SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.26389 · 2026

Maintaining Difficulty: A Margin Scheduler for Triplet Loss in Siamese Networks Training

Garcia Lucas, Pedroso, Paulo Lisboa De Almeida, Oge Marques, Roberto Sprengel, Minozzo Tomchak, Luiz Oliveira

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 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; 0 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2603.26389.json · badge: /api/ran/2603.26389.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
robertotomchak/maintaining-difficulty community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
AdaptiveTripletMarginLoss Ran
ran on a synthesized input · constructed an object; no result was computed
robertotomchak/maintaining-difficulty/Loss.py
code served (permissive licence) · get_code("31c4c9d247bfae26")
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 an instance of its own class, AdaptiveTripletMarginLoss: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

# Build a custom distance function to test the distance_function parameter
class CustomPairwiseDistance(nn.Module):
    def forward(self, x1, x2):
        return torch.norm(x1 - x2, p=2, dim=1)

# Create an instance of the custom distance function
custom_dist = CustomPairwiseDistance()

# Define ARGS dictionary with all parameters
ARGS = {
    'margin': 0.5,
    'threshold': 0.95,
    'increase': 0.05,
    'swap': False,
    'reduction': 'mean',
    'distance_function': custom_dist
}
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 AdaptiveTripletMarginLoss — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a AdaptiveTripletMarginLoss 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

The Triplet Margin Ranking Loss is one of the most widely used loss functions in Siamese Networks for solving Distance Metric Learning (DML) problems. This loss function depends on a margin parameter µ, which defines the minimum distance that should separate positive and negative pairs during training. In this work, we show that, during training, the effective margin of many triplets often exceeds the predefined value of µ, provided that a sufficient number of triplets violating this margin is observed. This behavior indicates that fixing the margin throughout training may limit the learning process. Based on this observation, we propose a margin scheduler that adjusts the value of µ according to the proportion of easy triplets observed at each epoch, with the goal of maintaining training difficulty over time. We show that the proposed strategy leads to improved performance when compared to both a constant margin and a monotonically increasing margin scheme. Experimental results on four different datasets show consistent gains in verification performance. Our trained models and source code are available at github.com/robertotomchak/maintaining-difficulty.

For agents

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

get_harvested_code_for_paper("2603.26389")
get_code_for_paper("2603.26389")
have("2603.26389")

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

curl https://syntology.ai/api/ran/2603.26389.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.26389.svg)](https://syntology.ai/paper/2603.26389)

Connect an agent — have() is free.