SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_33874 · AAAI · 2025

Scalable Acceleration for Classification-Based Derivative-Free Optimization

Yuan Jin, Zhipeng Guo, Tianyi Han, Jingya Li

Open in the Atlas

Code that ran

6 of 10 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 5 failures of our instrument; 4 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/aaai_33874.json · badge: /api/ran/aaai_33874.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
txsun1997/Black-Box-Tuning canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
FunctionStatusWhere it lives
BartLayerNorm Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
txsun1997/Black-Box-Tuning/models/deep_modeling_bart.py
code served (permissive licence) · get_code("be1791842044466a")
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 LayerNorm. 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 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 takes:
# - normalized_shape: torch.Size (the shape to normalize over, typically the last dimension(s))
# - eps: float (small epsilon for numerical stability, default 1e-05)
# - elementwise_affine: bool (whether to learn affine parameters, default True)

# normalized_shape should be a torch.Size object representing the shape of the normalized dimensions
# For LayerNorm, this is typically just the feature dimension
normalized_shape = torch.Size([768])

# eps is a float for numerical stability
eps = 1e-05

# elementwise_affine is a boolean indicating whether to learn scale and bias
elementwise_affine = True

ARGS = {
    "normalized_shape": normalized_shape,
    "eps": eps,
    "elementwise_affine": elementwise_affine,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
apex, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LayerNorm — a LayerNorm output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LayerNorm 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
attention_mask_func Ran
ran, honoured the contract we drafted
txsun1997/Black-Box-Tuning/models/deep_modeling_cpt.py
code served (permissive licence) · get_code("ce106170b591f393")
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 float, 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)

# attention_mask_func takes two parameters:
# 1. attention_scores: a tensor to which the mask is added
# 2. attention_mask: a tensor to be added to attention_scores

# Create small tensors with distinct shapes for clarity
attention_scores = torch.randn(2, 4)  # batch_size=2, sequence_length=4
attention_mask = torch.zeros(2, 4)    # same shape, mask of zeros

ARGS = {
    "attention_scores": attention_scores,
    "attention_mask": attention_mask,
}
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 float, 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
create_position_ids_from_input_ids Ran
ran; our contract draft was wrong, not the code
txsun1997/Black-Box-Tuning/models/deep_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
init_method Ran
ran; our contract draft was wrong, not the code
txsun1997/Black-Box-Tuning/models/deep_modeling_cpt.py
code served (permissive licence) · get_code("fba0a047e871cd2c")
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 function. 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)

# The function init_method takes a single parameter 'std' (standard deviation)
# and returns an initialization function that initializes tensors with normal distribution
# The returned function is meant to be used as an initializer for neural network parameters

std_value = 0.02

ARGS = {
    "std": std_value
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
shift_tokens_right Ran
ran; our contract draft was wrong, not the code
txsun1997/Black-Box-Tuning/models/deep_modeling_cpt.py
code served (permissive licence) · get_code("a315b8fc32a18efe")
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) 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
# Shape: (batch_size=2, sequence_length=4)
input_ids = torch.tensor([
    [101, 2054, 2003, 102],
    [101, 1045, 2572, 102]
], dtype=torch.long)

# Define pad_token_id
pad_token_id = 0

# Define decoder_start_token_id
decoder_start_token_id = 2

ARGS = {
    "input_ids": input_ids,
    "pad_token_id": pad_token_id,
    "decoder_start_token_id": decoder_start_token_id,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
shift_tokens_right Ran
ran; our contract draft was wrong, not the code
txsun1997/Black-Box-Tuning/models/deep_modeling_bart.py
code served (permissive licence) · get_code("da4e02647ad1a23f")
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 batch of input_ids with shape (batch_size=2, seq_length=4)
# Using values that represent token IDs, with some pad tokens and special tokens
input_ids = torch.tensor([
    [50256, 100, 200, -100],  # First sequence with -100 (masked) at end
    [300, 400, -100, -100]     # Second sequence with -100 (masked) tokens
], dtype=torch.long)

# Pad token ID (common in transformers, e.g., 0 for many models)
pad_token_id = 0

ARGS = {
    "input_ids": input_ids,
    "pad_token_id": pad_token_id
}
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
load_tf_weights_in_bert Not yet run
unverified (harvested, no recorded run)
txsun1997/Black-Box-Tuning/models/deep_modeling_bert.py
code served (permissive licence) · get_code("26be70dca3249c0b")
How it ran

no invocation recorded.

load_tf_weights_in_bert Not yet run
unverified (harvested, no recorded run)
txsun1997/Black-Box-Tuning/models/deep_modeling_cpt_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from CSU-NLP-Group/MARE, is pointer only (licence: NONE) · get_code("efbb0f3903b5f779")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from CSU-NLP-Group/MARE, and GitHub detected no licence in that repository 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.

load_tf_weights_in_gpt2 Not yet run
unverified (harvested, no recorded run)
txsun1997/Black-Box-Tuning/models/deep_modeling_gpt2.py
pointer only (licence: MIT); the stored copy get_code serves, from tencentarc/moto, is pointer only (licence: NOASSERTION) · get_code("00a33466c69c5705")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from tencentarc/moto, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

load_tf_weights_in_t5 Not yet run
unverified (harvested, no recorded run)
txsun1997/Black-Box-Tuning/models/deep_modeling_t5.py
code served (permissive licence) · get_code("247ce015d4375b22")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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
27 dated earlier, 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
load_tf_weights_in_gpt2 22 other papers
21 dated earlier, 1 same year, order not determinable
2106.01345 (2021-06)
Decision Transformer: Reinforcement Learning via Sequence Modeling
2110.06206 (2021-10)
StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning
2202.11705 (2022-02)
COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics
and 19 more not named here
create_position_ids_from_input_ids 8 other papers
8 dated earlier
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
load_tf_weights_in_bert 8 other papers
7 dated earlier, 1 same year, order not determinable
Dou_An_Empirical_Study_of_Training_End-to-End_Vision-and-Language_Transformers_CVPR_2022_paper (2022 (year only))
An Empirical Study of Training End-to-End Vision-and-Language Transformers
2210.10678 (2022-10)
Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study
2023.acl-long.182 (2023 (year only))
HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation
and 5 more not named here
shift_tokens_right 7 other papers
7 dated earlier
2109.04096 (2021-09)
A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
2201.05966 (2022-01)
UNIFIEDSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
2203.07836 (2022-03)
Graph Pre-training for AMR Parsing and Generation
and 4 more not named here
attention_mask_func 1 other paper
1 dated earlier
2203.01670 (2022-03)
A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation

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

Derivative-free optimization algorithms play an important role in scientific and engineering design optimization problems, especially when derivative information is not accessible. In this paper, we study the framework of sequential classification-based derivative-free optimization algorithms. By introducing learning theoretic concept hypothesis-target shattering rate, we revisit the computational complexity upper bound of SRACOS. Inspired by the revisited upper bound, we propose an algorithm named RACE-CARS, which adds a random region-shrinking step compared with SRACOS. We further establish theorems showing the acceleration by region shrinking. Experiments on the synthetic functions as well as black-box tuning for language-model-as-a-service demonstrate empirically the efficiency of RACE-CARS. An ablation experiment on the introduced hyper-parameters is also conducted, revealing the mechanism of RACE-CARS and putting forward an empirical hyper-parameter tuning guidance.

For agents

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

get_harvested_code_for_paper("aaai_33874")
get_code_for_paper("aaai_33874")
have("aaai_33874")

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

curl https://syntology.ai/api/ran/aaai_33874.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_33874.svg)](https://syntology.ai/paper/aaai_33874)

Connect an agent — have() is free.