SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.11942 · 2020

Towards Backward-Compatible Representation Learning

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 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 1 has no contract verdict; 4 failures of our instrument; 5 no recorded run), measured 2026-11-21; 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/2003.11942.json · badge: /api/ran/2003.11942.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
yifeizhou02/bt-2 reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
YantaoShen/openBCT reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 3 no recorded run
FunctionStatusWhere it lives
Backbone Ran
ran on a synthesized input
yifeizhou02/bt-2/models/resnet.py
pointer only (licence: NONE) · get_code("8c01dd7b393828af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yifeizhou02/bt-2 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.

BackboneBase Ran
ran; our contract draft was wrong, not the code
yifeizhou02/bt-2/models/resnet.py
pointer only (licence: NONE) · get_code("7042cceeb8b775f7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yifeizhou02/bt-2 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.

conv1x1 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from MediaBrain-SJTU/BCL
pointer only · get_code("d9def42110729a85")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from MediaBrain-SJTU/BCL
pointer only · get_code("160bb14bd76201b4")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

pairwise_distance Ran
ran; our contract draft was wrong, not the code
YantaoShen/openBCT/evaluate/evaluators.py
code served (permissive licence) · get_code("c0222e52bce8b04b")
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 Tensor, ndim 2, dtype family float, shape (2, 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
import torch.nn as nn

torch.manual_seed(0)

# Create a simple metric class that has a transform method
class SimpleMetric:
    def transform(self, x):
        # Simple transformation: just return the input
        return x

# Create small feature tensors (batch_size=2, feature_dim=4)
features = [
    torch.randn(2, 4),
    torch.randn(2, 4)
]

old_features = [
    torch.randn(2, 4),
    torch.randn(2, 4)
]

# Create query and gallery indices
query = [0, 1]
gallery = [0, 1]

# Create metric instance
metric = SimpleMetric()

ARGS = {
    "features": features,
    "old_features": old_features,
    "query": query,
    "gallery": gallery,
    "metric": metric
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 2) — shape (2, 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
ResNet Not yet run
unverified (harvested, no recorded run)
YantaoShen/openBCT/models/resnet.py
code served (permissive licence) · get_code("13331140f536b0c4")
How it ran

no invocation recorded.

ResNet Not yet run
unverified (harvested, no recorded run)
yifeizhou02/bt-2/models/resnet.py
pointer only (licence: NONE) · get_code("939bbcedb1825b72")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yifeizhou02/bt-2 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.

ResNet_ortho Not yet run
unverified (harvested, no recorded run)
yifeizhou02/bt-2/models/resnet.py
pointer only (licence: NONE) · get_code("f9a93c8d455dcd45")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yifeizhou02/bt-2 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.

evaluate_all Not yet run
unverified (harvested, no recorded run)
YantaoShen/openBCT/evaluate/evaluators.py
code served (permissive licence) · get_code("3e614bd12e5eada6")
How it ran

no invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
YantaoShen/openBCT/models/resnet.py
code served (permissive licence) · get_code("3ea19c97f450c87a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 3 the same month, 3 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
conv1x1
brick of this paper's assembly: helper
431 other papers
59 dated earlier, 12 the same month, 359 later, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3
brick of this paper's assembly: helper
312 other papers
30 dated earlier, 8 the same month, 273 later, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
resnet18 95 other papers
5 dated earlier, 4 the same month, 85 later, 1 undated
1805.00907 (2018-05)
Glow: Graph Lowering Compiler Techniques for Neural Networks
1902.08153 (2019-02)
Learned Step Size Quantization
1904.01355 (2019-04)
FCOS: Fully Convolutional One-Stage Object Detection
and 92 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 2026-11-21.

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 propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatible means that, if such features are used to compare images, then "new" features can be compared directly to "old" features, so they can be used interchangeably. This enables visual search systems to bypass computing new features for all previously seen images when updating the embedding models, a process known as backfilling. Backward compatibility is critical to quickly deploy new embedding models that leverage ever-growing large-scale training datasets and improvements in deep learning architectures and training methods. We propose a framework to train embedding models, called backward-compatible training (BCT), as a first step towards backward compatible representation learning. In experiments on learning embeddings for face recognition, models trained with BCT successfully achieve backward compatibility without sacrificing accuracy, thus enabling backfill-free model updates of visual embeddings.

For agents

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

get_harvested_code_for_paper("2003.11942")
get_code_for_paper("2003.11942")
have("2003.11942")

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

curl https://syntology.ai/api/ran/2003.11942.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.11942.svg)](https://syntology.ai/paper/2003.11942)

Connect an agent — have() is free.