SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.14738 · NeurIPS · 2022

Cost-Sensitive Self-Training for Optimizing Non-Decomposable Metrics

R Venkatesh Babu, Harsh Rangwani, Shrinivas Ramasubramanian, Sho Takemori, Takashi Kato, Yuhei Umeda

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 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/2304.14738.json · badge: /api/ran/2304.14738.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
val-iisc/costsensitiveselftraining canonical (classifier label)
classifier basis: classifier_2025
4 ran · 3 no recorded run
FunctionStatusWhere it lives
CSLLoss Ran
ran on a synthesized input · constructed an object; no result was computed
val-iisc/costsensitiveselftraining/models/fixmatch/fixmatchCSST.py
pointer only (licence: NONE) · get_code("db6f345480c633d9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, val-iisc/costsensitiveselftraining 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_Scalar Ran
ran on a synthesized input · constructed an object; no result was computed
val-iisc/costsensitiveselftraining/models/fixmatch/fixmatchCSST.py
pointer only (licence: NONE) · get_code("78afd5155edadae1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, val-iisc/costsensitiveselftraining 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_metrics Ran
ran on a synthesized input
val-iisc/costsensitiveselftraining/models/fixmatch/fixmatchCSST.py
pointer only (licence: NONE) · get_code("ef03e1684bfdfe80")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, val-iisc/costsensitiveselftraining 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.

net_builder Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
val-iisc/costsensitiveselftraining/models/fixmatch/fixmatchCSST.py
pointer only (licence: NONE) · get_code("1855fa71751d4127")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, val-iisc/costsensitiveselftraining 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.

FixMatch Not yet run
unverified (harvested, no recorded run)
val-iisc/costsensitiveselftraining/models/fixmatch/fixmatchCSST.py
pointer only (licence: NONE) · get_code("890a1c88231f5bd4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, val-iisc/costsensitiveselftraining 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.

accuracy Not yet run
unverified (harvested, no recorded run)
val-iisc/costsensitiveselftraining/models/fixmatch/fixmatchCSST.py
pointer only (licence: NONE) · get_code("43d1c326e960fe77")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, val-iisc/costsensitiveselftraining 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.

setattr_cls_from_kwargs Not yet run
unverified (harvested, no recorded run)
val-iisc/costsensitiveselftraining/models/fixmatch/fixmatchCSST.py
pointer only (licence: NONE) · get_code("8698fafdeaeaacac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, val-iisc/costsensitiveselftraining 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.

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, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
Get_Scalar
brick of this paper's assembly: helper
8 other papers
4 dated earlier, 4 later · 8 only as an assembly brick
2001.07685 (2020-01)
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
2110.08263 (2021-10)
FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling
2203.02533 (2022-03)
BoostMIS: Boosting Medical Image Semi-supervised Learning with Adaptive Pseudo Labeling and Informative Active Annotation
and 5 more not named here
accuracy
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 2 only as an assembly brick
2001.07685 (2020-01)
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
2208.08631 (2022-08)
ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization

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

Self-training based semi-supervised learning algorithms have enabled the learning of highly accurate deep neural networks, using only a fraction of labeled data. However, the majority of work on self-training has focused on the objective of improving accuracy whereas practical machine learning systems can have complex goals (e.g. maximizing the minimum of recall across classes etc.) that are non-decomposable in nature. In this work, we introduce the Cost-Sensitive Self-Training (CSST) framework which generalizes the self-training-based methods for optimizing non-decomposable metrics. We prove that our framework can better optimize the desired non-decomposable metric utilizing unlabeled data, under similar data distribution assumptions made for the analysis of self-training. Using the proposed CSST framework we obtain practical self-training methods (for both vision and NLP tasks) for optimizing different non-decomposable metrics using deep neural networks. Our results demonstrate that CSST achieves an improvement over the state-of-the-art in majority of the cases across datasets and objectives.

For agents

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

get_harvested_code_for_paper("2304.14738")
get_code_for_paper("2304.14738")
have("2304.14738")

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

curl https://syntology.ai/api/ran/2304.14738.json

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

[![Syntology run record](https://syntology.ai/api/ran/2304.14738.svg)](https://syntology.ai/paper/2304.14738)

Connect an agent — have() is free.