SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.20046 · 2023

Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection

arXiv · PDF · Open in the Atlas

Code that ran

12 of 15 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; 12 failures 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/2310.20046.json · badge: /api/ran/2310.20046.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-science/adaptive-in-context-learning canonical (classifier label)
classifier basis: census
12 ran · 3 no recorded run
FunctionStatusWhere it lives
cluster Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
amazon-science/adaptive-in-context-learning/algorithms.py
code served (permissive licence) · get_code("a7424bb088354401")
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 tuple. 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 numpy as np
from sklearn.cluster import KMeans

np.random.seed(0)

# Create small embeddings: 5 samples, 4-dimensional embeddings
embeddings = np.random.randn(5, 4).astype(np.float32)

# Create examples with 'content' field (required by thres logic)
examples = [
    {'content': 'hello world this is a test'},
    {'content': 'another example sentence here'},
    {'content': 'third test document text'},
    {'content': 'fourth sample with words'},
    {'content': 'fifth and final example'}
]

# Create a flag_idx that includes some valid indices
flag_idx = [0, 1, 2, 3, 4]

# Pre-trained clustering model (optional, can be None)
clustering_model_pretrained = KMeans(n_clusters=2, random_state=0)
clustering_model_pretrained.fit(embeddings)

ARGS = {
    'embeddings': embeddings,
    'select_num': 2,
    'examples': examples,
    'flag_idx': flag_idx,
    'thres': False,
    'reverse': False,
    'clustering_model': None,
    'seed': 0
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
density_max_coverage Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
amazon-science/adaptive-in-context-learning/algorithms.py
code served (permissive licence) · get_code("81689dc2c5f8dac8")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np

# Create small embeddings matrix (10 samples, 4 dimensions)
np.random.seed(0)
embeddings = np.random.randn(10, 4).astype(np.float32)

# Create index lists
hard_idx = [0, 1, 2, 3, 4]
easy_idx = [5, 6, 7]
selected_indices = [8, 9]

ARGS = {
    'embeddings': embeddings,
    'hard_idx': hard_idx,
    'easy_idx': easy_idx,
    'selected_indices': selected_indices,
    'select_num': 3,
    'k': 2,
    'vote_file': None,
    'weighted': False,
    'two_hop': True,
    'thres_graph': False,
    'mc_selection': 'hard'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
expand_to_aliases Ran
ran; our contract draft was wrong, not the code
amazon-science/adaptive-in-context-learning/utils.py
code served (permissive licence) · get_code("d51ed70aaef3b5d0")
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 set. 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 numpy as np

# Setup code to construct valid arguments for expand_to_aliases function

ARGS = {
    "given_answers": [
        "The_quick_brown_fox",
        "jumps-over, the 'fence'",
        "hello world",
        "test_answer-with.punctuation"
    ],
    "make_sub_answers": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set 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
fast_votek_mod Ran
ran; our contract draft was wrong, not the code
amazon-science/adaptive-in-context-learning/algorithms.py
code served (permissive licence) · get_code("d72b27f74858347a")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np
from collections import defaultdict

# Set random seed for reproducibility
np.random.seed(0)

# Create small embeddings (2 samples, 4 dimensions)
embeddings = np.random.randn(5, 4).astype(np.float32)

# Already selected indices (to be excluded from new selections)
selected_indices = [0]

# Budget for new selections
select_num = 2

# Graph hyperparameter k
k = 3

# Vote file for saving results (None to skip file I/O)
vote_file = None

ARGS = {
    "embeddings": embeddings,
    "selected_indices": selected_indices,
    "select_num": select_num,
    "k": k,
    "vote_file": vote_file,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
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
format_dataset Ran
ran; our contract draft was wrong, not the code
amazon-science/adaptive-in-context-learning/get_task.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cmavro/packllm, is pointer only (licence: NONE) · get_code("82fab1f6e6bddec2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from cmavro/packllm, 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. A run is recorded.

get_checkpoint_id Ran
ran; our contract draft was wrong, not the code
amazon-science/adaptive-in-context-learning/MetaICL/utils/utils.py
code served (permissive licence) · get_code("1e0c778236fc89b1")
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 tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os

def get_checkpoint_id(key):
    all_settings = ['hr_to_lr', 'hr_to_lr_noinst', 'hr_to_lr_inst', 'hr_to_lr_inst_all', 'class_to_class', 'non_class_to_class', 'qa_to_qa', 'non_qa_to_qa', 'non_nli_to_nli', 'non_paraphrase_to_paraphrase']
    all_methods = ['metaicl', 'channel-metaicl', 'multitask-zero', 'channel-multitask-zero']
    checkpoint_dir = 'https://dl.fbaipublicfiles.com/MetaICL'
    
    if key in all_methods:
        setting = 'hr_to_lr'
        method = key
    elif key in [method + '-inst' for method in all_methods] or key in [method + '-instruction' for method in all_methods]:
        setting = 'hr_to_lr_inst_all'
        method = '-'.join(key.split('-')[:-1])
    elif key in ['%s/%s' % (method, setting) for method in all_methods for setting in all_settings]:
        method, setting = key.split('/')
    else:
        return None
    return (method, setting, os.path.join(checkpoint_dir, method, setting, 'model.pt'))

ARGS = {
    'key': 'metaicl'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
get_sub_answers Ran
ran; our contract draft was wrong, not the code
amazon-science/adaptive-in-context-learning/utils.py
code served (permissive licence) · get_code("91631e556572af73")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np

# Analyze the function:
# - answers: a list that is iterated over
# - each element x in answers is a string (called with .split(' '))
# - begin: int, default 0
# - end: int or None, default None
# The function filters answers where len(x.split(' ')) > 1 (multi-word strings)
# and returns sliced joined strings

ARGS = {
    "answers": [
        "hello world",
        "foo bar baz",
        "single",
        "one two three four",
        "alpha beta"
    ],
    "begin": 0,
    "end": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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_data Ran
ran; our contract draft was wrong, not the code
amazon-science/adaptive-in-context-learning/MetaICL/utils/data.py
code served (permissive licence) · get_code("6b6f0821fb467ba9")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 os
import json
import tempfile
import shutil

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()
config_dir = os.path.join(temp_dir, 'config')
data_dir = os.path.join(temp_dir, 'data')
os.makedirs(config_dir)
os.makedirs(data_dir)

# Create a mock config file
task = 'test_task'
config_file = os.path.join(config_dir, task + '.json')
config_data = {
    'train': ['dataset1', 'dataset2'],
    'test': ['dataset1']
}
with open(config_file, 'w') as f:
    json.dump(config_data, f)

# Create mock data files
for dataset in ['dataset1', 'dataset2']:
    dataset_dir = os.path.join(data_dir, dataset)
    os.makedirs(dataset_dir)
    
    # Create data files for different k, seed, split combinations
    for k in [5, 10]:
        for seed in [0, 42]:
            for split in ['train', 'test']:
                data_file = os.path.join(
                    dataset_dir, 
                    f'{dataset}_{k}_{seed}_{split}.jsonl'
                )
                with open(data_file, 'w') as f:
                    for i in range(2):
                        dp = {
                            'input': f'input_{i}',
                            'output': f'output_{i}',
                            'id': i
                        }
                        f.write(json.dumps(dp) + '\n')

# Change to temp directory for the function to work
original_dir = os.getcwd()
os.chdir(temp_dir)

try:
    ARGS = {
        'task': 'test_task',
        'split': 'train',
        'k': 5,
        'seed': 0,
        'config_split': None,
        'datasets': None,
        'is_null': False
    }
finally:
    pass
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
prepro_sentence_pair Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
amazon-science/adaptive-in-context-learning/MetaICL/metaicl/data.py
code served (permissive licence) · get_code("ab97d7d0b637c027")
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

torch.manual_seed(0)

# Create small sample inputs for train and test
# These are lists of token IDs (integers)
train_inputs = [
    [101, 2054, 2003],  # First training sentence
    [101, 1045, 2572],  # Second training sentence
]

test_inputs = [
    [2054, 2003, 102],  # First test sentence
    [1045, 2572, 102],  # Second test sentence
]

max_length = 16
bos_token_id = 101
eos_token_id = 102
allow_truncation = False

ARGS = {
    'train_inputs': train_inputs,
    'test_inputs': test_inputs,
    'max_length': max_length,
    'bos_token_id': bos_token_id,
    'eos_token_id': eos_token_id,
    'allow_truncation': allow_truncation,
}
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
prepro_sentence_pair_single Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
amazon-science/adaptive-in-context-learning/MetaICL/metaicl/data.py
code served (permissive licence) · get_code("daece0094ff99380")
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 tuple, ndim 2, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 numpy as np

# Analyze the function to understand what parameters are needed
# ids1: list of token ids
# ids2: list of token ids
# max_length: int, maximum sequence length
# bos_token_id: int, beginning of sequence token id (not used in function body)
# eos_token_id: int, end of sequence token id (not used in function body)
# allow_truncation: bool, whether to allow truncation

# Create small valid token id lists
ids1 = [101, 2054, 2003]  # 3 tokens
ids2 = [1045, 2572, 102]  # 3 tokens

# max_length should be >= len(ids1) + len(ids2) = 6 (or less if allow_truncation=True)
max_length = 10

# Token ids (values don't matter, just need to be integers)
bos_token_id = 101
eos_token_id = 102

# Set allow_truncation to False to keep it simple
allow_truncation = False

ARGS = {
    "ids1": ids1,
    "ids2": ids2,
    "max_length": max_length,
    "bos_token_id": bos_token_id,
    "eos_token_id": eos_token_id,
    "allow_truncation": allow_truncation,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family int — a tuple output has no array shape of its own; none is stated
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
process_mnli_examples Ran
ran; our contract draft was wrong, not the code
amazon-science/adaptive-in-context-learning/get_task.py
code served (permissive licence) · get_code("071f4dd2f4d4b22c")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
from tqdm import tqdm

def process_mnli_examples(examples):
    processed_examples = []
    idx = 0
    for raw_data in tqdm(examples, desc='process mnli examples'):
        processed_examples.append({'id': idx, 'label': raw_data['label'], 'premise': raw_data['premise'], 'hypothesis': raw_data['hypothesis']})
        idx += 1
    return processed_examples

# Create example MNLI data
examples = [
    {
        'label': 0,
        'premise': 'A man is walking in the park.',
        'hypothesis': 'Someone is outside.'
    },
    {
        'label': 1,
        'premise': 'The cat is sleeping on the couch.',
        'hypothesis': 'The dog is barking loudly.'
    }
]

ARGS = {
    'examples': examples
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
process_rte_examples Ran
ran; our contract draft was wrong, not the code
amazon-science/adaptive-in-context-learning/get_task.py
code served (permissive licence) · get_code("b775e4262bf408f6")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
from tqdm import tqdm

# Construct example data matching what process_rte_examples expects
examples = [
    {
        'id': 0,
        'label': 0,
        'sentence1': 'The cat sat on the mat.',
        'sentence2': 'A feline rested on a rug.'
    },
    {
        'id': 1,
        'label': 1,
        'sentence1': 'It is raining outside.',
        'sentence2': 'The weather is clear and sunny.'
    }
]

ARGS = {
    'examples': examples
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
get_instance_length Not yet run
unverified (harvested, no recorded run)
amazon-science/adaptive-in-context-learning/prompt_retrieval.py
code served (permissive licence) · get_code("ddf793183ffe3659")
How it ran

no invocation recorded.

postprocess_text Not yet run
unverified (harvested, no recorded run)
amazon-science/adaptive-in-context-learning/main_adaptive_phases.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from inhwanbae/LMTrajectory, is pointer only (licence: NOASSERTION) · get_code("eff19094fe0ec70e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from inhwanbae/LMTrajectory, 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.

setup_fp16 Not yet run
unverified (harvested, no recorded run)
amazon-science/adaptive-in-context-learning/MetaICL/metaicl/model.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from cmavro/packllm, is pointer only (licence: NONE) · get_code("cbf1d84d85c303cc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from cmavro/packllm, 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.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 9 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 1 the same month, 5 later) and 6 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
format_dataset 2 other papers
1 dated earlier, 1 later
2212.09741 (2022-12)
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
2404.11531 (2024-04)
Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization
get_instance_length 2 other papers
1 the same month, 1 later
2310.10873 (2023-10)
IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
2404.11531 (2024-04)
Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization
postprocess_text 2 other papers
1 dated earlier, 1 later
2212.09741 (2022-12)
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
2403.18447 (2024-03)
Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction
expand_to_aliases 1 other paper
1 dated earlier
2212.09741 (2022-12)
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
get_sub_answers 1 other paper
1 dated earlier
2212.09741 (2022-12)
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
prepro_sentence_pair 1 other paper
1 later
2404.11531 (2024-04)
Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization
process_mnli_examples 1 other paper
1 dated earlier
2212.09741 (2022-12)
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
process_rte_examples 1 other paper
1 dated earlier
2212.09741 (2022-12)
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
setup_fp16 1 other paper
1 later
2404.11531 (2024-04)
Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization

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

Large Language Models (LLMs) can adapt to new tasks via in-context learning (ICL). ICL is efficient as it does not require any parameter updates to the trained LLM, but only few annotated examples as input for the LLM. In this work, we investigate an active learning approach for ICL, where there is a limited budget for annotating examples. We propose a model-adaptive optimization-free algorithm, termed AdaICL, which identifies examples that the model is uncertain about, and performs semantic diversity-based example selection. Diversity-based sampling improves overall effectiveness, while uncertainty sampling improves budget efficiency and helps the LLM learn new information. Moreover, AdaICL poses its sampling strategy as a Maximum Coverage problem, that dynamically adapts based on the model's feedback and can be approximately solved via greedy algorithms. Extensive experiments on nine datasets and seven LLMs show that AdaICL improves performance by 4.4% accuracy points over SOTA (7.7% relative improvement), is up to 3x more budget-efficient than performing annotations uniformly at random, while it outperforms SOTA with 2x fewer ICL examples.

For agents

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

get_harvested_code_for_paper("2310.20046")
get_code_for_paper("2310.20046")
have("2310.20046")

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

curl https://syntology.ai/api/ran/2310.20046.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.20046.svg)](https://syntology.ai/paper/2310.20046)

Connect an agent — have() is free.