SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.05739 · 2019

Abductive Commonsense Reasoning

arXiv · PDF · Open in the Atlas

Code that ran

14 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 9 have no contract verdict; 5 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/1908.05739.json · badge: /api/ran/1908.05739.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
allenai/abductive-commonsense-reasoning community (classifier label)
classifier basis not recorded on the link
8 ran · 1 no recorded run
seungonekim/abductive-commonsense-reasoning community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
bert_encode Ran
ran on a synthesized input
seungonekim/abductive-commonsense-reasoning/anlg/evaluation/bert_score/utils.py
code served (permissive licence) · get_code("8f0d52f285c5001f")
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 3, dtype family float, shape (2, 3, 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
import torch.nn as nn

torch.manual_seed(0)

# Build a minimal BERT-like model that satisfies the function's usage
class MinimalBertModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.embedding = nn.Embedding(100, 4)
        self.transformer = nn.TransformerEncoderLayer(
            d_model=4, nhead=2, dim_feedforward=8, batch_first=True
        )
        self.pooler = nn.Linear(4, 4)
    
    def forward(self, input_ids, token_type_ids, attention_mask=None, output_all_encoded_layers=False):
        # Embed input
        embedded = self.embedding(input_ids)
        
        # Add token type embeddings
        embedded = embedded + self.embedding(token_type_ids)
        
        # Transform attention mask for transformer (convert to additive mask)
        if attention_mask is not None:
            attention_mask_transformed = (1.0 - attention_mask.float()) * -10000.0
        else:
            attention_mask_transformed = None
        
        # Apply transformer
        encoded = self.transformer(embedded, src_key_padding_mask=None)
        
        # Pooling: take first token representation and pass through linear layer
        pooled = self.pooler(encoded[:, 0, :])
        
        return encoded, pooled

# Create model instance
model = MinimalBertModel()

# Create input tensors (batch_size=2, seq_length=3, vocab indices 0-99)
x = torch.randint(0, 100, (2, 3), dtype=torch.long)

# Create attention mask (1 for real tokens, 0 for padding)
attention_mask = torch.ones((2, 3), dtype=torch.long)

ARGS = {
    "model": model,
    "x": x,
    "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 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 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
cook_refs Ran
ran; our contract draft was wrong, not the code
seungonekim/abductive-commonsense-reasoning/anlg/evaluation/bleu/bleu_scorer.py
code served (permissive licence) · get_code("7586e1d32f7325f7")
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.

from collections import defaultdict

ARGS = {
    'refs': [
        'the quick brown fox jumps over the lazy dog',
        'a quick brown fox leaps over a lazy dog'
    ],
    'eff': 'shortest',
    'n': 4
}
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
cook_test Ran
ran on a synthesized input
seungonekim/abductive-commonsense-reasoning/anlg/evaluation/bleu/bleu_scorer.py
code served (permissive licence) · get_code("9c09fbe68477f787")
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.

from collections import defaultdict

def precook(s, n=4, out=False):
    """Takes a string as input and returns an object that can be given to
    either cook_refs or cook_test. This is optional: cook_refs and cook_test
    can take string arguments as well."""
    words = s.split()
    counts = defaultdict(int)
    for k in range(1, n + 1):
        for i in range(len(words) - k + 1):
            ngram = tuple(words[i:i + k])
            counts[ngram] += 1
    return (len(words), counts)

def cook_test(test, tup, eff=None, n=4):
    """Takes a test sentence and returns an object that
    encapsulates everything that BLEU needs to know about it."""
    reflen, refmaxcounts = tup
    testlen, counts = precook(test, n, True)
    result = {}
    if eff == 'closest':
        result['reflen'] = min(((abs(l - testlen), l) for l in reflen))[1]
    else:
        result['reflen'] = reflen
    result['testlen'] = testlen
    result['guess'] = [max(0, testlen - k + 1) for k in range(1, n + 1)]
    result['correct'] = [0] * n
    for ngram, count in counts.items():
        result['correct'][len(ngram) - 1] += min(refmaxcounts.get(ngram, 0), count)
    return result

# Build reference tuple using precook
ref_string = "the quick brown fox jumps over the lazy dog"
ref_tuple = precook(ref_string, n=4)

# Build test string
test_string = "the quick brown fox jumps"

# Build ARGS dict
ARGS = {
    'test': test_string,
    'tup': ref_tuple,
    'eff': None,
    'n': 4
}
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 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
correct_middle Ran
ran on a synthesized input
allenai/abductive-commonsense-reasoning/anli/corpus_statistics.py
code served (permissive licence) · get_code("0b75dd17295eeef5")
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 int, ndim 0, dtype family int, 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
import torch.nn as nn

torch.manual_seed(0)

# The function accesses r['hyp' + r['label']]
# So r must be a dict with:
# - a 'label' key with a string value
# - a 'hyp' + label key with some value

r = {
    'label': 'test',
    'hyptest': 42
}

ARGS = {'r': r}
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 int, ndim 0, dtype family int, 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
incorrect_middle Ran
ran on a synthesized input
allenai/abductive-commonsense-reasoning/anli/corpus_statistics.py
code served (permissive licence) · get_code("d0d6da0d2a941144")
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 str. 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)

# The function takes a dict 'r' with keys 'label', 'hyp1', and 'hyp2'
# It checks if r['label'] == '1' and returns either r['hyp2'] or r['hyp1']

ARGS = {
    'r': {
        'label': '1',
        'hyp1': 'hypothesis_one',
        'hyp2': 'hypothesis_two'
    }
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
mean_word_lens Ran
ran on a synthesized input
allenai/abductive-commonsense-reasoning/anli/corpus_statistics.py
code served (permissive licence) · get_code("a0397d9919a23e00")
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 float64, ndim 0, 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 numpy as np

ARGS = {
    "lst": [
        "hello world",
        "this is a test",
        "one",
        "four words in this string"
    ]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
num_correct Ran
ran on a synthesized input
allenai/abductive-commonsense-reasoning/anli/run_anli.py
code served (permissive licence) · get_code("aebac6962806ff28")
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 int64, ndim 0, dtype family int, 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 numpy as np

# Create small numpy arrays for testing
np.random.seed(0)

# out: predictions with shape (batch_size, num_classes)
# The function calls np.argmax(out, axis=1), so it needs a 2D array
out = np.random.randn(2, 4)  # batch_size=2, num_classes=4

# labels: ground truth labels with shape (batch_size,)
# The function compares outputs == labels, so needs 1D array of class indices
labels = np.array([1, 3])  # batch_size=2, each label is 0-3

ARGS = {
    "out": out,
    "labels": labels
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int64, ndim 0, dtype family int, 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
padding Ran
ran; our contract draft was wrong, not the code
seungonekim/abductive-commonsense-reasoning/anlg/evaluation/bert_score/utils.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yuhui-zh15/nlg_metrics, is pointer only (licence: NONE) · get_code("13ef8eeae8570519")
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 yuhui-zh15/nlg_metrics, 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.

precook Ran
ran; our contract draft was wrong, not the code
seungonekim/abductive-commonsense-reasoning/anlg/evaluation/bleu/bleu_scorer.py
code served (permissive licence) · get_code("ec4448373d72d636")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) 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.

ARGS = {
    "s": "the quick brown fox jumps over the lazy dog",
    "n": 4,
    "out": False
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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
process Ran
ran on a synthesized input
seungonekim/abductive-commonsense-reasoning/anlg/evaluation/bert_score/utils.py
code served (permissive licence) · get_code("94931df06dab4db5")
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

class StandInTokenizer:
    def tokenize(self, text):
        # Return a simple list of tokens
        return text.split()
    
    def convert_tokens_to_ids(self, tokens):
        # Convert tokens to integer ids
        # Map each token to a simple integer
        token_to_id = {token: i for i, token in enumerate(set(tokens))}
        return [token_to_id[token] for token in tokens]

# Create a tokenizer instance
tokenizer = StandInTokenizer()

# Test case 1: with tokenizer
a_with_tokenizer = "hello world"

# Test case 2: without tokenizer (a should be a list/set that works with set())
a_without_tokenizer = [1, 2, 3, 2, 1]

ARGS = {
    "a": a_with_tokenizer,
    "tokenizer": tokenizer
}
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
read_jsonl_lines Ran
ran; our contract draft was wrong, not the code
allenai/abductive-commonsense-reasoning/utils/file_utils.py
code served (permissive licence) · get_code("d0d8b8a41cf48c5e")
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 tempfile
import json
import os

# Create a temporary JSONL file with sample data
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_data.jsonl")

# Write sample JSONL data
sample_data = [
    {"id": 1, "text": "hello world"},
    {"id": 2, "text": "foo bar"},
    {"id": 3, "text": "test data"}
]

with open(temp_file, 'w') as f:
    for item in sample_data:
        f.write(json.dumps(item) + '\n')

ARGS = {
    "input_file": temp_file
}
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
read_lines Ran
ran on a synthesized input
allenai/abductive-commonsense-reasoning/utils/file_utils.py
code served (permissive licence) · get_code("7e775841119597bd")
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 tempfile
import os

# Create a temporary file with some test content
temp_dir = tempfile.mkdtemp()
test_file = os.path.join(temp_dir, "test_input.txt")

with open(test_file, 'w') as f:
    f.write("line one\n")
    f.write("line two with spaces  \n")
    f.write("line three\n")

ARGS = {
    "input_file": test_file
}
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
sample_sequence Ran
ran on a synthesized input
allenai/abductive-commonsense-reasoning/anlg/run_generation.py
code served (permissive licence) · get_code("e2f5996137ac1cb9")
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 (1, 5) 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
import torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Create a minimal model that matches how sample_sequence uses it
class MinimalLanguageModel(nn.Module):
    def __init__(self, vocab_size=10, hidden_size=8):
        super().__init__()
        self.embedding = nn.Embedding(vocab_size, hidden_size)
        self.lm_head = nn.Linear(hidden_size, vocab_size)
    
    def forward(self, input_ids, comet_input=None, comet_mask=None, 
                perm_mask=None, target_mapping=None):
        # The function expects outputs[0] to be shape (batch, seq_len, vocab_size)
        embedded = self.embedding(input_ids)
        logits = self.lm_head(embedded)
        return (logits,)

model = MinimalLanguageModel(vocab_size=10, hidden_size=8)
model.eval()

# Context: small token sequence (batch will be expanded by num_samples)
context = [1, 2, 3]

# Generation length
length = 2

# Number of samples to generate in parallel
num_samples = 1

# Temperature for softmax scaling
temperature = 1.0

# Top-k filtering parameter
top_k = 5

# Top-p (nucleus) filtering parameter
top_p = 0.9

# Whether model is XLNet (affects input format)
is_xlnet = False

# Device
device = 'cpu'

# Optional comet inputs (set to None for basic case)
comet_input = None
comet_mask = None

ARGS = {
    'model': model,
    'length': length,
    'context': context,
    'num_samples': num_samples,
    'temperature': temperature,
    'top_k': top_k,
    'top_p': top_p,
    'is_xlnet': is_xlnet,
    'device': device,
    'comet_input': comet_input,
    'comet_mask': comet_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 int, shape (1, 5) — shape (1, 5) 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
top_k_top_p_filtering Ran
ran; our contract draft was wrong, not the code
allenai/abductive-commonsense-reasoning/anlg/run_generation.py
code served (permissive licence) · get_code("ee8b235cc453809b")
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 (10,) 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
import torch.nn.functional as F

torch.manual_seed(0)

# The function expects:
# - logits: a 1D tensor of logits (vocabulary distribution)
# - top_k: int, number of top tokens to keep
# - top_p: float, cumulative probability threshold
# - filter_value: float, value to replace filtered logits with

# Create a small vocabulary logits tensor (1D)
logits = torch.randn(10)

ARGS = {
    "logits": logits,
    "top_k": 5,
    "top_p": 0.9,
    "filter_value": -float('Inf')
}
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 (10,) — shape (10,) 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
select_field Not yet run
unverified (harvested, no recorded run)
allenai/abductive-commonsense-reasoning/anli/data_processors.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yuweihao/reclor, is pointer only (licence: NONE) · get_code("0a546b305d274996")
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 yuweihao/reclor, 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, 6 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 6 later) and 9 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
precook 22 other papers
7 dated earlier, 15 later
1411.4555 (2014-11)
Show and Tell: A Neural Image Caption Generator
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1611.09268 (2016-11)
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
and 19 more not named here
cook_refs 21 other papers
6 dated earlier, 15 later
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1611.09268 (2016-11)
MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
1611.09571 (2016-11)
Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model
and 18 more not named here
select_field 9 other papers
9 later
2002.04326 (2020-02)
ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning
2004.04494 (2020-04)
MuTual: A Dataset for Multi-Turn Dialogue Reasoning
2009.06504 (2020-09)
Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue
and 6 more not named here
padding 6 other papers
1 dated earlier, 5 later · 1 only as an assembly brick
1904.09675 (2019-04)
BERTScore: Evaluating Text Generation with BERT
1909.02622 (2019-09)
MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance
2005.01196 (2020-05)
On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation
and 3 more not named here
top_k_top_p_filtering 4 other papers
4 later
1910.10683 (2019-10)
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
2005.00558 (2020-05)
POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training
2012.15416 (2020-12)
Directed Beam Search: Plug-and-Play Lexically Constrained Language Generation
and 1 more not named here
read_jsonl_lines 2 other papers
2 later
2010.05953 (2020-10)
COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs
2403.07398 (2024-03)
Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Abductive reasoning is inference to the most plausible explanation. For example, if Jenny finds her house in a mess when she returns from work, and remembers that she left a window open, she can hypothesize that a thief broke into her house and caused the mess, as the most plausible explanation. While abduction has long been considered to be at the core of how people interpret and read between the lines in natural language (Hobbs et al., 1988), there has been relatively little research in support of abductive natural language inference and generation. We present the first study that investigates the viability of language-based abductive reasoning. We introduce a challenge dataset, ART, that consists of over 20k commonsense narrative contexts and 200k explanations. Based on this dataset, we conceptualize two new tasks -- (i) Abductive NLI: a multiple-choice question answering task for choosing the more likely explanation, and (ii) Abductive NLG: a conditional generation task for explaining given observations in natural language. On Abductive NLI, the best model achieves 68.9% accuracy, well below human performance of 91.4%. On Abductive NLG, the current best language generators struggle even more, as they lack reasoning capabilities that are trivial for humans. Our analysis leads to new insights into the types of reasoning that deep pre-trained language models fail to perform--despite their strong performance on the related but more narrowly defined task of entailment NLI--pointing to interesting avenues for future research.

For agents

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

get_harvested_code_for_paper("1908.05739")
get_code_for_paper("1908.05739")
have("1908.05739")

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

curl https://syntology.ai/api/ran/1908.05739.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.05739.svg)](https://syntology.ai/paper/1908.05739)

Connect an agent — have() is free.