SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.08115 · EMNLP · 2020

Learning from Task Descriptions

Matthew Peters, Orion Weller, Nicholas Lourie, Matt Gardner

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure 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/2011.08115.json · badge: /api/ran/2011.08115.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/zest canonical (classifier label)
classifier basis: classifier_2025
2 ran · 1 no recorded run
FunctionStatusWhere it lives
answer_json_to_strings Ran
ran; our contract draft was wrong, not the code
allenai/zest/bin/evaluate-zest.py
code served (permissive licence) · get_code("04cd7ac53a43201b")
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 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 json
from typing import Any, Dict, List, Set, Tuple, Union, Optional

# Test case 1: answer with a number
answer_number = {
    'number': 42
}

# Test case 2: answer with single span
answer_single_span = {
    'spans': ['Paris']
}

# Test case 3: answer with multiple spans
answer_multiple_spans = {
    'spans': ['New York', 'Los Angeles', 'Chicago']
}

# Test case 4: answer with date
answer_date = {
    'date': {
        'day': 15,
        'month': 'March',
        'year': 2021
    }
}

# Use the number case as the primary test
ARGS = {
    'answer': answer_number
}
Setup block drafted by
a language model, Claude Haiku 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 — 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
get_metrics Ran
ran, honoured the contract we drafted
allenai/zest/bin/evaluate-zest.py
code served (permissive licence) · get_code("71bbf63b6ce20f21")
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 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 re
import string
from typing import Any, Dict, List, Set, Tuple, Union, Optional
import numpy as np
from scipy.optimize import linear_sum_assignment

# Setup code for get_metrics function

# Example 1: Simple string predictions and gold answers
predicted_1 = "The quick brown fox"
gold_1 = "The quick brown fox"

# Example 2: List of strings for predicted and gold
predicted_2 = ["Paris", "France"]
gold_2 = ["Paris", "France"]

# Example 3: Different answers to test F1 computation
predicted_3 = "The answer is forty two"
gold_3 = "The answer is 42"

# Example 4: Tuple of strings
predicted_4 = ("hello world", "goodbye world")
gold_4 = ("hello world", "goodbye world")

# Example 5: Single string with numbers
predicted_5 = "5 apples"
gold_5 = "5.0 apples"

# Choose one representative case for ARGS
ARGS = {
    "predicted": "The quick brown fox jumps",
    "gold": "The quick brown fox jumps"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, scipy — 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
evaluate_json Not yet run
unverified (harvested, no recorded run)
allenai/zest/bin/evaluate-zest.py
code served (permissive licence) · get_code("17260a6169c3862f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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
answer_json_to_strings 1 other paper
1 later
2024.findings-emnlp.812 (2024 (year only))
Skills-in-Context: Unlocking Compositionality in Large Language Models

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

Typically, machine learning systems solve new tasks by training on thousands of examples. In contrast, humans can solve new tasks by reading some instructions, with perhaps an example or two. To take a step toward closing this gap, we introduce a framework for developing NLP systems that solve new tasks after reading their descriptions, synthesizing prior work in this area. We instantiate this framework with a new English language dataset, ZEST, structured for task-oriented evaluation on unseen tasks. Formulating task descriptions as questions, we ensure each is general enough to apply to many possible inputs, thus comprehensively evaluating a model's ability to solve each task. Moreover, the dataset's structure tests specific types of systematic generalization. We find that the state-of-the-art T5 model achieves a score of 12% on ZEST, leaving a significant challenge for NLP researchers. 1

For agents

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

get_harvested_code_for_paper("2011.08115")
get_code_for_paper("2011.08115")
have("2011.08115")

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

curl https://syntology.ai/api/ran/2011.08115.json

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

[![Syntology run record](https://syntology.ai/api/ran/2011.08115.svg)](https://syntology.ai/paper/2011.08115)

Connect an agent — have() is free.