SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.05424 · EMNLP · 2021

Pairwise Supervised Contrastive Learning of Sentence Representations

Andrew Arnold, Henghui Zhu, Bing Xiang, Ramesh Nallapati, Dejiao Zhang, Shang-Wen Li, Wei Xiao

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; 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/2109.05424.json · badge: /api/ran/2109.05424.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
amazon-research/sentence-representations marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
PairSupConBert Ran
ran on a synthesized input · constructed an object; no result was computed
amazon-research/sentence-representations/PairSupCon/models/Transformers.py
code served (permissive licence) · get_code("6fa6e6f1318fd800")
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, PairSupConBert: 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
from transformers import BertConfig, BertModel

torch.manual_seed(0)

# Create a minimal BertConfig
bert_config = BertConfig(
    vocab_size=1000,
    hidden_size=128,
    num_hidden_layers=2,
    num_attention_heads=2,
    intermediate_size=256,
    hidden_dropout_prob=0.1,
    attention_probs_dropout_prob=0.1,
)

# Test case 1: evaluate task
input_ids_eval = torch.randint(0, 1000, (2, 8))  # batch_size=2, seq_len=8
attention_mask_eval = torch.ones(2, 8, dtype=torch.long)

# Test case 2: classification/contrastive/both tasks
# Need shape (batch_size, 2, seq_len) for unbinding
input_ids_pair = torch.randint(0, 1000, (2, 2, 8))  # (batch_size=2, pair_count=2, seq_len=8)
attention_mask_pair = torch.ones(2, 2, 8, dtype=torch.long)

ARGS = {
    "config": bert_config,
    "num_classes": 2,
    "feat_dim": 128,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PairSupConBert — 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 PairSupConBert 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

Many recent successes in sentence representation learning have been achieved by simply fine-tuning on the Natural Language Inference (NLI) datasets with triplet loss or siamese loss. Nevertheless, they share a common weakness: sentences in a contradiction pair are not necessarily from different semantic categories. Therefore, optimizing the semantic entailment and contradiction reasoning objective alone is inadequate to capture the high-level semantic structure. The drawback is compounded by the fact that the vanilla siamese or triplet losses only learn from individual sentence pairs or triplets, which often suffer from bad local optima. In this paper, we propose PairSupCon, an instance discrimination based approach aiming to bridge semantic entailment and contradiction understanding with high-level categorical concept encoding. We evaluate PairSupCon on various downstream tasks that involve understanding sentence semantics at different granularities. We outperform the previous state-of-theart method with 10%-13% averaged improvement on eight clustering tasks, and 5%-6% averaged improvement on seven semantic textual similarity (STS) tasks.

For agents

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

get_harvested_code_for_paper("2109.05424")
get_code_for_paper("2109.05424")
have("2109.05424")

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

curl https://syntology.ai/api/ran/2109.05424.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.05424.svg)](https://syntology.ai/paper/2109.05424)

Connect an agent — have() is free.