SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1704.05974 · 2017

Cross-domain Semantic Parsing via Paraphrasing

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 2 failures of our instrument; 0 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/1704.05974.json · badge: /api/ran/1704.05974.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
ysu1989/CrossSemparse canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
average Ran
ran, honoured the contract we drafted
ysu1989/CrossSemparse/scripts/extract_test_result.py
code served (permissive licence) · get_code("1873cbd2c8faa9ff")
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 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

torch.manual_seed(0)

# The function takes 'lists' parameter which should be a list of lists
# It iterates through indices and tries to access elements from each inner list
# It handles cases where lists have different lengths (using try/except)
# It computes averages across the lists at each index position

# Create lists of different lengths to test the averaging functionality
list1 = [1.0, 2.0, 3.0, 4.0]
list2 = [5.0, 6.0, 7.0]
list3 = [10.0, 11.0, 12.0, 13.0, 14.0]

ARGS = {
    "lists": [list1, list2, list3]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
extract_downsample_exp_domain Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ysu1989/CrossSemparse/scripts/extract_test_result.py
code served (permissive licence) · get_code("39593793ca7a361f")
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 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 temporary directory and test log files
temp_dir = tempfile.mkdtemp()

# Create the directory structure and test log files
setting = "test_setting"
dataset = "test_dataset"
domain = "test_domain"
exec_nums = [1, 2]
downsample_ratios = [0.01, 0.05, 0.1, 0.3, 0.5, 0.7, 0.9]

for exec_num in exec_nums:
    for ratio in downsample_ratios:
        model_dir = os.path.join(temp_dir, 'execs', setting, dataset, domain, f'sample_{ratio}', f'exec{exec_num}')
        os.makedirs(model_dir, exist_ok=True)
        
        # Create test.log file with mock data
        log_file = os.path.join(model_dir, 'test.log')
        with open(log_file, 'w') as f:
            # Write a line with mean acc at position 13 (0-indexed)
            f.write("epoch 1 loss 0.5 acc 0.8 val_loss 0.6 val_acc 0.75 test_loss 0.7 test_acc 0.72 mean acc 0.85;\n")

# Also create with retrain subdirectory
for exec_num in exec_nums:
    for ratio in downsample_ratios:
        model_dir = os.path.join(temp_dir, 'execs', setting, dataset, domain, f'sample_{ratio}', f'exec{exec_num}', 'retrain')
        os.makedirs(model_dir, exist_ok=True)
        
        log_file = os.path.join(model_dir, 'test.log')
        with open(log_file, 'w') as f:
            f.write("epoch 1 loss 0.5 acc 0.8 val_loss 0.6 val_acc 0.75 test_loss 0.7 test_acc 0.72 mean acc 0.87;\n")

# Change to temp directory so relative paths work
original_dir = os.getcwd()
os.chdir(temp_dir)

ARGS = {
    "setting": "test_setting",
    "dataset": "test_dataset",
    "domain": "test_domain",
    "exec_nums": [1, 2],
    "retrain": False,
    "init_type": None
}
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 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_last_line_of_file Ran
ran; our contract draft was wrong, not the code
ysu1989/CrossSemparse/scripts/extract_test_result.py
code served (permissive licence) · get_code("9d5baf329e7d120b")
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 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 tempfile
import os

# Create a temporary file with some content
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("first line\n")
temp_file.write("second line\n")
temp_file.write("last line\n")
temp_file.close()

ARGS = {
    'filename': temp_file.name
}
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 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

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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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

Existing studies on semantic parsing mainly focus on the in-domain setting. We formulate cross-domain semantic parsing as a domain adaptation problem: train a semantic parser on some source domains and then adapt it to the target domain. Due to the diversity of logical forms in different domains, this problem presents unique and intriguing challenges. By converting logical forms into canonical utterances in natural language, we reduce semantic parsing to paraphrasing, and develop an attentive sequence-to-sequence paraphrase model that is general and flexible to adapt to different domains. We discover two problems, small micro variance and large macro variance, of pre-trained word embeddings that hinder their direct use in neural networks, and propose standardization techniques as a remedy. On the popular Overnight dataset, which contains eight domains, we show that both cross-domain training and standardized pre-trained word embeddings can bring significant improvement.

For agents

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

get_harvested_code_for_paper("1704.05974")
get_code_for_paper("1704.05974")
have("1704.05974")

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

curl https://syntology.ai/api/ran/1704.05974.json

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

[![Syntology run record](https://syntology.ai/api/ran/1704.05974.svg)](https://syntology.ai/paper/1704.05974)

Connect an agent — have() is free.