SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.04966 · 2020

Prototypical Contrastive Learning of Unsupervised Representations

arXiv · PDF · Open in the Atlas

Code that ran

2 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, 1 violated it and 0 have no contract verdict; 1 failure 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/2005.04966.json · badge: /api/ran/2005.04966.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
salesforce/PCL canonical (classifier label)
classifier basis: classifier_2025
2 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_ap Ran
ran, violated the contract we drafted
salesforce/PCL/eval_svm_voc.py
code served (permissive licence) · get_code("ebb82e479d372d1d")
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 1, dtype family float, shape (1,) 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

# Looking at the function, it expects:
# - rec: a numpy array with a 'size' attribute and reshape method
# - prec: a numpy array with a 'size' attribute and reshape method
# The function treats these as 1D arrays of recall and precision values

# Create sample recall and precision arrays
# These should represent points on a precision-recall curve
rec = np.array([0.0, 0.2, 0.4, 0.6, 0.8, 1.0])
prec = np.array([1.0, 0.95, 0.85, 0.70, 0.50, 0.3])

ARGS = {
    'rec': rec,
    'prec': prec
}
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 1, dtype family float, shape (1,) — shape (1,) 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_precision_recall Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
salesforce/PCL/eval_svm_voc.py
code served (permissive licence) · get_code("5779ac02cf555fe2")
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 numpy as np

# Analyze the function get_precision_recall:
# - targets: array-like, compared with 0, converted to float32
# - preds: array-like, used for scoring/sorting, converted to float64
# Both should be 1D arrays of the same length

# Create small test data
targets = np.array([1, 0, 1, 2, 0], dtype=np.float32)
preds = np.array([0.9, 0.2, 0.8, 0.95, 0.1], dtype=np.float32)

ARGS = {
    "targets": targets,
    "preds": preds
}
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 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
accuracy Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from zbh2047/clipping-algorithms
pointer only; the stored copy get_code serves, from zbh2047/clipping-algorithms, is pointer only (licence: NONE) · get_code("9b8289076669fe4f")
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. No invocation recorded.

compute_features Not yet run
unverified (harvested, no recorded run)
salesforce/PCL/main_pcl.py
code served (permissive licence) · get_code("2e8c79927398fd28")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
salesforce/PCL/eval_cls_imagenet.py
code served (permissive licence) · get_code("e905656ff0c6e04a")
How it ran

no invocation recorded.

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, 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 4 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
accuracy 80 other papers
36 dated earlier, 2 the same month, 42 later
1307.0414 (2013-07)
Challenges in Representation Learning: A report on three machine learning contests
1412.6553 (2014-12)
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
1503.02531 (2015-03)
Distilling the Knowledge in a Neural Network
and 77 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

This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning. PCL not only learns low-level features for the task of instance discrimination, but more importantly, it implicitly encodes semantic structures of the data into the learned embedding space. Specifically, we introduce prototypes as latent variables to help find the maximum-likelihood estimation of the network parameters in an Expectation-Maximization framework. We iteratively perform E-step as finding the distribution of prototypes via clustering and M-step as optimizing the network via contrastive learning. We propose ProtoNCE loss, a generalized version of the InfoNCE loss for contrastive learning, which encourages representations to be closer to their assigned prototypes. PCL outperforms state-of-the-art instance-wise contrastive learning methods on multiple benchmarks with substantial improvement in low-resource transfer learning. Code and pretrained models are available at https://github.com/salesforce/PCL.

For agents

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

get_harvested_code_for_paper("2005.04966")
get_code_for_paper("2005.04966")
have("2005.04966")

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

curl https://syntology.ai/api/ran/2005.04966.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.04966.svg)](https://syntology.ai/paper/2005.04966)

Connect an agent — have() is free.