MOOSE-Star-HC-R1D-7B Model Card

Overview

MOOSE-Star-HC-R1D-7B (referred to as MS-HC-7B w/ 1x bounded in the paper) is a 7B parameter language model fine-tuned for generating scientific hypotheses from research questions, background surveys, and cross-paper inspirations. It's designed for incremental hypothesis composition in scientific discovery workflows.

• Paper: MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier (arXiv:2603.03756)
• Base Model: DeepSeek-R1-Distill-Qwen-7B
• License: Apache 2.0
• Code: ZonglinY/MOOSE-Star
• Multi-task variant: MOOSE-Star-R1D-7B (IR + HC in one model)

Model Description

Parameter	Value
Base Model	DeepSeek-R1-Distill-Qwen-7B
Training Method	Full-parameter SFT (ZeRO-3)
Training Data	TOMATO-Star-SFT-Data-R1D-32B HC split (114,548 samples, with 1x bounded composition)
Chat Template	deepseekr1
Cutoff Length	8192
Learning Rate	1e-5
Epochs	1
Batch Size	128
Training	Full-parameter, ZeRO-3, bf16

Task Description

The model generates delta hypotheses — specific contributions from individual inspiration papers. Given:

• Research question
• Background survey
• Previous hypothesis (optional)
• New inspiration paper (title + abstract)

The model outputs:

• Inspiration: Key concept from the paper
• Motivation (WHY): How it addresses gaps
• Mechanism (HOW IT WORKS): Core scientific mechanism
• Methodology (HOW IT'S INTEGRATED): Implementation approach

Prompt Format (Simplified Overview)

The full prompt template is constructed via instruction_prompts() in the code example below. The general structure is:

[Task instruction preamble]

## Information Provided

**Research Question**:
{research_question}

**Background Survey**:
{background_survey}

**Previous Hypothesis**:
{previous_hypothesis_or_none}

**New Inspiration Paper Title**:
{inspiration_title}

**New Inspiration Paper Abstract**:
{inspiration_abstract}

## Your Response

<think>
[reasoning process]
</think>

Inspiration: [Key concept]
- Motivation (WHY): [Why this addresses a gap]
- Mechanism (HOW IT WORKS): [How the concept works]
- Methodology (HOW IT'S INTEGRATED): [Implementation steps]

Usage

Prerequisites: Clone the MOOSE-Star repo for prompt templates:

git clone https://github.com/ZonglinY/MOOSE-Star.git && cd MOOSE-Star
# See requirements.txt for full dependencies; at minimum: pip install transformers torch

import sys
sys.path.insert(0, "./utils")
from prompt_store import instruction_prompts
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "ZonglinY/MOOSE-Star-HC-R1D-7B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name, 
    dtype="auto", 
    device_map="auto"
)

# Use bounded/delta composition for hierarchical search
p = instruction_prompts("prepare_HC_sft_data_to_go_comprehensive_v2_delta")

research_question = "Your research question here"
background_survey = "Your background survey here"
inspiration_title = "Inspiration paper title"
inspiration_abstract = "Inspiration paper abstract"

prompt = (p[0] + research_question
        + p[1] + background_survey
        + p[2] + "No previous hypothesis."
        + p[3] + inspiration_title
        + p[4] + inspiration_abstract
        + p[5])

messages = [{"role": "user", "content": prompt}]
formatted = tokenizer.apply_chat_template(
    messages, 
    tokenize=False, 
    add_generation_prompt=False
)
formatted += "<｜Assistant｜>"

inputs = tokenizer(formatted, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs, 
    max_new_tokens=8192, 
    temperature=0.6, 
    top_p=0.9, 
    do_sample=True
)
response = tokenizer.decode(
    outputs[0][inputs["input_ids"].shape[1]:], 
    skip_special_tokens=True
)
print(response)

Evaluation Results

Rubric-based evaluation on normal composition with ground-truth inspirations (Judge: GPT-4o):

Model	Total	Mot	Mec	Met	Length
R1-Distilled-Qwen-7B (base)	4.05	1.96	1.30	0.80	231.02
MS-HC-7B	4.68	2.13	1.46	1.09	204.12
MS-HC-7B w/ 1x bounded (this model)	4.74	2.16	1.48	1.10	203.84
MS-HC-7B w/ 2x bounded	4.73	2.15	1.48	1.09	205.17

Citation

@article{yang2025moosestar,
  title={MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier},
  author={Yang, Zonglin and Bing, Lidong},
  journal={arXiv preprint arXiv:2603.03756},
  year={2026}
}

Try It on the Inference Provider (Copy-Paste Examples)

The HF Inference Provider playground for this model currently has known limitations (default max_tokens is set to the full context window, and the parameter is not adjustable in the UI). Until that is fixed upstream, the recommended way to try the model is via the API.

Quickstart (Python)

from huggingface_hub import InferenceClient

client = InferenceClient(provider="featherless-ai", token="<HF_TOKEN>")
prompt = """<paste one of the prompts below>"""

r = client.chat_completion(
    messages=[{"role": "user", "content": prompt}],
    model="<this model id>",
    max_tokens=4096,        # IMPORTANT: must be < 32768 - len(prompt_tokens)
    temperature=0.6,
    top_p=0.9,
)
print(r.choices[0].message.content)

Note on chat template: under the DeepSeek-R1 chat template the opening <think> tag is injected by the template itself, so the raw output begins directly with reasoning text and contains only the closing </think>. This is expected.

Example Case (real TOMATO-Star test paper, October 2025)

• Research question: How to comprehensively explain and predict the heterogeneity of neurodegeneration in Alzheimer's disease?
• Ground-truth inspiration: "Network neuroscience" (Bassett & Sporns, 2017) — the kind of cross-disciplinary leap MOOSE-Star is trained to surface (using graph-theoretic brain-network tools to explain AD heterogeneity that single-pathology models miss).

HC prompt — compose Δhypothesis from the retrieved inspiration "Network neuroscience"

You are a scientific hypothesis composer. Given a research question, background survey, potentially a previous hypothesis to build upon, and a new inspiration paper, you will reason through how to adapt concepts from the inspiration to advance the solution, then formulate a DELTA HYPOTHESIS - the specific contribution from THIS inspiration paper (not the full cumulative hypothesis).

## Your Task

Analyze the provided research context and inspiration paper to:
1. Identify the key conceptual innovation from the inspiration paper (Note: the paper may directly provide a concept that can be adapted, OR it may contain related ideas/transferable mechanisms that inspire what we need - look beyond exact concept names)
2. Determine how this innovation addresses gaps (either in existing methods or in your previous hypothesis)
3. Reason through adaptation and integration into your solution
4. Formulate a delta hypothesis describing ONLY what THIS inspiration contributes

## Key Principles

**Reasoning Process:**
- Start by understanding the problem and what current methods lack
- If there's a previous hypothesis, understand what it already addresses and what gaps/limitations remain
- Analyze the inspiration paper to identify relevant concepts that could be adapted
- Reason through: What specific knowledge/technique from this paper could serve as an inspiration?
- Connect the dots: How does this potential inspiration address the identified gaps?
- Work through the mechanism: How would this inspiration actually function in our context?
- Develop the methodology: Detail the specific implementation and integration
- Don't just identify concepts - reason through their practical application and adaptation

**Delta Hypothesis Requirements:**
- Output ONLY what THIS inspiration adds (delta), NOT the full cumulative hypothesis
- Don't repeat what's already in the previous hypothesis
- Must clearly explain WHY the inspiration addresses the problem (Motivation)
- Must detail HOW the inspiration works in this context (Mechanism)
- Must specify HOW to implement it methodologically (Methodology)
- Follow the exact structured format shown below

## Information Provided

**Research Question** (the specific problem to solve):
How to comprehensively explain and predict the heterogeneity of neurodegeneration in Alzheimer's disease?

**Background Survey** (existing methods and their limitations):
Current Alzheimer's disease (AD) research is dominated by unifactorial approaches, primarily the amyloid-beta (Aβ) hypothesis, which posits Aβ accumulation as the central cause of neurodegeneration. Established methods include:  
- Biomarker-focused frameworks (e.g., ATN framework), which categorize AD pathology into amyloid/tau/neurodegeneration but oversimplify heterogeneity.  
- Reductionist therapeutics like Aβ antibodies (lecanemab [17], donanemab [18]) that remove plaques but yield marginal cognitive improvements (±25% delay) and cause adverse effects (brain swelling/microbleeds).  
- Siloed scale investigations: Molecular studies (Aβ/tau at nanoscale [4]), cellular analyses (neuroinflammation at microscale [29]), and epidemiological risk tracking (exposcale [33]) lack integration.  

Key Limitations:  
- Aβ-centric models fail to explain:  
  - Aβ plaques in cognitively healthy seniors [8–10]  
  - Poor correlation between Aβ burden and cognitive decline [11–13]  
  - Heterogeneity in clinical presentations (e.g., visual vs. memory-predominant AD [56])  
- Clinical trials targeting single entities ignore cross-scale interactions (e.g., exercise improves cognition via vascular/metabolic pathways [58]).

**Previous Hypothesis** (if any - the current state of your solution to build upon):
No previous hypothesis.

**New Inspiration Paper Title** (external work to incorporate):
Network neuroscience.

**New Inspiration Paper Abstract**:
Despite substantial recent progress, our understanding of the principles and mechanisms underlying complex brain function and cognition remains incomplete. Network neuroscience proposes to tackle these enduring challenges. Approaching brain structure and function from an explicitly integrative perspective, network neuroscience pursues new ways to map, record, analyze and model the elements and interactions of neurobiological systems. Two parallel trends drive the approach: the availability of new empirical tools to create comprehensive maps and record dynamic patterns among molecules, neurons, brain areas and social systems; and the theoretical framework and computational tools of modern network science. The convergence of empirical and computational advances opens new frontiers of scientific inquiry, including network dynamics, manipulation and control of brain networks, and integration of network processes across spatiotemporal domains. We review emerging trends in network neuroscience and attempt to chart a path toward a better understanding of the brain as a multiscale networked system.

## Your Response

Analyze how this inspiration paper's concepts can advance your solution:

1. **If starting from scratch** (no previous hypothesis): 
   - Identify how the inspiration addresses the core gaps in existing methods
   - This becomes your first conceptual building block beyond the baseline approach

2. **If building on a previous hypothesis**: 
   - First understand what the previous hypothesis already accomplishes
   - Identify remaining limitations or opportunities for enhancement
   - Determine how this new inspiration specifically addresses those gaps

Show your reasoning process as you:
- Extract relevant concepts from the inspiration paper (may not be obvious - reason through what could be useful)
- Identify what specific technique/knowledge could serve as the inspiration
- Connect this inspiration to your problem: Why is this relevant? How does it address gaps?
- Work through adaptation: How to modify this concept for your specific context?
- Detail the motivation, mechanism, and methodology for THIS inspiration's contribution
- Reason through implementation details

Then formulate a delta hypothesis that captures ONLY what THIS inspiration adds.

## Output Format

**IMPORTANT**: Structure your response exactly as follows:

<think>
[Your reasoning process here - explore all aspects thoroughly]
</think>

**Delta Hypothesis starts:**
Inspiration: [Key concept derived from or inspired by the inspiration paper]
- Motivation (WHY): [Why this addresses a gap - what specific limitation does it solve?]
- Mechanism (HOW IT WORKS): [How the concept works in this context]
- Methodology (HOW IT'S INTEGRATED): [How to integrate it - specific implementation steps]
**Delta Hypothesis ends**

⚠️ CRITICAL: The delta hypothesis is the ONLY part that gets evaluated!
- Include ALL components you FINALIZED in your reasoning (not early ideas you later revised)
- Be COMPREHENSIVE - every technical detail, mechanism, and methodology step you reasoned through should appear in the delta hypothesis
- Don't assume the reader saw your reasoning - the delta hypothesis must be SELF-CONTAINED and COMPLETE
- Focus on THIS inspiration's contribution only - don't repeat previous hypothesis content

Expected output format:

<think>
[reasoning]
</think>

**Delta Hypothesis starts:**
Inspiration: [...]
- Motivation (WHY): [...]
- Mechanism (HOW IT WORKS): [...]
- Methodology (HOW IT'S INTEGRATED): [...]
**Delta Hypothesis ends**