SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.15727 · ECCV · 2024

LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation

Xiangyang Ji, Yan Di, Chenyangguang Zhang, Ruida Zhang, Xingxing Zuo, Ziqin Huang, Gu Wang, Jiwen Tang

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 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; 4 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 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/2409.15727.json · badge: /api/ran/2409.15727.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
lolrudy/LaPose canonical (classifier label)
classifier basis: census
10 ran · 2 no recorded run
FunctionStatusWhere it lives
gaussian_aleatoric_uncertainty_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lolrudy/LaPose/losses/uncertainty_loss.py
code served (permissive licence) · get_code("f0e17dd9afdc4ef3")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Create small tensors for the function parameters
batch_size = 2
dim = 4

input_tensor = torch.randn(batch_size, dim)
target_tensor = torch.randn(batch_size, dim)
log_variance_tensor = torch.randn(batch_size, dim)

ARGS = {
    'input': input_tensor,
    'target': target_tensor,
    'log_variance': log_variance_tensor,
    'reduction': 'mean'
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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: none by the harness; any seed is in the setup block
get_closest_rot Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lolrudy/LaPose/losses/pose_loss.py
code served (permissive licence) · get_code("d2ea259d1b19d283")
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 ndarray, ndim 2, dtype family float, shape (3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 valid 3x3 rotation matrices
def create_rotation_matrix():
    """Create a valid 3x3 rotation matrix using QR decomposition."""
    random_matrix = np.random.randn(3, 3)
    q, r = np.linalg.qr(random_matrix)
    # Ensure determinant is 1 (not -1)
    if np.linalg.det(q) < 0:
        q[:, 0] *= -1
    return q.astype(np.float32)

# Generate rotation matrices
rot_est = create_rotation_matrix()
rot_gt = create_rotation_matrix()

# Create symmetry info: Kx3x3 ndarray of rotation matrices
# K=2 symmetries
sym_info = np.array([
    create_rotation_matrix(),
    create_rotation_matrix()
], dtype=np.float32)

ARGS = {
    "rot_est": rot_est,
    "rot_gt": rot_gt,
    "sym_info": sym_info
}
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 ndarray, ndim 2, dtype family float, shape (3, 3) — shape (3, 3) as a later run recorded it
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: none by the harness; any seed is in the setup block
get_closest_rot_batch Ran
ran; our contract draft was wrong, not the code
lolrudy/LaPose/losses/pose_loss.py
code served (permissive licence) · get_code("9cab8f7c8dd2fdb3")
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 Tensor, ndim 3, dtype family float, shape (2, 3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 batch of predicted rotations [B, 3, 3]
batch_size = 2
pred_rots = torch.randn(batch_size, 3, 3)

# Create batch of ground truth rotations [B, 3, 3]
gt_rots = torch.randn(batch_size, 3, 3)

# Create symmetry info list
# First element: 2x3x3 symmetry matrices (object with 2 symmetries)
# Second element: None (no symmetry)
sym_info_0 = np.random.randn(2, 3, 3)
sym_info_1 = None
sym_infos = [sym_info_0, sym_info_1]

ARGS = {
    "pred_rots": pred_rots,
    "gt_rots": gt_rots,
    "sym_infos": sym_infos
}
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 Tensor, ndim 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 3) as a later run recorded it
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: none by the harness; any seed is in the setup block
get_mask_prob Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lolrudy/LaPose/network/PoseNet.py
code served (permissive licence) · get_code("3f181c78165b34de")
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 Tensor, ndim 4, dtype family float, shape (2, 1, 4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Test case 1: L1 loss type
pred_mask_l1 = torch.randn(2, 1, 4, 3)

# Test case 2: BCE loss type
pred_mask_bce = torch.randn(2, 1, 4, 3)

# Test case 3: CE loss type (needs c >= 2)
pred_mask_ce = torch.randn(2, 3, 4, 3)

# We'll use the L1 case as the primary test
ARGS = {
    'pred_mask': pred_mask_l1,
    'mask_loss_type': 'L1'
}
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 Tensor, ndim 4, dtype family float, shape (2, 1, 4, 3) — shape (2, 1, 4, 3) as a later run recorded it
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: none by the harness; any seed is in the setup block
get_xyz_doublemask_region_out_dim Ran
ran, honoured the contract we drafted
lolrudy/LaPose/network/model_utils.py
code served (permissive licence) · get_code("cda33f25b25606d1")
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, ndim 1, dtype family int; 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

class StandInConfig:
    def __init__(self, **kwargs):
        for key, value in kwargs.items():
            setattr(self, key, value)

# Build the nested config structure
loss_cfg = StandInConfig(
    XYZ_LOSS_TYPE='MSE',
    MASK_LOSS_TYPE='BCE'
)

g_head_cfg = StandInConfig(
    XYZ_BIN=8,
    NUM_REGIONS=5
)

net_cfg = StandInConfig(
    GEO_HEAD=g_head_cfg,
    LOSS_CFG=loss_cfg
)

model_cfg = StandInConfig(
    POSE_NET=net_cfg
)

cfg = StandInConfig(
    MODEL=model_cfg
)

ARGS = {
    'cfg': cfg
}
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, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
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: none by the harness; any seed is in the setup block
get_xyz_mask_out_dim Ran
ran, honoured the contract we drafted
lolrudy/LaPose/network/model_utils.py
code served (permissive licence) · get_code("eccb96d3c27a0c32")
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, ndim 1, dtype family int; 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

torch.manual_seed(0)

# Create a minimal config object that mimics the nested structure
class LossCfg:
    def __init__(self, xyz_loss_type, mask_loss_type):
        self.XYZ_LOSS_TYPE = xyz_loss_type
        self.MASK_LOSS_TYPE = mask_loss_type

class GeoHeadCfg:
    def __init__(self, xyz_bin):
        self.XYZ_BIN = xyz_bin

class PoseNetCfg:
    def __init__(self, geo_head_cfg, loss_cfg):
        self.GEO_HEAD = geo_head_cfg
        self.LOSS_CFG = loss_cfg

class ModelCfg:
    def __init__(self, pose_net_cfg):
        self.POSE_NET = pose_net_cfg

class Config:
    def __init__(self, model_cfg):
        self.MODEL = model_cfg

# Create instances with valid configurations
loss_cfg = LossCfg(xyz_loss_type='MSE', mask_loss_type='BCE')
geo_head_cfg = GeoHeadCfg(xyz_bin=16)
pose_net_cfg = PoseNetCfg(geo_head_cfg=geo_head_cfg, loss_cfg=loss_cfg)
model_cfg = ModelCfg(pose_net_cfg=pose_net_cfg)
cfg = Config(model_cfg=model_cfg)

ARGS = {
    'cfg': cfg
}
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, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
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: none by the harness; any seed is in the setup block
get_xyz_mask_region_out_dim Ran
ran, honoured the contract we drafted
lolrudy/LaPose/network/model_utils.py
code served (permissive licence) · get_code("c0267b560c7d9bc4")
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, ndim 1, dtype family int; 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

class DummyXYZBinConfig:
    def __init__(self):
        self.XYZ_BIN = 5
        self.NUM_REGIONS = 10

class DummyLossConfig:
    def __init__(self, xyz_loss_type='MSE', mask_loss_type='BCE'):
        self.XYZ_LOSS_TYPE = xyz_loss_type
        self.MASK_LOSS_TYPE = mask_loss_type

class DummyGeoHeadConfig:
    def __init__(self):
        self.XYZ_BIN = 5
        self.NUM_REGIONS = 10

class DummyPoseNetConfig:
    def __init__(self):
        self.GEO_HEAD = DummyGeoHeadConfig()
        self.LOSS_CFG = DummyLossConfig(xyz_loss_type='MSE', mask_loss_type='BCE')

class DummyModelConfig:
    def __init__(self):
        self.POSE_NET = DummyPoseNetConfig()

class DummyConfig:
    def __init__(self):
        self.MODEL = DummyModelConfig()

cfg = DummyConfig()

ARGS = {
    'cfg': cfg
}
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, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
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: none by the harness; any seed is in the setup block
laplacian_aleatoric_uncertainty_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lolrudy/LaPose/losses/uncertainty_loss.py
code served (permissive licence) · get_code("bba5373998491ff5")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Create small tensors with distinct shapes for different dimensions
batch_size = 2
feature_dim = 4

input_tensor = torch.randn(batch_size, feature_dim)
target_tensor = torch.randn(batch_size, feature_dim)
log_variance_tensor = torch.randn(batch_size, feature_dim)
balance_weight_value = 0.5

ARGS = {
    'input': input_tensor,
    'target': target_tensor,
    'log_variance': log_variance_tensor,
    'balance_weight': balance_weight_value,
    'reduction': 'mean',
    'sum_last_dim': 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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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: none by the harness; any seed is in the setup block
str2bool Ran
ran, violated the contract we drafted
lolrudy/LaPose/network/extractor_dino.py
code served (permissive licence) · get_code("7c508037b40522af")
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) and returned bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 argparse

def str2bool(v):
    if isinstance(v, bool):
        return v
    if v.lower() in ('yes', 'true', 't', 'y', '1'):
        return True
    elif v.lower() in ('no', 'false', 'f', 'n', '0'):
        return False
    else:
        raise argparse.ArgumentTypeError('Boolean value expected.')

# Test cases for str2bool
ARGS = {
    'v': 'true'  # string input that should convert to boolean
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
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: none by the harness; any seed is in the setup block
symmetry_rotation_matrix_y Ran
ran, honoured the contract we drafted
lolrudy/LaPose/losses/pose_loss.py
code served (permissive licence) · get_code("9dffb930679c0370")
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 ndarray, ndim 3, dtype family float, shape (30, 3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 numpy as np

def symmetry_rotation_matrix_y(number=30):
    result = []
    for i in range(number):
        theta = 2 * np.pi / number * i
        r = np.array([[np.cos(theta), 0, np.sin(theta)], [0, 1, 0], [-np.sin(theta), 0, np.cos(theta)]])
        result.append(r)
    result = np.stack(result)
    return result

ARGS = {
    "number": 30
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (30, 3, 3) — shape (30, 3, 3) as a later run recorded it
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: none by the harness; any seed is in the setup block
compute_mean_re_te Not yet run
unverified (harvested, no recorded run)
lolrudy/LaPose/network/PoseNet.py
code served (permissive licence) · get_code("3ba3d677fa36efd1")
How it ran

no invocation recorded.

get_rot_mat Not yet run
unverified (harvested, no recorded run)
lolrudy/LaPose/network/PoseNet.py
code served (permissive licence) · get_code("7fc242fb372d5b3b")
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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 11 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
str2bool 175 other papers
138 dated earlier, 3 the same month, 33 later, 1 same year, order not determinable · 2 only as an assembly brick
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1603.09382 (2016-03)
Deep Networks with Stochastic Depth
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
and 172 more not named here

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

While RGBD-based methods for category-level object pose estimation hold promise, their reliance on depth data limits their applicability in diverse scenarios. In response, recent efforts have turned to RGB-based methods; however, they face significant challenges stemming from the absence of depth information. On one hand, the lack of depth exacerbates the difficulty in handling intra-class shape variation, resulting in increased uncertainty in shape predictions. On the other hand, RGB-only inputs introduce inherent scale ambiguity, rendering the estimation of object size and translation an ill-posed problem. To tackle these challenges, we propose LaPose, a novel framework that models the object shape as the Laplacian mixture model for Pose estimation. By representing each point as a probabilistic distribution, we explicitly quantify the shape uncertainty. LaPose leverages both a generalized 3D information stream and a specialized feature stream to independently predict the Laplacian distribution for each point, capturing different aspects of object geometry. These two distributions are then integrated as a Laplacian mixture model to establish the 2D-3D correspondences, which are utilized to solve the pose via the PnP module. In order to mitigate scale ambiguity, we introduce a scale-agnostic representation for object size and translation, enhancing training efficiency and overall robustness. Extensive experiments on the NOCS datasets validate the effectiveness of LaPose, yielding state-of-the-art performance in RGB-based category-level object pose estimation. Codes are released at https://github.com/lolrudy/LaPose.

For agents

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

get_harvested_code_for_paper("2409.15727")
get_code_for_paper("2409.15727")
have("2409.15727")

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

curl https://syntology.ai/api/ran/2409.15727.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.15727.svg)](https://syntology.ai/paper/2409.15727)

Connect an agent — have() is free.