SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.10723 · ICCV · 2021

Improving 3D Object Detection with Channel-wise Transformer

Xian-Sheng Hua, Jianqiang Huang, Yuan Liu, Hualian Sheng, Sijia Cai, Bing Deng, Min-Jian Zhao

arXiv · PDF · Open in the Atlas

Code that ran

6 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 1 failure of our instrument; 6 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/2108.10723.json · badge: /api/ran/2108.10723.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
hlsheng1/ct3d marked official in Papers with Code
Papers with Code archive
6 ran · 6 no recorded run
FunctionStatusWhere it lives
MultiHeadedAttention Ran
ran on a synthesized input
hlsheng1/ct3d/pcdet/models/roi_heads/ct3d_head.py
code served (permissive licence) · get_code("671c67f4433ae3c1")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
import torch.nn.functional as F
from copy import deepcopy

class MLP(nn.Module):
    """ Very simple multi-layer perceptron (also called FFN)"""

    def __init__(self, input_dim, hidden_dim, output_dim, num_layers):
        super().__init__()
        self.num_layers = num_layers
        h = [hidden_dim] * (num_layers - 1)
        self.layers = nn.ModuleList((nn.Linear(n, k) for n, k in zip([input_dim] + h, h + [output_dim])))

    def forward(self, x):
        for i, layer in enumerate(self.layers):
            x = F.relu(layer(x)) if i < self.num_layers - 1 else layer(x)
        return x

def attention(query, key, value):
    dim = query.shape[1]
    scores_1 = torch.einsum('bdhn,bdhm->bhnm', query, key) / dim ** 0.5
    scores_2 = torch.einsum('abcd, aced->abcd', key, scores_1)
    prob = torch.nn.functional.softmax(scores_2, dim=-1)
    output = torch.einsum('bnhm,bdhm->bdhn', prob, value)
    return (output, prob)

class MultiHeadedAttention(nn.Module):
    """ Multi-head attention to increase model expressivitiy """

    def __init__(self, num_heads: int, d_model: int):
        super().__init__()
        assert d_model % num_heads == 0
        self.dim = d_model // num_heads
        self.num_heads = num_heads
        merge = nn.Conv1d(d_model, d_model, kernel_size=1)
        self.proj = nn.ModuleList([deepcopy(merge) for _ in range(3)])
        self.down_mlp = MLP(input_dim=self.dim, hidden_dim=32, output_dim=1, num_layers=1)

    def forward(self, query, key, value):
        batch_dim = query.size(0)
        query, key, value = [l(x).view(batch_dim, self.dim, self.num_heads, -1) for l, x in zip(self.proj, (query, key, value))]
        x, prob = attention(query, key, value)
        x = self.down_mlp(x)
        return x.contiguous().view(batch_dim, self.dim * self.num_heads, -1)

INIT_ARGS = {
    'num_heads': 2,
    'd_model': 8,
}

ARGS = {
    'query': torch.randn(2, 8, 5),
    'key': torch.randn(2, 8, 5),
    'value': torch.randn(2, 8, 5),
}

if __name__ == '__main__':
    model = MultiHeadedAttention(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Output: {output}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
TransformerDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
hlsheng1/ct3d/pcdet/models/roi_heads/ct3d_head.py
code served (permissive licence) · get_code("b41cfee48847d79e")
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 an instance of its own class, TransformerDecoder: the run constructed the object and did not call it, so no result was computed. 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
from typing import Optional, List

torch.manual_seed(0)

# Create a minimal decoder layer that matches the interface expected
class MinimalDecoderLayer(nn.Module):
    def __init__(self, d_model):
        super().__init__()
        self.d_model = d_model
        self.linear = nn.Linear(d_model, d_model)
    
    def forward(self, tgt, memory, tgt_mask=None, memory_mask=None, 
                tgt_key_padding_mask=None, memory_key_padding_mask=None, 
                pos=None, query_pos=None):
        # Simple pass-through with linear transformation
        return self.linear(tgt)

# Create a minimal norm layer
class MinimalNorm(nn.Module):
    def __init__(self, d_model):
        super().__init__()
        self.norm = nn.LayerNorm(d_model)
    
    def forward(self, x):
        return self.norm(x)

# Set up dimensions
d_model = 4
seq_len = 3
batch_size = 2
num_layers = 2

# Create decoder layer
decoder_layer = MinimalDecoderLayer(d_model)

# Create norm
norm = MinimalNorm(d_model)

# Create tensors
tgt = torch.randn(seq_len, batch_size, d_model)
memory = torch.randn(seq_len, batch_size, d_model)

ARGS = {
    "decoder_layer": decoder_layer,
    "num_layers": num_layers,
    "norm": norm,
    "return_intermediate": False
}
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 TransformerDecoder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TransformerDecoder 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
TransformerDecoderLayer Ran
ran on a synthesized input · constructed an object; no result was computed
hlsheng1/ct3d/pcdet/models/roi_heads/ct3d_head.py
code served (permissive licence) · get_code("2cb413b2d6fa8f2e")
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 an instance of its own class, TransformerDecoderLayer: the run constructed the object and did not call it, so no result was computed. 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

torch.manual_seed(0)

ARGS = {
    'd_model': 4,
    'nhead': 2,
    'dim_feedforward': 8,
    'dropout': 0.1,
    'activation': 'relu',
    'normalize_before': False,
}
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 TransformerDecoderLayer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TransformerDecoderLayer 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
TransformerEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
hlsheng1/ct3d/pcdet/models/roi_heads/ct3d_head.py
code served (permissive licence) · get_code("10ec8fb6960c9e5e")
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 an instance of its own class, TransformerEncoder: the run constructed the object and did not call it, so no result was computed. 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
from torch import Tensor

torch.manual_seed(0)

# Create a minimal encoder layer that implements the interface expected by TransformerEncoder
class MinimalEncoderLayer(nn.Module):
    def __init__(self, d_model=4):
        super().__init__()
        self.linear = nn.Linear(d_model, d_model)
    
    def forward(self, src, src_mask=None, src_key_padding_mask=None, pos=None):
        # The layer receives src and optional mask/padding_mask/pos parameters
        return self.linear(src)

# Create a minimal norm layer
norm_layer = nn.LayerNorm(4)

# Create encoder layer instance
encoder_layer = MinimalEncoderLayer(d_model=4)

# Number of layers
num_layers = 2

# Build ARGS dictionary with all parameters
ARGS = {
    "encoder_layer": encoder_layer,
    "num_layers": num_layers,
    "norm": norm_layer
}
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 TransformerEncoder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TransformerEncoder 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
TransformerEncoderLayer Ran
ran on a synthesized input · constructed an object; no result was computed
hlsheng1/ct3d/pcdet/models/roi_heads/ct3d_head.py
code served (permissive licence) · get_code("9f90c23222eb4bbf")
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 an instance of its own class, TransformerEncoderLayer: the run constructed the object and did not call it, so no result was computed. 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
import torch.nn.functional as F
from typing import Optional, List
from torch import Tensor

torch.manual_seed(0)

def _get_activation_fn(activation):
    """Return an activation function given a string"""
    if activation == 'relu':
        return F.relu
    if activation == 'gelu':
        return F.gelu
    if activation == 'glu':
        return F.glu
    raise RuntimeError(f'activation should be relu/gelu, not {activation}.')

class TransformerEncoderLayer(nn.Module):

    def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1, activation='relu', normalize_before=False):
        super().__init__()
        self.self_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
        self.linear1 = nn.Linear(d_model, dim_feedforward)
        self.dropout = nn.Dropout(dropout)
        self.linear2 = nn.Linear(dim_feedforward, d_model)
        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.dropout1 = nn.Dropout(dropout)
        self.dropout2 = nn.Dropout(dropout)
        self.activation = _get_activation_fn(activation)
        self.normalize_before = normalize_before

    def with_pos_embed(self, tensor, pos: Optional[Tensor]):
        return tensor if pos is None else tensor + pos

    def forward_post(self, src, src_mask: Optional[Tensor]=None, src_key_padding_mask: Optional[Tensor]=None, pos: Optional[Tensor]=None):
        q = k = self.with_pos_embed(src, pos)
        src2 = self.self_attn(q, k, value=src, attn_mask=src_mask, key_padding_mask=src_key_padding_mask)[0]
        src = src + self.dropout1(src2)
        src = self.norm1(src)
        src2 = self.linear2(self.dropout(self.activation(self.linear1(src))))
        src = src + self.dropout2(src2)
        src = self.norm2(src)
        return src

    def forward_pre(self, src, src_mask: Optional[Tensor]=None, src_key_padding_mask: Optional[Tensor]=None, pos: Optional[Tensor]=None):
        src2 = self.norm1(src)
        q = k = self.with_pos_embed(src2, pos)
        src2 = self.self_attn(q, k, value=src2, attn_mask=src_mask, key_padding_mask=src_key_padding_mask)[0]
        src = src + self.dropout1(src2)
        src2 = self.norm2(src)
        src2 = self.linear2(self.dropout(self.activation(self.linear1(src2))))
        src = src + self.dropout2(src2)
        return src

    def forward(self, src, src_mask: Optional[Tensor]=None, src_key_padding_mask: Optional[Tensor]=None, pos: Optional[Tensor]=None):
        if self.normalize_before:
            return self.forward_pre(src, src_mask, src_key_padding_mask, pos)
        return self.forward_post(src, src_mask, src_key_padding_mask, pos)

# Create minimal valid arguments
d_model = 4
nhead = 2
dim_feedforward = 8
dropout = 0.1
activation = 'relu'
normalize_before = False

# Create the layer instance
layer = TransformerEncoderLayer(
    d_model=d_model,
    nhead=nhead,
    dim_feedforward=dim_feedforward,
    dropout=dropout,
    activation=activation,
    normalize_before=normalize_before
)

# Create input tensors: (seq_len, batch, d_model)
src = torch.randn(3, 2, d_model)
pos = torch.randn(3, 2, d_model)
src_mask = None
src_key_padding_mask = None

ARGS = {
    'd_model': d_model,
    'nhead': nhead,
    'dim_feedforward': dim_feedforward,
    'dropout': dropout,
    'activation': activation,
    'normalize_before': normalize_before
}
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 TransformerEncoderLayer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a TransformerEncoderLayer 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
attention Ran
ran; our contract draft was wrong, not the code
hlsheng1/ct3d/pcdet/models/roi_heads/ct3d_head.py
code served (permissive licence) · get_code("f93d42eb62cfe6e7")
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. 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.functional as F

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# query, key, value shapes: (batch, dim, heads, seq_len)
batch_size = 2
dim = 4
num_heads = 3
seq_len = 5

query = torch.randn(batch_size, dim, num_heads, seq_len)
key = torch.randn(batch_size, dim, num_heads, seq_len)
value = torch.randn(batch_size, dim, num_heads, seq_len)

ARGS = {
    "query": query,
    "key": key,
    "value": value
}
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 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
CT3DHead Not yet run
unverified (harvested, no recorded run)
hlsheng1/ct3d/pcdet/models/roi_heads/ct3d_head.py
code served (permissive licence) · get_code("77a66a7bbe4e9a9c")
How it ran

no invocation recorded.

ProposalTargetLayer Not yet run
unverified (harvested, no recorded run)
hlsheng1/ct3d/pcdet/models/roi_heads/ct3d_head.py
code served (permissive licence) · get_code("d54c911dcaa871cf")
How it ran

no invocation recorded.

RoIHeadTemplate Not yet run
unverified (harvested, no recorded run)
hlsheng1/ct3d/pcdet/models/roi_heads/ct3d_head.py
code served (permissive licence) · get_code("443b75afeff90018")
How it ran

no invocation recorded.

Transformer Not yet run
unverified (harvested, no recorded run)
hlsheng1/ct3d/pcdet/models/roi_heads/ct3d_head.py
code served (permissive licence) · get_code("443cb18b71862421")
How it ran

no invocation recorded.

build_transformer Not yet run
unverified (harvested, no recorded run)
hlsheng1/ct3d/pcdet/models/roi_heads/ct3d_head.py
code served (permissive licence) · get_code("2b5d92421f68b895")
How it ran

no invocation recorded.

class_agnostic_nms Not yet run
unverified (harvested, no recorded run)
hlsheng1/ct3d/pcdet/models/roi_heads/ct3d_head.py
code served (permissive licence) · get_code("c0b17d12fe8897b3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 9 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 9 later) and 3 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
build_transformer
brick of this paper's assembly: helper
32 other papers
6 dated earlier, 1 the same month, 25 later
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2103.12115 (2021-03)
End-to-End Trainable Multi-Instance Pose Estimation with Transformers
2104.04369 (2021-04)
Video-aided Unsupervised Grammar Induction
and 29 more not named here
TransformerEncoder
brick of this paper's assembly: model
16 other papers
5 dated earlier, 1 the same month, 10 later · 7 only as an assembly brick
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2103.11468 (2021-03)
Learning Multi-Scene Absolute Pose Regression with Transformers
2103.12236 (2021-03)
Instance-level Image Retrieval using Reranking Transformers
and 13 more not named here
TransformerEncoderLayer
brick of this paper's assembly: helper
16 other papers
4 dated earlier, 12 later · 8 only as an assembly brick
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2103.11468 (2021-03)
Learning Multi-Scene Absolute Pose Regression with Transformers
2104.02439 (2021-04)
Few-Shot Transformation of Common Actions into Time and Space
and 13 more not named here
TransformerDecoder
brick of this paper's assembly: model
8 other papers
4 dated earlier, 1 the same month, 3 later · 4 only as an assembly brick
2005.12872 (2020-05)
End-to-End Object Detection with Transformers
2103.11468 (2021-03)
Learning Multi-Scene Absolute Pose Regression with Transformers
2104.03964 (2021-04)
Handwriting Transformers
and 5 more not named here
MultiHeadedAttention
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2308.07732 (2023-08)
UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation
Transformer
brick of this paper's assembly: model
1 other paper
1 later · 1 only as an assembly brick
2308.07732 (2023-08)
UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation
TransformerDecoderLayer
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2308.07732 (2023-08)
UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation
attention
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2308.07732 (2023-08)
UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation
class_agnostic_nms
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2109.02499 (2021-09)
Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

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

Though 3D object detection from point clouds has achieved rapid progress in recent years, the lack of flexible and high-performance proposal refinement remains a great hurdle for existing state-of-the-art two-stage detectors. Previous works on refining 3D proposals have relied on humandesigned components such as keypoints sampling, set abstraction and multi-scale feature fusion to produce powerful 3D object representations. Such methods, however, have limited ability to capture rich contextual dependencies among points. In this paper, we leverage the high-quality region proposal network and a Channel-wise Transformer architecture to constitute our two-stage 3D object detection framework (CT3D) with minimal hand-crafted design. The proposed CT3D simultaneously performs proposal-aware embedding and channel-wise context aggregation for the point features within each proposal. Specifically, CT3D uses proposal's keypoints for spatial contextual modelling and learns attention propagation in the encoding module, mapping the proposal to point embeddings. Next, a new channel-wise decoding module enriches the query-key interaction via channel-wise re-weighting to effectively merge multi-level contexts, which contributes to more accurate object predictions. Extensive experiments demonstrate that our CT3D method has superior performance and excellent scalability. Remarkably, CT3D achieves the AP of 81.77% in the moderate car category on the KITTI test 3D detection benchmark, outperforms state-of-the-art 3D detectors.

For agents

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

get_harvested_code_for_paper("2108.10723")
get_code_for_paper("2108.10723")
have("2108.10723")

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

curl https://syntology.ai/api/ran/2108.10723.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.10723.svg)](https://syntology.ai/paper/2108.10723)

Connect an agent — have() is free.