality of detection electrodes forming capacitances between the respective driving electrodes, in which the M driving electrodes and the plurality of detection electro...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a touch panel input device, unrelated to green or climate‑change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 97] (Uncertainty: 0.9961)\n",
+      "CLAIM: 1. An information display system in a transportation apparatus, the information display system comprises: a liquid crystal display (LCD) screen that occupies at least a portion of a dashboard of the transportation apparatus, wherein the LCD screen is capable of graphically displaying multiple inform...\n",
+      "------------------------------------------------------------\n",
+      "Asking LM Studio...\n",
+      "LLM output invalid JSON: <|channel|>final <|constrain|>JSON<|message|>{\"suggestion\":0,\"confidence\":\"High\",\"rationale\":\"The claim describes an information display system for a vehicle dashboard, which does not directly address greenhouse gas reduction or climate change mitigation.\"}\n",
+      "LLM Failed (Check settings or Label Manually)\n",
+      "Saved.\n",
+      "\n",
+      "[Row 98] (Uncertainty: 0.9960)\n",
+      "CLAIM: 1. A photovoltaic (PV) device, comprising: at least one PV interband cascade (IC PV) stage having a conduction band and a valence band, comprising: wherein the absorption region is positioned between the intraband transport region and the interband tunneling region, wherein the interband tunneling r...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 1 (High) | Rationale: The claim describes a photovoltaic device for generating electricity from light.\n",
+      "Saved.\n",
+      "\n",
+      "[Row 99] (Uncertainty: 0.9960)\n",
+      "CLAIM: 1. A rack system comprising: a plurality of trays configured to hold a respective plurality of battery-powered unmanned aerial vehicles; and a frame configured to support the plurality of trays in a vertical arrangement, wherein each tray of the plurality of trays comprises:...\n",
+      "------------------------------------------------------------\n",
+      "Asking LM Studio...\n",
+      "LLM output invalid JSON: <|channel|>final <|constrain|>JSON<|message|>{\"suggestion\":0,\"confidence\":\"Medium\",\"rationale\":\"The claim describes a storage rack for battery-powered UAVs, which does not directly address green or climate change mitigation technologies.\"}\n",
+      "LLM Failed (Check settings or Label Manually)\n",
+      "Saved.\n",
+      "\n",
+      "[Row 100] (Uncertainty: 0.9959)\n",
+      "CLAIM: 1. A DC electrical machine comprising: an armature having a non-integer number of winding slots per pole-pair of a magnetic field of a field means, each winding slot having a phase angle, wherein the phase angle is electrical and is a position of the winding slot in relation to a fundamental wavefor...\n",
+      "------------------------------------------------------------\n",
+      "LLM Says: 0 (High) | Rationale: The claim describes a technical improvement to a DC electrical machine, unrelated to climate change mitigation.\n",
+      "Saved.\n",
+      "\n",
+      "Done\n"
+     ]
+    }
+   ],
+   "source": [
+    "import requests\n",
+    "\n",
+    "# LLM model is locally hosted via network via LM Studio.\n",
+    "LM_STUDIO_URL = \"http://localhost:1234/v1/chat/completions\"\n",
+    "\n",
+    "# GPT-OSS-20B is run locally\n",
+    "MODEL_NAME = \"local-model\" \n",
+    "\n",
+    "filename = \"hitl_green_100.csv\"\n",
+    "\n",
+    "def get_llm_response_lmstudio(claim_text):\n",
+    "    \"\"\"Function to call LM Studio with Error Printing\"\"\"\n",
+    "    \n",
+    "    system_prompt = \"\"\"\n",
+    "    You are a patent classification AI. You must respond in valid JSON format only.\n",
+    "    Schema:\n",
+    "    {\n",
+    "        \"suggestion\": 0 or 1,\n",
+    "        \"confidence\": \"Low\", \"Medium\", or \"High\",\n",
+    "        \"rationale\": \"short sentence\"\n",
+    "    }\n",
+    "    \"\"\"\n",
+    "    \n",
+    "    user_prompt = f\"\"\"\n",
+    "    Analyze this patent claim. Is it related to Green/Climate Change mitigation (Y02)?\n",
+    "    Claim: \"{claim_text[:2000]}\"\n",
+    "    \"\"\"\n",
+    "\n",
+    "    payload = {\n",
+    "        \"model\": MODEL_NAME,\n",
+    "        \"messages\": [\n",
+    "            {\"role\": \"system\", \"content\": system_prompt},\n",
+    "            {\"role\": \"user\", \"content\": user_prompt}\n",
+    "        ],\n",
+    "        \"temperature\": 0.1, \n",
+    "        \"max_tokens\": 150\n",
+    "    }\n",
+    "\n",
+    "    try:\n",
+    "        response = requests.post(LM_STUDIO_URL, json=payload, headers={\"Content-Type\": \"application/json\"})\n",
+    "        \n",
+    "        #DEBUGGING BLOCK\n",
+    "        if response.status_code == 200:\n",
+    "            result = response.json()\n",
+    "            \n",
+    "            # Check if the server sent an error instead of an answer\n",
+    "            if 'choices' not in result:\n",
+    "                print(f\"\\n LM STUDIO ERROR: {result}\")\n",
+    "                return None\n",
+    "                \n",
+    "            content = result['choices'][0]['message']['content']\n",
+    "            \n",
+    "            # Clean up code blocks if present\n",
+    "            if \"```\" in content:\n",
+    "                content = content.replace(\"```json\", \"\").replace(\"```\", \"\").strip()\n",
+    "            \n",
+    "            try:\n",
+    "                return json.loads(content)\n",
+    "            except json.JSONDecodeError:\n",
+    "                print(f\"\\nLLM output invalid JSON: {content}\")\n",
+    "                return None\n",
+    "        else:\n",
+    "            print(f\"Server Error {response.status_code}: {response.text}\")\n",
+    "            return None\n",
+    "            \n",
+    "    except Exception as e:\n",
+    "        print(f\"Connection Error: {e}\")\n",
+    "        return None\n",
+    "\n",
+    "def labeling_loop():\n",
+    "    if not os.path.exists(filename):\n",
+    "        print(f\"Error: {filename} not found.\")\n",
+    "        return\n",
+    "    \n",
+    "    df = pd.read_csv(filename)\n",
+    "    \n",
+    "    # Create columns if missing\n",
+    "    for col in ['llm_green_suggested', 'llm_confidence', 'llm_rationale', 'is_green_human', 'notes']:\n",
+    "        if col not in df.columns: df[col] = \"\"\n",
+    "\n",
+    "    # Find empty rows\n",
+    "    remaining_indices = df[df['is_green_human'].isna() | (df['is_green_human'] == \"\")].index.tolist()\n",
+    "    \n",
+    "    print(f\"--- Part C: HITL Labeling ---\")\n",
+    "    print(f\"Remaining rows: {len(remaining_indices)}\")\n",
+    "    print(\"-----------------------------\\n\")\n",
+    "\n",
+    "    for idx in remaining_indices:\n",
+    "        row = df.loc[idx]\n",
+    "        claim_text = str(row['text'])\n",
+    "        \n",
+    "        print(f\"[Row {idx+1}] (Uncertainty: {row['u']:.4f})\")\n",
+    "        print(f\"CLAIM: {claim_text[:300]}...\") \n",
+    "        print(\"-\" * 60)\n",
+    "\n",
+    "        # 1. Ask LLM\n",
+    "        print(\"Asking LM Studio...\", end=\"\\r\")\n",
+    "        llm_result = get_llm_response_lmstudio(claim_text)\n",
+    "        \n",
+    "        suggestion = 0\n",
+    "        conf = \"Low\"\n",
+    "        rat = \"\"\n",
+    "        \n",
+    "        if llm_result:\n",
+    "            suggestion = llm_result.get('suggestion', 0)\n",
+    "            conf = llm_result.get('confidence', \"Low\")\n",
+    "            rat = llm_result.get('rationale', \"\")\n",
+    "            print(f\"LLM Says: {suggestion} ({conf}) | Rationale: {rat}\")\n",
+    "        else:\n",
+    "            print(\"LLM Failed (Check settings or Label Manually)\")\n",
+    "\n",
+    "        # 2. Human Review\n",
+    "        while True:\n",
+    "            user_input = input(f\"Your Label (0/1) [Enter for {suggestion}]: \")\n",
+    "            if user_input.strip() == \"\":\n",
+    "                final_label = suggestion\n",
+    "                break\n",
+    "            if user_input.strip() in ['0', '1']:\n",
+    "                final_label = int(user_input)\n",
+    "                break\n",
+    "            print(\"Please enter 0 or 1.\")\n",
+    "\n",
+    "        # 3. Save\n",
+    "        df.at[idx, 'llm_green_suggested'] = suggestion\n",
+    "        df.at[idx, 'llm_confidence'] = conf\n",
+    "        df.at[idx, 'llm_rationale'] = rat\n",
+    "        df.at[idx, 'is_green_human'] = final_label\n",
+    "        \n",
+    "        df.to_csv(filename, index=False)\n",
+    "        print(\"Saved.\\n\")\n",
+    "\n",
+    "    print(\"Done\")\n",
+    "\n",
+    "labeling_loop()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "42e180f2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "============================================================\n",
+      "HITL ANALYSIS REPORT\n",
+      "============================================================\n",
+      "Total Claims Labeled: 100\n",
+      "Human Overrides:      3\n",
+      "Agreement Rate:       97.0%\n",
+      "------------------------------------------------------------\n",
+      "\n",
+      " 3 EXAMPLES OF HUMAN OVERRIDES:\n",
+      "\n",
+      "Example #1:\n",
+      "   • Claim Snippet: \"1. An apparatus, comprising: a single, dilute solids phase reactor having a top, a central section, and a bottom section with an exit port, and a top ...\"\n",
+      "   • LLM Suggestion: 0 (Rationale: The claim describes a particle removal apparatus for exhaust gases, which addresses air pollution control rather than greenhouse gas mitigation.)\n",
+      "   • Human Label:    1\n",
+      "   • Your Notes:     Manual override: This technology is classified as Green under CPC Y02.\n",
+      "\n",
+      "Example #2:\n",
+      "   • Claim Snippet: \"1. A biogenic flocculant composition for CEPT sludge conditioning comprising a) a first flocculant component which comprises at least one acidophilic ...\"\n",
+      "   • LLM Suggestion: 0 (Rationale: The claim focuses on sludge conditioning using microbial flocculants, which is a wastewater treatment application rather than a direct climate‑change mitigation technology.)\n",
+      "   • Human Label:    1\n",
+      "   • Your Notes:     Manual override: This technology is classified as Green under CPC Y02.\n",
+      "\n",
+      "Example #3:\n",
+      "   • Claim Snippet: \"1. A nuclear reactor comprising: an elongated reactor vessel enclosed at a lower end and having an open upper end on which an annular flange is formed...\"\n",
+      "   • LLM Suggestion: 0 (Rationale: The claim describes a nuclear reactor component, not a climate‑change mitigation technology.)\n",
+      "   • Human Label:    1\n",
+      "   • Your Notes:     Manual override: This technology is classified as Green under CPC Y02.\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Load the completed file\n",
+    "filename = \"hitl_green_100.csv\"\n",
+    "try:\n",
+    "    df = pd.read_csv(filename)\n",
+    "except FileNotFoundError:\n",
+    "    print(f\"Error: Could not find {filename}. Make sure you saved your work!\")\n",
+    "    exit()\n",
+    "\n",
+    "# Find Disagreements between LLM and Human Labels (0/1)\n",
+    "df['llm_green_suggested'] = pd.to_numeric(df['llm_green_suggested'], errors='coerce').fillna(-1).astype(int)\n",
+    "df['is_green_human'] = pd.to_numeric(df['is_green_human'], errors='coerce').fillna(-1).astype(int)\n",
+    "\n",
+    "overrides = df[df['llm_green_suggested'] != df['is_green_human']]\n",
+    "total_count = len(df)\n",
+    "override_count = len(overrides)\n",
+    "\n",
+    "#Print the Report\n",
+    "print(\"=\"*60)\n",
+    "print(\"HITL ANALYSIS REPORT\")\n",
+    "print(\"=\"*60)\n",
+    "print(f\"Total Claims Labeled: {total_count}\")\n",
+    "print(f\"Human Overrides:      {override_count}\")\n",
+    "print(f\"Agreement Rate:       {((total_count - override_count)/total_count)*100:.1f}%\")\n",
+    "print(\"-\" * 60)\n",
+    "\n",
+    "if override_count > 0:\n",
+    "    print(\"\\n 3 EXAMPLES OF HUMAN OVERRIDES:\")\n",
+    "    # Selecting 3 examples to show\n",
+    "    examples = overrides.head(3)\n",
+    "    \n",
+    "    for i, (idx, row) in enumerate(examples.iterrows(), 1):\n",
+    "        print(f\"\\nExample #{i}:\")\n",
+    "        print(f\"   • Claim Snippet: \\\"{str(row['text'])[:150]}...\\\"\")\n",
+    "        print(f\"   • LLM Suggestion: {row['llm_green_suggested']} (Rationale: {row['llm_rationale']})\")\n",
+    "        print(f\"   • Human Label:    {row['is_green_human']}\")\n",
+    "        if row['notes']:\n",
+    "            print(f\"   • Your Notes:     {row['notes']}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a4fefb37",
+   "metadata": {},
+   "source": [
+    "# Part D"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0ad0f2e4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Starting Part D: Final Active Learning Evaluation...\n",
+      "   - Generating Base Training and Eval Embeddings...\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "213f76fffed1405582e4c06644c3a2cf",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Encoding:   0%|          | 0/63 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5c3e96ca30f94a0fa27f27b24368d491",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Encoding:   0%|          | 0/157 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "   - Loading 100 human-labeled examples...\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "21f8b1a47ab249c8bea9de13cd2b80e9",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Encoding:   0%|          | 0/4 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "========================================\n",
+      "FINAL PERFORMANCE COMPARISON\n",
+      "========================================\n",
+      "Metric          | Baseline (Part A)    | Active (Part D)     \n",
+      "------------------------------------------------------------\n",
+      "Precision       |               0.7489 |               0.7473 (-0.0015)\n",
+      "Recall          |               0.7488 |               0.7467 (-0.0021)\n",
+      "F1-score        |               0.7488 |               0.7465 (-0.0023)\n",
+      "============================================================\n",
+      "Assignment Complete! Copy the table above into your README.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"Starting Part D: Final Active Learning Evaluation...\")\n",
+    "\n",
+    "# Setup Model & Data\n",
+    "model_name = \"AI-Growth-Lab/PatentSBERTa\"\n",
+    "tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
+    "model = AutoModel.from_pretrained(model_name)\n",
+    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
+    "model.to(device); model.eval()\n",
+    "\n",
+    "def get_embeddings(text_list, batch_size=32):\n",
+    "    all_embeddings = []\n",
+    "    for i in tqdm(range(0, len(text_list), batch_size), desc=\"Encoding\"):\n",
+    "        batch_texts = text_list[i:i+batch_size]\n",
+    "        inputs = tokenizer(batch_texts, padding=True, truncation=True, max_length=128, return_tensors=\"pt\").to(device)\n",
+    "        with torch.no_grad():\n",
+    "            outputs = model(**inputs)\n",
+    "            all_embeddings.append(outputs.last_hidden_state[:, 0, :].cpu().numpy())\n",
+    "    return np.vstack(all_embeddings)\n",
+    "\n",
+    "# Re-create splits from Part A\n",
+    "df = pd.read_parquet(\"patents_50k_green.parquet\")\n",
+    "df_eval = df.sample(n=5000, random_state=42)\n",
+    "df_remaining = df.drop(df_eval.index)\n",
+    "df_train = df_remaining.sample(n=2000, random_state=42)\n",
+    "\n",
+    "print(\"   - Generating Base Training and Eval Embeddings...\")\n",
+    "X_train = get_embeddings(df_train['text'].tolist())\n",
+    "y_train = df_train['is_green_silver'].values\n",
+    "X_eval = get_embeddings(df_eval['text'].tolist())\n",
+    "y_eval = df_eval['is_green_silver'].values\n",
+    "\n",
+    "# Train Baseline\n",
+    "clf_base = LogisticRegression(max_iter=1000, random_state=42)\n",
+    "clf_base.fit(X_train, y_train)\n",
+    "base_report = classification_report(y_eval, clf_base.predict(X_eval), output_dict=True)\n",
+    "\n",
+    "# Load your HITL Gold Labels\n",
+    "df_hitl = pd.read_csv(\"hitl_green_100.csv\")\n",
+    "print(f\"   - Loading {len(df_hitl)} human-labeled examples...\")\n",
+    "X_hitl = get_embeddings(df_hitl['text'].tolist())\n",
+    "y_hitl = df_hitl['is_green_human'].values\n",
+    "\n",
+    "# Active Learning: Combine Original Train + Human Gold Labels\n",
+    "X_combined = np.vstack([X_train, X_hitl])\n",
+    "y_combined = np.concatenate([y_train, y_hitl])\n",
+    "\n",
+    "# Train the Active Learning Model\n",
+    "clf_active = LogisticRegression(max_iter=1000, random_state=42)\n",
+    "clf_active.fit(X_combined, y_combined)\n",
+    "active_report = classification_report(y_eval, clf_active.predict(X_eval), output_dict=True)\n",
+    "\n",
+    "# FINAL COMPARISON REPORT\n",
+    "print(\"\\n\" + \"=\"*40)\n",
+    "print(\"FINAL PERFORMANCE COMPARISON\")\n",
+    "print(\"=\"*40)\n",
+    "print(f\"{'Metric':<15} | {'Baseline (Part A)':<20} | {'Active (Part D)':<20}\")\n",
+    "print(\"-\" * 60)\n",
+    "for m in ['precision', 'recall', 'f1-score']:\n",
+    "    val_a = base_report['macro avg'][m]\n",
+    "    val_d = active_report['macro avg'][m]\n",
+    "    diff = val_d - val_a\n",
+    "    print(f\"{m.capitalize():<15} | {val_a:20.4f} | {val_d:20.4f} ({'+' if diff >=0 else ''}{diff:.4f})\")\n",
+    "print(\"=\"*60)\n",
+    "print(\"Assignment Complete! Copy the table above into your README.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cf420b77",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

patents_50k_green.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce03253c78337876a32fa166356cc6a5b87f66488f3aac55be4c02420fa1fb6
+size 21754536