SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.00593 · EACL Findings · 2023

Reliable Gradient-free and Likelihood-free Prompt Tuning

Subhro Das, Soumya Ghosh, Prasanna Sattigeri, Yuheng Bu, Gregory Wornell, Maohao Shen

arXiv · PDF · Open in the Atlas

Code that ran

5 of 6 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 4 have no contract verdict; 1 failure of our instrument; 1 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/2305.00593.json · badge: /api/ran/2305.00593.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
maohaos2/SBI_LLM canonical (classifier label)
classifier basis: census
5 ran · 1 no recorded run
FunctionStatusWhere it lives
Entropy Ran
ran on a synthesized input
maohaos2/SBI_LLM/utils.py
code served (permissive licence) · get_code("1e1c05bc5a2f0504")
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 Tensor, ndim 1, dtype family float, shape (2,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# The function takes a probability distribution tensor and computes entropy
# It expects input_ to be a 2D tensor where:
# - dim 0 is the batch dimension
# - dim 1 is the probability distribution dimension
# We need values between 0 and 1 (probabilities)

input_tensor = torch.rand(2, 4)  # batch_size=2, num_classes=4
# Normalize to ensure valid probabilities
input_tensor = input_tensor / input_tensor.sum(dim=1, keepdim=True)

ARGS = {
    "input_": input_tensor
}
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 Tensor, ndim 1, dtype family float, shape (2,) — shape (2,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
brier_loss Ran
ran on a synthesized input
maohaos2/SBI_LLM/utils.py
code served (permissive licence) · get_code("5ab5d9cd232c87e9")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape 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)

# The function expects:
# - logit: a tensor of shape (batch_size, num_classes)
# - target: a tensor of shape (batch_size,) with class indices

batch_size = 2
num_classes = 4

# Create logit tensor with shape (2, 4)
logit = torch.randn(batch_size, num_classes)

# Create target tensor with shape (2,) containing valid class indices
target = torch.tensor([0, 3])

ARGS = {
    "logit": logit,
    "target": target,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
convert_to_features Ran
ran on a synthesized input
maohaos2/SBI_LLM/dataloader.py
code served (permissive licence) · get_code("0dfc4ac31a46001f")
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 dict. 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)

class MockTokenizer:
    def __init__(self):
        self.mask_token_id = 103
    
    def batch_encode_plus(self, texts, add_special_tokens=True):
        # Return mock encodings with input_ids and attention_mask
        batch_size = len(texts)
        # Create input_ids with mask token present for the first element
        input_ids = [
            [101, self.mask_token_id, 102, 0],  # First has mask token at index 1
            [101, 2054, self.mask_token_id, 102]  # Second has mask token at index 2
        ][:batch_size]
        
        attention_mask = [
            [1, 1, 1, 0],
            [1, 1, 1, 1]
        ][:batch_size]
        
        return {
            'input_ids': input_ids,
            'attention_mask': attention_mask
        }

example_batch = {
    'input_text': ['what is this', 'who are you'],
    'target_text': ['answer one', 'answer two']
}

tokenizer = MockTokenizer()

ARGS = {
    'example_batch': example_batch,
    'tokenizer': tokenizer
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
create_position_ids_from_input_ids Ran
ran; our contract draft was wrong, not the code
maohaos2/SBI_LLM/models/modeling_roberta.py
code served (permissive licence) · get_code("bbfc47d976ee7225")
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 Tensor, ndim 2, dtype family int, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Create a small batch of input_ids tensor
# Shape: (batch_size=2, seq_length=4)
# Values: token indices, with some padding tokens mixed in
input_ids = torch.tensor([
    [1, 2, 0, 3],
    [5, 0, 0, 4]
], dtype=torch.long)

# padding_idx is typically 0 in most transformer models
padding_idx = 0

ARGS = {
    "input_ids": input_ids,
    "padding_idx": padding_idx,
}
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 Tensor, ndim 2, dtype family int, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
hinge_loss Ran
ran on a synthesized input
maohaos2/SBI_LLM/utils.py
code served (permissive licence) · get_code("7bc8bc9cbcbec1d0")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

torch.manual_seed(0)

# Parameters for hinge_loss function
# logit: (N, C, d_1, d_2, ..., d_K) - let's use (N=2, C=4, d_1=3)
logit = torch.randn(2, 4, 3)

# target: (N, d_1, d_2, ..., d_K) - let's use (N=2, d_1=3)
# target values should be valid class indices in range [0, C-1], so [0, 3]
target = torch.randint(0, 4, (2, 3))

# margin: float - a small positive value
margin = 1.0

# reduction: str - one of 'sum', 'mean', 'none'
reduction = 'sum'

ARGS = {
    'logit': logit,
    'target': target,
    'margin': margin,
    'reduction': reduction
}
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 Tensor, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
load_tf_weights_in_bert Not yet run
unverified (harvested, no recorded run)
maohaos2/SBI_LLM/models/modeling_bert.py
code served (permissive licence) · get_code("26be70dca3249c0b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 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.

FunctionAlso present inEarliest-datedOthers named
load_tf_weights_in_bert 28 other papers
13 dated earlier, 1 the same month, 13 later, 1 same year, order not determinable
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
2021.emnlp-main.154 (2021 (year only))
Reconstruction Attack on Instance Encoding for Language Understanding
2104.06599 (2021-04)
Learning How to Ask: Querying LMs with Mixtures of Soft Prompts
and 25 more not named here
create_position_ids_from_input_ids 8 other papers
3 dated earlier, 1 the same month, 3 later, 1 same year, order not determinable
2021.emnlp-main.154 (2021 (year only))
Reconstruction Attack on Instance Encoding for Language Understanding
2104.08247 (2021-04)
What to Pre-Train on? Efficient Intermediate Task Selection
2201.03514 (2022-01)
Black-Box Tuning for Language-Model-as-a-Service
and 5 more not named here
convert_to_features 1 other paper
1 dated earlier
2201.03514 (2022-01)
Black-Box Tuning for Language-Model-as-a-Service
hinge_loss 1 other paper
1 dated earlier
2201.03514 (2022-01)
Black-Box Tuning for Language-Model-as-a-Service

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

Due to privacy or commercial constraints, large pre-trained language models (PLMs) are often offered as black-box APIs. Fine-tuning such models to downstream tasks is challenging because one can neither access the model's internal representations nor propagate gradients through it. This paper addresses these challenges by developing techniques for adapting PLMs with only API access. Building on recent work on soft prompt tuning, we develop methods to tune the soft prompts without requiring gradient computation. Further, we develop extensions that in addition to not requiring gradients also do not need to access any internal representation of the PLM beyond the input embeddings. Moreover, instead of learning a single prompt, our methods learn a distribution over prompts allowing us to quantify predictive uncertainty. Ours is the first work to consider uncertainty in prompts when only having API access to the PLM. Finally, through extensive experiments, we carefully vet the proposed methods and find them competitive with (and sometimes even improving on) gradient-based approaches with full access to the PLM.

For agents

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

get_harvested_code_for_paper("2305.00593")
get_code_for_paper("2305.00593")
have("2305.00593")

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

curl https://syntology.ai/api/ran/2305.00593.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.00593.svg)](https://syntology.ai/paper/2305.00593)

Connect an agent — have() is free.