SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.00830 · 2024

Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 3 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/2406.00830.json · badge: /api/ran/2406.00830.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
yangcaoai/CoDA_NeurIPS2023 canonical (classifier label)
classifier basis: census
8 ran · 3 no recorded run
FunctionStatusWhere it lives
adjust_learning_rate Ran
ran, honoured the contract we drafted
yangcaoai/CoDA_NeurIPS2023/engine.py
code served (permissive licence) · get_code("708e6c6c165cb1cd")
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 float, 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
import torch.nn as nn
import torch.optim as optim
import math

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Create args object as a simple class with required attributes
class Args:
    def __init__(self):
        self.warm_lr_epochs = 2
        self.max_epoch = 10
        self.warm_lr = 0.0001
        self.base_lr = 0.1
        self.final_lr = 0.001

args = Args()

# Current epoch normalized (between 0 and 1)
curr_epoch = 0.5

ARGS = {
    'args': args,
    'optimizer': optimizer,
    'curr_epoch': curr_epoch
}
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 float, 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
compute_learning_rate Ran
ran, honoured the contract we drafted
yangcaoai/CoDA_NeurIPS2023/engine.py
code served (permissive licence) · get_code("ce7775d94f0bd12d")
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 float, 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 math

class Args:
    def __init__(self):
        self.warm_lr_epochs = 5
        self.max_epoch = 100
        self.warm_lr = 0.0001
        self.base_lr = 0.1
        self.final_lr = 0.00001

ARGS = {
    'args': Args(),
    'curr_epoch_normalized': 0.5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 float, 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
filter_pretrained_cfg Ran
ran; our contract draft was wrong, not the code
yangcaoai/CoDA_NeurIPS2023/models/_pretrained.py
code served (permissive licence) · get_code("744b11661038b00f")
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)

# Construct a sample pretrained config dictionary
cfg = {
    'url': 'https://example.com/model.pth',
    'file': '/path/to/model.pth',
    'hf_hub_id': 'org/model',
    'hf_hub_filename': 'model.safetensors',
    'source': 'timm',
    'pool_size': (7, 7),
    'first_conv': {'out_channels': 64, 'kernel_size': 7},
    'classifier': 'linear',
    'num_classes': 1000,
    'input_size': (3, 224, 224),
    'crop_pct': 0.875,
    'interpolation': 'bicubic',
    'mean': [0.485, 0.456, 0.406],
    'std': [0.229, 0.224, 0.225],
    'architecture': 'resnet50',
    'pretrained': True,
    'some_null_field': None,
    'another_null_field': None,
}

ARGS = {
    'cfg': cfg,
    'remove_source': False,
    'remove_null': 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 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
flip_axis_to_camera Ran
ran, honoured the contract we drafted
yangcaoai/CoDA_NeurIPS2023/datasets/scannet_utils.py
code served (permissive licence) · get_code("3ed80fe1e3b53d53")
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 (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 numpy as np

# Create a small point cloud with shape (N, 3)
# Using 4 points to have a small but non-trivial example
pc = np.array([
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0],
    [7.0, 8.0, 9.0],
    [10.0, 11.0, 12.0]
], dtype=np.float32)

ARGS = {
    "pc": pc
}
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 2, dtype family float, shape (4, 3) — shape (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
flip_axis_to_camera_tensor Ran
ran; our contract draft was wrong, not the code
yangcaoai/CoDA_NeurIPS2023/datasets/scannet_utils.py
code served (permissive licence) · get_code("63a11dcc6cbfa161")
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 2, dtype family float, shape (2, 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)

# Create a small point cloud tensor with shape (N, 3)
# N=2 points, 3 coordinates each
pc = torch.randn(2, 3)

ARGS = {
    "pc": pc
}
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 2, dtype family float, shape (2, 3) — shape (2, 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
flip_axis_to_depth Ran
ran, honoured the contract we drafted
yangcaoai/CoDA_NeurIPS2023/datasets/scannet_utils.py
code served (permissive licence) · get_code("9ffea672391678c2")
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 (2, 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

# Create a small point cloud array
# Shape: (2, 3) - 2 points with 3 coordinates (x, y, z)
pc = np.array([
    [1.0, 2.0, 3.0],
    [4.0, 5.0, 6.0]
], dtype=np.float32)

ARGS = {
    "pc": pc
}
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 2, dtype family float, shape (2, 3) — shape (2, 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
pretrained_cfg_for_features Ran
ran; our contract draft was wrong, not the code
yangcaoai/CoDA_NeurIPS2023/models/_builder.py
code served (permissive licence) · get_code("08cf29ad66c15a74")
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 copy import deepcopy

# Construct a valid pretrained_cfg dict
# The function will deepcopy it and remove certain keys
pretrained_cfg = {
    'num_classes': 1000,
    'classifier': 'linear',
    'global_pool': 'avg',
    'architecture': 'resnet50',
    'input_size': (3, 224, 224),
    'mean': [0.485, 0.456, 0.406],
    'std': [0.229, 0.224, 0.225],
}

ARGS = {
    'pretrained_cfg': pretrained_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 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
split_model_name_tag Ran
ran; our contract draft was wrong, not the code
yangcaoai/CoDA_NeurIPS2023/models/_pretrained.py
code served (permissive licence) · get_code("1113702c1be31a65")
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 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

def split_model_name_tag(model_name: str, no_tag=''):
    model_name, *tag_list = model_name.split('.', 1)
    tag = tag_list[0] if tag_list else no_tag
    return (model_name, tag)

ARGS = {
    'model_name': 'bert.v2',
    'no_tag': ''
}
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 float — 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
build_model_with_cfg Not yet run
unverified (harvested, no recorded run)
yangcaoai/CoDA_NeurIPS2023/models/_builder.py
code served (permissive licence) · get_code("2333de27c6f455ad")
How it ran

no invocation recorded.

generate_default_cfgs Not yet run
unverified (harvested, no recorded run)
yangcaoai/CoDA_NeurIPS2023/models/_pretrained.py
code served (permissive licence) · get_code("322418b4b7acb44e")
How it ran

no invocation recorded.

resolve_pretrained_cfg Not yet run
unverified (harvested, no recorded run)
yangcaoai/CoDA_NeurIPS2023/models/_builder.py
code served (permissive licence) · get_code("29a3e687db3fce97")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 4 later) and 7 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
adjust_learning_rate 4 other papers
2 dated earlier, 2 later
2308.04409 (2023-08)
V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection
2311.18651 (2023-11)
LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning
2407.08931 (2024-07)
Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection
and 1 more not named here
compute_learning_rate 4 other papers
2 dated earlier, 2 later
2311.18651 (2023-11)
LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning
2312.10763 (2023-12)
M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts
2407.08931 (2024-07)
Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection
and 1 more not named here
pretrained_cfg_for_features 1 other paper
1 later
2410.23623 (2024-10)
On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection
resolve_pretrained_cfg 1 other paper
1 later
2410.23623 (2024-10)
On Learning Multi-Modal Forgery Representation for Diffusion Generated Video 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

Open-vocabulary 3D Object Detection (OV-3DDet) addresses the detection of objects from an arbitrary list of novel categories in 3D scenes, which remains a very challenging problem. In this work, we propose CoDAv2, a unified framework designed to innovatively tackle both the localization and classification of novel 3D objects, under the condition of limited base categories. For localization, the proposed 3D Novel Object Discovery (3D-NOD) strategy utilizes 3D geometries and 2D open-vocabulary semantic priors to discover pseudo labels for novel objects during training. 3D-NOD is further extended with an Enrichment strategy that significantly enriches the novel object distribution in the training scenes, and then enhances the model's ability to localize more novel objects. The 3D-NOD with Enrichment is termed 3D-NODE. For classification, the Discovery-driven Cross-modal Alignment (DCMA) module aligns features from 3D point clouds and 2D/textual modalities, employing both class-agnostic and class-specific alignments that are iteratively refined to handle the expanding vocabulary of objects. Besides, 2D box guidance boosts the classification accuracy against complex background noises, which is coined as Box-DCMA. Extensive evaluation demonstrates the superiority of CoDAv2. CoDAv2 outperforms the best-performing method by a large margin (AP_Novel of 9.17 vs. 3.61 on SUN-RGBD and 9.12 vs. 3.74 on ScanNetv2). Source code and pre-trained models are available at the GitHub project page.

For agents

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

get_harvested_code_for_paper("2406.00830")
get_code_for_paper("2406.00830")
have("2406.00830")

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

curl https://syntology.ai/api/ran/2406.00830.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.00830.svg)](https://syntology.ai/paper/2406.00830)

Connect an agent — have() is free.