SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.09770 · ACL · 2022

Prototypical Verbalizer for Prompt-based Few-shot Tuning

Zhiyuan Liu, Ning Ding, Ganqu Cui, Longtao Huang, Shengding Hu

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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 1 has no contract verdict; 0 failures of our instrument; 2 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/2203.09770.json · badge: /api/ran/2203.09770.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
thunlp/OpenPrompt canonical (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
FunctionStatusWhere it lives
get_config_from_file Ran
ran on a synthesized input
thunlp/OpenPrompt/openprompt/config.py
code served (permissive licence) · get_code("b50275399496884d")
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 CfgNode. 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 tempfile
import os
from yacs.config import CfgNode

# Create a temporary config file
temp_dir = tempfile.mkdtemp()
config_file_path = os.path.join(temp_dir, "test_config.yaml")

# Write a valid YACS config file
with open(config_file_path, 'w') as f:
    f.write("""
MODEL:
  NAME: "resnet50"
  NUM_LAYERS: 50
TRAIN:
  LR: 0.001
  BATCH_SIZE: 32
  EPOCHS: 100
DATA:
  ROOT: "/path/to/data"
""")

ARGS = {
    "path": config_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yacs — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CfgNode — a CfgNode output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CfgNode 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
get_conditional_config Not yet run
unverified (harvested, no recorded run)
thunlp/OpenPrompt/openprompt/config.py
code served (permissive licence) · get_code("c4adc1412f1960c8")
How it ran

no invocation recorded.

get_user_config Not yet run
unverified (harvested, no recorded run)
thunlp/OpenPrompt/openprompt/config.py
code served (permissive licence) · get_code("9cdefe23f43015ca")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 0 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_conditional_config 4 other papers
1 dated earlier, 3 later
2111.01998 (2021-11)
OpenPrompt: An Open-source Framework for Prompt-learning
2211.00151 (2022-11)
A Close Look into the Calibration of Pre-trained Language Models
2303.02909 (2023-03)
Dynamic Prompting: A Unified Framework for Prompt Tuning
and 1 more not named here
get_config_from_file 4 other papers
1 dated earlier, 3 later
2111.01998 (2021-11)
OpenPrompt: An Open-source Framework for Prompt-learning
2211.00151 (2022-11)
A Close Look into the Calibration of Pre-trained Language Models
2303.02909 (2023-03)
Dynamic Prompting: A Unified Framework for Prompt Tuning
and 1 more not named here
get_user_config 4 other papers
1 dated earlier, 3 later
2111.01998 (2021-11)
OpenPrompt: An Open-source Framework for Prompt-learning
2211.00151 (2022-11)
A Close Look into the Calibration of Pre-trained Language Models
2303.02909 (2023-03)
Dynamic Prompting: A Unified Framework for Prompt Tuning
and 1 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

Prompt-based tuning for pre-trained language models (PLMs) has shown its effectiveness in few-shot learning. Typically, prompt-based tuning wraps the input text into a cloze question. To make predictions, the model maps the output words to labels via a verbalizer, which is either manually designed or automatically built. However, manual verbalizers heavily depend on domain-specific prior knowledge and human efforts, while finding appropriate label words automatically still remains challenging. In this work, we propose the prototypical verbalizer (ProtoVerb) which is built directly from training data. Specifically, Pro-toVerb learns prototype vectors as verbalizers by contrastive learning. In this way, the prototypes summarize training instances and are able to enclose rich class-level semantics. We conduct experiments on both topic classification and entity typing tasks, and the results demonstrate that ProtoVerb significantly outperforms current automatic verbalizers, especially when training data is extremely scarce. More surprisingly, ProtoVerb consistently boosts promptbased tuning even on untuned PLMs, indicating an elegant non-tuning way to utilize PLMs. Our codes are avaliable at https: //github.com/thunlp/OpenPrompt.

For agents

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

get_harvested_code_for_paper("2203.09770")
get_code_for_paper("2203.09770")
have("2203.09770")

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

curl https://syntology.ai/api/ran/2203.09770.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.09770.svg)](https://syntology.ai/paper/2203.09770)

Connect an agent — have() is free.