Yu Cheng, Jason Wei, Soroush Vosoughi, Chengyu Huang, Shiqi Xu
1 of 4 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 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/2103.07552.json · badge: /api/ran/2103.07552.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.
| Repository | Role | Ran |
|---|---|---|
| copy not recorded | community not in the paper's declared repositories |
1 ran · 0 no recorded run |
| jasonwei20/triplet-loss | marked official in Papers with Code Papers with Code archive |
0 ran · 3 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| get_only_chars | Ran ran; our contract draft was wrong, not the code |
this paper's copy was not recorded; identical code first harvested from tom4649/lp-ft_ntk pointer only · get_code("f15117422b72cf43") How it ranThe 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. |
| add_word | Not yet run unverified (harvested, no recorded run) |
jasonwei20/triplet-loss/utils/augmentation.py pointer only (licence: NONE) · get_code("aaab64f44df99509") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, jasonwei20/triplet-loss 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. |
| eda | Not yet run unverified (harvested, no recorded run) |
jasonwei20/triplet-loss/utils/augmentation.py pointer only (licence: NONE) · get_code("0962b30e7758e5da") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, jasonwei20/triplet-loss 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. |
| random_insertion | Not yet run unverified (harvested, no recorded run) |
jasonwei20/triplet-loss/utils/augmentation.py pointer only (licence: NONE) · get_code("9b8518d494e188ec") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, jasonwei20/triplet-loss 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. |
Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 later) and 2 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.
| Function | Also present in | Earliest-dated | Others named |
|---|---|---|---|
| get_only_chars brick of this paper's assembly: helper |
6 other papers 1 dated earlier, 5 later |
1901.11196 (2019-01) EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks |
2204.01959 (2022-04) Data Augmentation for Intent Classification with Off-the-shelf Large Language Models 2205.01308 (2022-05) Contrastive Learning for Prompt-Based Few-Shot Language Learners and 3 more not named here |
| random_insertion brick of this paper's assembly: data_transform |
1 other paper 1 later |
2109.05941 (2021-09) Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learning |
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Few-shot text classification is a fundamental NLP task in which a model aims to classify text into a large number of categories, given only a few training examples per category. This paper explores data augmentation-a technique particularly suitable for training with limited data-for this few-shot, highlymulticlass text classification setting. On four diverse text classification tasks, we find that common data augmentation techniques can improve the performance of triplet networks by up to 3.0% on average. To further boost performance, we present a simple training strategy called curriculum data augmentation, which leverages curriculum learning by first training on only original examples and then introducing augmented data as training progresses. We explore a twostage and a gradual schedule, and find that, compared with standard single-stage training, curriculum data augmentation trains faster, improves performance, and remains robust to high amounts of noising from augmentation.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.07552")
get_code_for_paper("2103.07552")
have("2103.07552")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2103.07552.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2103.07552)
Connect an agent — have() is free.