SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.15006 · 2024

Airavata: Introducing Hindi Instruction-tuned LLM

arXiv · PDF · Open in the Atlas

Code that ran

10 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2401.15006.json · badge: /api/ran/2401.15006.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ai4bharat/indicinstruct canonical (classifier label)
classifier basis: census
10 ran · 4 no recorded run
FunctionStatusWhere it lives
convert_message Ran
ran; our contract draft was wrong, not the code
ai4bharat/indicinstruct/open_instruct/gradio_demo_chat.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from THU-KEG/ADELIE, is pointer only (licence: NONE) · get_code("17d17a8f4a188a7d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from THU-KEG/ADELIE, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

create_prompt_with_gemma_chat_format Ran
ran; our contract draft was wrong, not the code
ai4bharat/indicinstruct/eval/templates.py
code served (permissive licence) · get_code("e125c6d221046882")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

# Define the messages list with proper chat format
messages = [
    {
        'role': 'system',
        'content': 'You are a helpful assistant.'
    },
    {
        'role': 'user',
        'content': 'What is 2+2?'
    },
    {
        'role': 'assistant',
        'content': 'The answer is 4.'
    }
]

# Define ARGS dict with all parameters
ARGS = {
    'messages': messages,
    'bos': '<bos>',
    'eos': '<eos>',
    'add_bos': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_prompt_with_llama2_chat_format Ran
ran; our contract draft was wrong, not the code
ai4bharat/indicinstruct/eval/templates.py
code served (permissive licence) · get_code("c2ea9b08ef7b2a43")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

# Define messages for the chat format
# Testing with a user message followed by an assistant response
messages = [
    {'role': 'user', 'content': 'Hello, how are you?'},
    {'role': 'assistant', 'content': 'I am doing well, thank you for asking!'}
]

ARGS = {
    'messages': messages,
    'bos': '<s>',
    'eos': '</s>',
    'add_bos': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_prompt_with_tulu_chat_format Ran
ran; our contract draft was wrong, not the code
ai4bharat/indicinstruct/eval/templates.py
code served (permissive licence) · get_code("aa0185cde82ab7d0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# Construct valid arguments for create_prompt_with_tulu_chat_format

messages = [
    {
        'role': 'system',
        'content': 'You are a helpful assistant.'
    },
    {
        'role': 'user',
        'content': 'What is 2 + 2?'
    },
    {
        'role': 'assistant',
        'content': 'The answer is 4.'
    }
]

ARGS = {
    'messages': messages,
    'bos': '<s>',
    'eos': '</s>',
    'add_bos': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
dispatch_openai_chat_requesets Ran
ran; our contract draft was wrong, not the code
ai4bharat/indicinstruct/eval/dispatch_openai_requests.py
code served (permissive licence) · get_code("4967e8b8db0b2f2c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned coroutine. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import openai
import asyncio
from typing import Any, List, Dict

# Mock the openai module since we can't make real API calls
class MockChatCompletion:
    @staticmethod
    async def acreate(model: str, messages: List[Dict[str, Any]], **kwargs) -> str:
        # Simulate async API response
        await asyncio.sleep(0.001)
        return f"Mock response for {model}"

# Replace openai.ChatCompletion with our mock
openai.ChatCompletion = MockChatCompletion

# Construct valid arguments
messages_list = [
    [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello, what is 2+2?"}
    ],
    [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
    ]
]

model = "gpt-3.5-turbo"

completion_kwargs = {
    "temperature": 0.7,
    "max_tokens": 100,
    "top_p": 0.9
}

ARGS = {
    "messages_list": messages_list,
    "model": model,
    **completion_kwargs
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
openai — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type coroutine — a coroutine output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a coroutine output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
dispatch_openai_prompt_requesets Ran
ran; our contract draft was wrong, not the code
ai4bharat/indicinstruct/eval/dispatch_openai_requests.py
code served (permissive licence) · get_code("d03d79aa598e2229")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned coroutine. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import openai
import asyncio
from typing import Any, List, Dict

# Setup for dispatch_openai_prompt_requesets function
# The function takes a list of prompts, a model name, and keyword arguments for OpenAI completion API

ARGS = {
    "prompt_list": [
        "What is the capital of France?",
        "Explain quantum computing in simple terms.",
    ],
    "model": "text-davinci-003",
    "max_tokens": 100,
    "temperature": 0.7,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
openai — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type coroutine — a coroutine output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a coroutine output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
encode_with_messages_format Ran
ran; our contract draft was wrong, not the code
ai4bharat/indicinstruct/open_instruct/finetune.py
code served (permissive licence) · get_code("1cb0eeb16cf04ee3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from unittest.mock import Mock

torch.manual_seed(0)

class MockTokenizer:
    def __init__(self):
        self.eos_token = '<|end|>'
    
    def __call__(self, text, return_tensors=None, max_length=None, truncation=None):
        # Return a mock tokenization result with input_ids
        # We need to return different lengths based on the text to simulate real tokenization
        text_len = len(text.split())
        token_count = min(text_len + 5, max_length) if max_length else text_len + 5
        
        result = Mock()
        result.input_ids = torch.randint(0, 1000, (1, token_count))
        return result

example = {
    'messages': [
        {
            'role': 'system',
            'content': 'You are a helpful assistant.'
        },
        {
            'role': 'user',
            'content': 'Hello, how are you?'
        },
        {
            'role': 'assistant',
            'content': 'I am doing well, thank you for asking.'
        }
    ]
}

tokenizer = MockTokenizer()
max_seq_length = 128

ARGS = {
    'example': example,
    'tokenizer': tokenizer,
    'max_seq_length': max_seq_length
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
encode_with_prompt_completion_format Ran
ran; our contract draft was wrong, not the code
ai4bharat/indicinstruct/open_instruct/finetune.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from clinicalml/co-llm, is pointer only (licence: NONE) · get_code("661419d69a095bfe")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from clinicalml/co-llm, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_next_word_predictions Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ai4bharat/indicinstruct/eval/utils.py
code served (permissive licence) · get_code("d134c88af0236263")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from unittest.mock import Mock

torch.manual_seed(0)

# Build a minimal model that satisfies function requirements
class MinimalLanguageModel(nn.Module):
    def __init__(self, vocab_size=100, hidden_size=4):
        super().__init__()
        self.linear = nn.Linear(hidden_size, vocab_size)
        self.device_obj = Mock()
        self.device_obj.type = 'cpu'
    
    @property
    def device(self):
        return self.device_obj
    
    def forward(self, input_ids, attention_mask):
        # input_ids: (batch_size, seq_len)
        # Return logits of shape (batch_size, seq_len, vocab_size)
        batch_size, seq_len = input_ids.shape
        hidden = torch.randn(batch_size, seq_len, 4)
        logits = self.linear(hidden)
        return Mock(logits=logits)

# Build a minimal tokenizer that satisfies function requirements
class MinimalTokenizer:
    def __init__(self, vocab_size=100):
        self.vocab_size = vocab_size
    
    def __call__(self, texts, padding='longest', return_tensors='pt', add_special_tokens=True):
        if isinstance(texts, str):
            texts = [texts]
        max_len = max(len(text.split()) for text in texts) + 2
        batch_size = len(texts)
        input_ids = torch.randint(0, self.vocab_size, (batch_size, max_len))
        attention_mask = torch.ones(batch_size, max_len)
        return Mock(input_ids=input_ids, attention_mask=attention_mask)
    
    def convert_ids_to_tokens(self, ids):
        if isinstance(ids, torch.Tensor):
            ids = ids.tolist()
        if isinstance(ids, list):
            return [f'token_{id}' for id in ids]
        return f'token_{ids}'

model = MinimalLanguageModel(vocab_size=100, hidden_size=4)
tokenizer = MinimalTokenizer(vocab_size=100)
prompts = ["Hello world", "How are you"]
candidate_token_ids = torch.tensor([5, 10, 15, 20])

ARGS = {
    'model': model,
    'tokenizer': tokenizer,
    'prompts': prompts,
    'candidate_token_ids': candidate_token_ids,
    'batch_size': 1,
    'return_token_predictions': False,
    'add_special_tokens': True,
    'disable_tqdm': True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
identity Ran
ran; our contract draft was wrong, not the code
ai4bharat/indicinstruct/open_instruct/finetune.py
code served (permissive licence) · get_code("1d0160fa2079785a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create a minimal tokenizer stand-in
class SimpleTokenizer:
    def __init__(self):
        self.vocab_size = 100
    
    def encode(self, text):
        return [1, 2, 3]
    
    def decode(self, ids):
        return "text"

# Create a minimal example (could be a dict, string, tensor, etc.)
example = {
    "text": "Hello world",
    "id": 1
}

# Create tokenizer instance
tokenizer = SimpleTokenizer()

# Set max sequence length
max_seq_length = 128

ARGS = {
    "example": example,
    "tokenizer": tokenizer,
    "max_seq_length": max_seq_length
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
forward Not yet run
unverified (harvested, no recorded run)
ai4bharat/indicinstruct/open_instruct/bloom_flash_attn_monkey_patch.py
code served (permissive licence) · get_code("b4bab7d7cf5218ef")
How it ran

no invocation recorded.

generate_completions Not yet run
unverified (harvested, no recorded run)
ai4bharat/indicinstruct/eval/utils.py
code served (permissive licence) · get_code("352416cd121404a7")
How it ran

no invocation recorded.

get_statistics_for_messages_data Not yet run
unverified (harvested, no recorded run)
ai4bharat/indicinstruct/open_instruct/get_statistics.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from THU-KEG/ADELIE, is pointer only (licence: NONE) · get_code("533568a0e86ef298")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from THU-KEG/ADELIE, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_statistics_for_prompt_completion_data Not yet run
unverified (harvested, no recorded run)
ai4bharat/indicinstruct/open_instruct/get_statistics.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from THU-KEG/ADELIE, is pointer only (licence: NONE) · get_code("84aeb6a7586885f5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from THU-KEG/ADELIE, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 9 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 6 the same month, 9 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_next_word_predictions 10 other papers
1 the same month, 9 later
2401.16405 (2024-01)
Scaling Sparse Fine-Tuning to Large Language Models
2402.16705 (2024-02)
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
2405.05008 (2024-05)
ADELIE: Aligning Large Language Models on Information Extraction
and 7 more not named here
encode_with_prompt_completion_format 9 other papers
2 dated earlier, 3 the same month, 4 later
2311.05657 (2023-11)
Agent Lumos: Unified and Modular Training for Open-Source Language Agents
2312.07540 (2023-12)
diff History for Neural Language Agents
2401.08565 (2024-01)
Tuning Language Models by Proxy
and 6 more not named here
dispatch_openai_prompt_requesets 8 other papers
1 dated earlier, 2 the same month, 5 later
2310.06830 (2023-10)
Lemur: Harmonizing Natural Language and Code for Language Agents
2401.10768 (2024-01)
Knowledge Verification to Nip Hallucination in the Bud
2401.16405 (2024-01)
Scaling Sparse Fine-Tuning to Large Language Models
and 5 more not named here
encode_with_messages_format 8 other papers
3 dated earlier, 2 the same month, 3 later
2310.08491 (2023-10)
Prometheus: Inducing Fine-grained Evaluation Capability in Language Models
2310.11511 (2023-10)
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
2311.05657 (2023-11)
Agent Lumos: Unified and Modular Training for Open-Source Language Agents
and 5 more not named here
dispatch_openai_chat_requesets 7 other papers
1 dated earlier, 2 the same month, 4 later
2310.06830 (2023-10)
Lemur: Harmonizing Natural Language and Code for Language Agents
2401.10768 (2024-01)
Knowledge Verification to Nip Hallucination in the Bud
2401.16405 (2024-01)
Scaling Sparse Fine-Tuning to Large Language Models
and 4 more not named here
generate_completions 6 other papers
1 dated earlier, 2 the same month, 3 later
2310.08491 (2023-10)
Prometheus: Inducing Fine-grained Evaluation Capability in Language Models
2401.10768 (2024-01)
Knowledge Verification to Nip Hallucination in the Bud
2401.16405 (2024-01)
Scaling Sparse Fine-Tuning to Large Language Models
and 3 more not named here
convert_message 1 other paper
1 later
2405.05008 (2024-05)
ADELIE: Aligning Large Language Models on Information Extraction
get_statistics_for_messages_data 1 other paper
1 later
2405.05008 (2024-05)
ADELIE: Aligning Large Language Models on Information Extraction
get_statistics_for_prompt_completion_data 1 other paper
1 later
2405.05008 (2024-05)
ADELIE: Aligning Large Language Models on Information Extraction

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We announce the initial release of "Airavata," an instruction-tuned LLM for Hindi. Airavata was created by fine-tuning OpenHathi with diverse, instruction-tuning Hindi datasets to make it better suited for assistive tasks. Along with the model, we also share the IndicInstruct dataset, which is a collection of diverse instruction-tuning datasets to enable further research for Indic LLMs. Additionally, we present evaluation benchmarks and a framework for assessing LLM performance across tasks in Hindi. Currently, Airavata supports Hindi, but we plan to expand this to all 22 scheduled Indic languages. You can access all artifacts at https://ai4bharat.github.io/airavata.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2401.15006")
get_code_for_paper("2401.15006")
have("2401.15006")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2401.15006.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2401.15006.svg)](https://syntology.ai/paper/2401.15006)

Connect an agent — have() is free.