Update protocol-aligned terminology

README.md

@@ -5,7 +5,7 @@ library_name: peft
 pipeline_tag: image-text-to-text
 tags:
 - laboratory
-- protocol-conditioned-action-prediction
+- protocol-aligned-action-prediction
 - lora
 - qwen
 - long-horizon-planning
@@ -30,7 +30,7 @@ tags:
 [![Data L2 Protocol](https://img.shields.io/badge/%F0%9F%A4%97%20Data-L2%20Protocol-purple)](https://huggingface.co/datasets/Stanford-CongLab/LabHorizon-Protocol-Conditioned-Planning) 
 [![Model](https://img.shields.io/badge/%F0%9F%A4%97%20Model-Qwen3.6-orange)](https://huggingface.co/Stanford-CongLab/LabHorizon-Model)
 
-**Qwen3.6-35B-A3B LoRA for protocol-conditioned laboratory action prediction**
+**Qwen3.6-35B-A3B LoRA for protocol-aligned laboratory action prediction**
 
 [Overview](#-overview) | [News](#-news) | [Highlights](#-highlights) | [Datasets](#-datasets) | [Evaluation](#-evaluation) | [Leaderboard](#-leaderboard) | [Training](#-training-result) | [Agent](#-actor-simulator-selector-agent) | [Quick Start](#-quick-start) | [Citation](#-citation)
 
@@ -44,7 +44,7 @@ tags:
 
 ## 🔎 Overview
 
-This repository releases the LabHorizon Qwen3.6 LoRA adapter trained from `Qwen/Qwen3.6-35B-A3B` on the 6,000-sample LabHorizon training split. The model is optimized for **Protocol-Conditioned Action Prediction**:
+This repository releases the LabHorizon Qwen3.6 LoRA adapter trained from `Qwen/Qwen3.6-35B-A3B` on the 6,000-sample LabHorizon training split. The model is optimized for **Protocol-Aligned Action Prediction**:
 
 - **Level 1:** connect multi-view laboratory assets and historical actions to the gold next action.
 - **Level 2:** produce a structured long-horizon experimental action sequence from context, constraints, available inputs, and an action pool.
@@ -62,7 +62,7 @@ This model repository is the model-side companion to the LabHorizon code and dat
 <tr>
 <td align="center" width="25%">🧪<br/><b>Qwen3.6 Adapter</b><br/><sub>LoRA weights for Qwen3.6-35B-A3B</sub></td>
 <td align="center" width="25%">🔬<br/><b>Level 1 Signal</b><br/><sub>Multi-view asset next-action prediction</sub></td>
-<td align="center" width="25%">🧭<br/><b>Level 2 Signal</b><br/><sub>Long-horizon protocol-conditioned planning</sub></td>
+<td align="center" width="25%">🧭<br/><b>Level 2 Signal</b><br/><sub>Long-horizon protocol-aligned planning</sub></td>
 <td align="center" width="25%">🧠<br/><b>Train + Agent</b><br/><sub>Supports trained and trained+agents settings</sub></td>
 </tr>
 </table>
@@ -74,7 +74,7 @@ The adapter is trained on the same public LabHorizon train split described by th
 | Level | Hugging Face Dataset | Input | Target | Metric |
 |:---|:---|:---|:---|:---|
 | **Level 1** | [LabHorizon-3D-Asset-Perception](https://huggingface.co/datasets/Stanford-CongLab/LabHorizon-3D-Asset-Perception) | Three asset views, historical actions, candidate next actions | Gold next action | Next-action accuracy |
-| **Level 2** | [LabHorizon-Protocol-Conditioned-Planning](https://huggingface.co/datasets/Stanford-CongLab/LabHorizon-Protocol-Conditioned-Planning) | Context, goal, constraints, available inputs, action pool | Gold experimental action sequence | L2 Action Sequence Similarity, L2 Parameter Accuracy |
+| **Level 2** | [LabHorizon Protocol-Aligned Planning](https://huggingface.co/datasets/Stanford-CongLab/LabHorizon-Protocol-Conditioned-Planning) | Context, goal, constraints, available inputs, action pool | Gold experimental action sequence | L2 Action Sequence Similarity, L2 Parameter Accuracy |
 
 ## 📦 Model
 
@@ -86,8 +86,8 @@ The adapter is trained on the same public LabHorizon train split described by th
 | Adapter type | LoRA / PEFT adapter |
 | Training data | 6,000 LabHorizon train samples |
 | Level 1 training split | 3,000 multimodal laboratory 3D asset samples |
-| Level 2 training split | 3,000 text-only protocol-conditioned planning samples |
-| Main task | Protocol-conditioned laboratory action prediction |
+| Level 2 training split | 3,000 text-only protocol-aligned planning samples |
+| Main task | Protocol-aligned laboratory action prediction |
 | Main metrics | Level 1 Next Action Accuracy; L2 Action Sequence Similarity and L2 Parameter Accuracy |
 | Intended loading mode | Load this adapter with the matching Qwen3.6-35B-A3B base model |
 
@@ -139,7 +139,7 @@ The tables below report direct-prompting baselines on the same test split used f
 | 13 | Qwen3.6 35B-A3B | 0.475 |
 | 14 | Gemini 3.1 Pro | 0.465 |
 
-### 🧪 Level 2: Protocol-Conditioned Planning
+### 🧪 Level 2: Protocol-Aligned Planning
 
 | Rank | Model | L2 Final Score | L2 Action Sequence Similarity | L2 Parameter Accuracy |
 |:---:|:---|---:|---:|---:|
@@ -168,7 +168,7 @@ The adapter is trained on the public LabHorizon training split:
 | Component | Size | Role |
 |:---|---:|:---|
 | Level 1 train | 3,000 | Multi-view laboratory asset perception and next-action prediction |
-| Level 2 train | 3,000 | Protocol-conditioned long-horizon experimental action-sequence planning |
+| Level 2 train | 3,000 | Protocol-aligned long-horizon experimental action-sequence planning |
 | Total train | 6,000 | Unified supervised fine-tuning data for laboratory action prediction |
 
 The training data are converted into Qwen chat format and then into the LLaMA-Factory ShareGPT-VL-style format. Level 1 keeps the three asset images and candidate next actions; Level 2 uses text-only context, constraints, available inputs, action pool, and gold experimental action sequence.
@@ -259,7 +259,7 @@ This adapter is intended for academic research on laboratory action prediction,
 
 Recommended use cases:
 
-- Evaluate protocol-conditioned next-action prediction and long-horizon planning.
+- Evaluate protocol-aligned next-action prediction and long-horizon planning.
 - Study how training data improves laboratory action prediction.
 - Use the adapter as the Actor in the Actor-Simulator-Selector framework.
 - Analyze remaining failures in action order, parameter copying, dependency tracking, and protocol-stage consistency.