SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.13870 · 2020

A Unified Framework of Surrogate Loss by Refactoring and Interpolation

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 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 2 have no contract verdict; 1 failure of our instrument; 4 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/2007.13870.json · badge: /api/ran/2007.13870.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
princeton-vl/uniloss canonical (classifier label)
classifier basis: census
3 ran · 4 no recorded run
FunctionStatusWhere it lives
ap_frombins Ran
ran on a synthesized input
princeton-vl/uniloss/binary_classficiation/ap_frombins.py
code served (permissive licence) · get_code("3adee5742c021578")
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
import numpy as np

torch.manual_seed(0)

# The function ap_frombins takes:
# - bins: used with indexing (bins[idx]), compared with > 0
# - target: a tensor with .float(), .size(0), indexing, .sum(), and tensor indexing

# Create small test data
# bins should be a list or array that can be indexed
# We need bs*(bs-1)/2 elements for the nested loop comparisons
bs = 3
num_comparisons = bs * (bs - 1) // 2  # 3 comparisons for bs=3

# bins: array/list of values that will be compared with 0
bins = np.array([1.0, -1.0, 0.5])

# target: tensor with batch size bs, containing binary labels (0 or 1)
target = torch.tensor([1.0, 0.0, 1.0])

ARGS = {
    "bins": bins,
    "target": target,
}
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 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
binary_ap Ran
ran on a synthesized input
princeton-vl/uniloss/binary_classficiation/binary_ap.py
code served (permissive licence) · get_code("b11a721c6f455cfd")
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 testing
# pred: shape (bs, num_cols) - predictions for multiple classes
# target: shape (bs,) - binary targets
# col: integer index for which column to extract

bs = 2  # batch size
num_cols = 4  # number of columns

pred = torch.randn(bs, num_cols)  # shape (2, 4)
target = torch.tensor([1.0, 0.0])  # shape (2,) - binary targets
col = 1  # column index to extract

ARGS = {
    "pred": pred,
    "target": target,
    "col": col,
}
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
conv3x3 Ran
ran; our contract draft was wrong, not the code
princeton-vl/uniloss/multi_classification/resnet.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from chenxiangma/auglocal, is pointer only (licence: NONE) · get_code("6af95ebe99af2e36")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from chenxiangma/auglocal, and GitHub detected no licence in that repository 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.

get_test_loader Not yet run
unverified (harvested, no recorded run)
princeton-vl/uniloss/binary_classficiation/data_loader.py
code served (permissive licence) · get_code("f2408826617b17ac")
How it ran

no invocation recorded.

get_test_loader Not yet run
unverified (harvested, no recorded run)
princeton-vl/uniloss/multi_classification/data_loader.py
code served (permissive licence) · get_code("b53a1c00ac666f44")
How it ran

no invocation recorded.

get_train_valid_loader Not yet run
unverified (harvested, no recorded run)
princeton-vl/uniloss/binary_classficiation/data_loader.py
code served (permissive licence) · get_code("fa23ed58235aa52c")
How it ran

no invocation recorded.

get_train_valid_loader Not yet run
unverified (harvested, no recorded run)
princeton-vl/uniloss/multi_classification/data_loader.py
code served (permissive licence) · get_code("5b3223075bdf5993")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 6 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
conv3x3 686 other papers
238 dated earlier, 16 the same month, 431 later, 1 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 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

We introduce UniLoss, a unified framework to generate surrogate losses for training deep networks with gradient descent, reducing the amount of manual design of task-specific surrogate losses. Our key observation is that in many cases, evaluating a model with a performance metric on a batch of examples can be refactored into four steps: from input to real-valued scores, from scores to comparisons of pairs of scores, from comparisons to binary variables, and from binary variables to the final performance metric. Using this refactoring we generate differentiable approximations for each non-differentiable step through interpolation. Using UniLoss, we can optimize for different tasks and metrics using one unified framework, achieving comparable performance compared with task-specific losses. We validate the effectiveness of UniLoss on three tasks and four datasets. Code is available at https://github.com/princeton-vl/uniloss.

For agents

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

get_harvested_code_for_paper("2007.13870")
get_code_for_paper("2007.13870")
have("2007.13870")

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

curl https://syntology.ai/api/ran/2007.13870.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.13870.svg)](https://syntology.ai/paper/2007.13870)

Connect an agent — have() is free.