SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.03195 · 2019

LVIS: A Dataset for Large Vocabulary Instance Segmentation

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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 5 have no contract verdict; 0 failures of our instrument; 0 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/1908.03195.json · badge: /api/ran/1908.03195.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
craston/object_detection_cib community (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_iou Ran
ran on a synthesized input
craston/object_detection_cib/kod/core/bbox/iou.py
code served (permissive licence) · get_code("0fb7599af3cad11b")
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 1, dtype family float, shape (2,) 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 two sets of bounding boxes in format [x1, y1, x2, y2]
# Shape: (batch_size, 4)
boxes1 = torch.tensor([
    [10.0, 10.0, 20.0, 30.0],
    [5.0, 5.0, 15.0, 15.0]
], dtype=torch.float32)

boxes2 = torch.tensor([
    [12.0, 12.0, 22.0, 32.0],
    [6.0, 6.0, 16.0, 16.0]
], dtype=torch.float32)

eps = 1e-07

ARGS = {
    "boxes1": boxes1,
    "boxes2": boxes2,
    "eps": eps
}
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 1, dtype family float, shape (2,) — shape (2,) 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_iou_unaligned Ran
ran on a synthesized input
craston/object_detection_cib/kod/core/bbox/iou.py
code served (permissive licence) · get_code("f0f4d92549fbddb9")
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, 5) 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 two sets of bounding boxes
# bboxes1: shape (2, 3, 4) - batch_size=2, num_boxes=3, coords=4
# bboxes2: shape (2, 5, 4) - batch_size=2, num_boxes=5, coords=4
# Format: [x1, y1, x2, y2] where x1,y1 is top-left and x2,y2 is bottom-right

bboxes1 = torch.tensor([
    [[0.0, 0.0, 10.0, 10.0],
     [5.0, 5.0, 15.0, 15.0],
     [20.0, 20.0, 30.0, 30.0]],
    [[1.0, 1.0, 11.0, 11.0],
     [6.0, 6.0, 16.0, 16.0],
     [21.0, 21.0, 31.0, 31.0]]
], dtype=torch.float32)

bboxes2 = torch.tensor([
    [[0.0, 0.0, 8.0, 8.0],
     [4.0, 4.0, 12.0, 12.0],
     [10.0, 10.0, 20.0, 20.0],
     [25.0, 25.0, 35.0, 35.0],
     [40.0, 40.0, 50.0, 50.0]],
    [[2.0, 2.0, 9.0, 9.0],
     [5.0, 5.0, 13.0, 13.0],
     [11.0, 11.0, 21.0, 21.0],
     [26.0, 26.0, 36.0, 36.0],
     [41.0, 41.0, 51.0, 51.0]]
], dtype=torch.float32)

ARGS = {
    "bboxes1": bboxes1,
    "bboxes2": bboxes2,
    "eps": 1e-07
}
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 3, dtype family float, shape (2, 3, 5) — shape (2, 3, 5) 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
fp16_clamp Ran
ran on a synthesized input
craston/object_detection_cib/kod/core/bbox/iou.py
code served (permissive licence) · get_code("0343317ba06fd841")
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, 4) 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 float16 tensor on CPU
x = torch.randn(2, 4, dtype=torch.float16)

# Define arguments for fp16_clamp
ARGS = {
    'x': x,
    'min': -1.0,
    'max': 1.0
}
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, 4) — shape (2, 4) 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_logger Ran
ran on a synthesized input
craston/object_detection_cib/kod/lightning/logger.py
code served (permissive licence) · get_code("d13d820fb1f13532")
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 Logger. 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 logging
from lightning.pytorch.utilities import rank_zero_only

torch_manual_seed = 0

ARGS = {
    "name": "test_logger"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
lightning — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
non_max_suppression Ran
ran on a synthesized input
craston/object_detection_cib/kod/core/nms.py
code served (permissive licence) · get_code("e2c4fbced38f2435")
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 list, 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 torchvision

torch.manual_seed(0)

# Create a small batch of detections
# Shape: (batch_size, num_detections, num_classes + 5)
# The +5 corresponds to: x1, y1, x2, y2, confidence
# We'll create 2 batches with 3 detections each and 3 classes
batch_size = 2
num_detections = 3
num_classes = 3

detections = torch.zeros((batch_size, num_detections, num_classes + 5))

# Fill with some sample detection data
# First batch
detections[0, 0] = torch.tensor([10.0, 20.0, 50.0, 60.0, 0.9, 0.7, 0.1, 0.2])  # high conf
detections[0, 1] = torch.tensor([15.0, 25.0, 55.0, 65.0, 0.8, 0.2, 0.6, 0.1])  # high conf
detections[0, 2] = torch.tensor([100.0, 100.0, 150.0, 150.0, 0.2, 0.1, 0.1, 0.8])  # low conf

# Second batch
detections[1, 0] = torch.tensor([5.0, 5.0, 40.0, 40.0, 0.85, 0.8, 0.1, 0.1])  # high conf
detections[1, 1] = torch.tensor([200.0, 200.0, 250.0, 250.0, 0.3, 0.2, 0.2, 0.1])  # low conf
detections[1, 2] = torch.tensor([30.0, 30.0, 80.0, 80.0, 0.7, 0.1, 0.7, 0.2])  # high conf

conf_thres = 0.25
nms_thres = 0.45
classes = [0, 1]  # Filter to keep only classes 0 and 1

ARGS = {
    "detections": detections,
    "conf_thres": conf_thres,
    "nms_thres": nms_thres,
    "classes": classes,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 3, dtype family float — a list 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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

Progress on object detection is enabled by datasets that focus the research community's attention on open challenges. This process led us from simple images to complex scenes and from bounding boxes to segmentation masks. In this work, we introduce LVIS (pronounced `el-vis'): a new dataset for Large Vocabulary Instance Segmentation. We plan to collect ~2 million high-quality instance segmentation masks for over 1000 entry-level object categories in 164k images. Due to the Zipfian distribution of categories in natural images, LVIS naturally has a long tail of categories with few training samples. Given that state-of-the-art deep learning methods for object detection perform poorly in the low-sample regime, we believe that our dataset poses an important and exciting new scientific challenge. LVIS is available at http://www.lvisdataset.org.

For agents

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

get_harvested_code_for_paper("1908.03195")
get_code_for_paper("1908.03195")
have("1908.03195")

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

curl https://syntology.ai/api/ran/1908.03195.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.03195.svg)](https://syntology.ai/paper/1908.03195)

Connect an agent — have() is free.