SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2311.01161 · EMNLP · 2023

Weakly Supervised Semantic Parsing with Execution-based Spurious Program Filtering

Kyomin Jung, Kang-Il Lee, Segwang Kim

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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; 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/2311.01161.json · badge: /api/ran/2311.01161.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
klee972/exec-filter canonical (classifier label)
classifier basis: census
5 ran · 4 no recorded run
FunctionStatusWhere it lives
construct_row_selections Ran
ran; our contract draft was wrong, not the code
klee972/exec-filter/wikitable/weaksp_em19/wikitable/model/util.py
code served (permissive licence) · get_code("032f3a4aa80a6255")
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.

# Setup code for construct_row_selections

ARGS = {
    'sel_type': 'number',
    'operator': '>',
    'column_action': 'select_column_1',
    'ent_action': 'apply_entity_filter'
}
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
construct_same Ran
ran; our contract draft was wrong, not the code
klee972/exec-filter/wikitable/weaksp_em19/wikitable/model/util.py
code served (permissive licence) · get_code("3dc9a2264692f53a")
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

torch.manual_seed(0)

# The function construct_same takes three string parameters
# and returns a list containing those parameters along with some string templates.
# No complex objects are needed - just strings.

str_col_ac = "StringColumn_accessor"
ent_ac = "entity_accessor"
col_ac = "Column_accessor"

ARGS = {
    "str_col_ac": str_col_ac,
    "ent_ac": ent_ac,
    "col_ac": col_ac
}
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 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
log_sum_exp Ran
ran; our contract draft was wrong, not the code
klee972/exec-filter/wikitable/weaksp_em19/wikitable/model/baseline.py
code served (permissive licence) · get_code("3d7631fc6903e509")
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 (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.functional as F

torch.manual_seed(0)

# The function takes score_list which can be either:
# 1. A list of tensors
# 2. A tensor directly
# 
# The function stacks them if list, then applies log_softmax and computes mean
# We need tensors with compatible dimensions for stacking and log_softmax

# Create a list of small tensors with shape (4,) - batch size 2 along dim 0
score_tensor_1 = torch.randn(4)
score_tensor_2 = torch.randn(4)
score_list = [score_tensor_1, score_tensor_2]

ARGS = {
    "score_list": score_list
}
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 (4,) — shape (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
log_sum_exp Ran
ran; our contract draft was wrong, not the code
klee972/exec-filter/wikitable/weaksp_em19/wikitable/module/lattice.py
code served (permissive licence) · get_code("c9cc0b6ea0723393")
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
import torch.nn.functional as F

torch.manual_seed(0)

# Create a list of tensors to pass as score_list
# The function expects a list that will be stacked along dimension 0
# Each tensor should have shape (batch_size, feature_dim)
score_list = [
    torch.randn(2, 4),  # First score tensor
    torch.randn(2, 4),  # Second score tensor
    torch.randn(2, 4),  # Third score tensor
]

ARGS = {
    "score_list": score_list,
}
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
log_sum_exp_2d Ran
ran; our contract draft was wrong, not the code
klee972/exec-filter/wikitable/weaksp_em19/wikitable/module/lattice.py
code served (permissive licence) · get_code("73406fc88cc3f5e6")
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 (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.functional as F

torch.manual_seed(0)

# The function log_sum_exp_2d takes a 2D tensor and:
# 1. Computes log_softmax along dim=0
# 2. Subtracts it from the input
# 3. Takes mean along dim=0
# So score_v should be a 2D tensor

# Create a small 2D tensor (batch_size=2, features=4)
score_v = torch.randn(2, 4)

ARGS = {
    "score_v": score_v
}
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 (4,) — shape (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
construct_junction Not yet run
unverified (harvested, no recorded run)
klee972/exec-filter/wikitable/weaksp_em19/wikitable/model/util.py
code served (permissive licence) · get_code("22099db512a112a0")
How it ran

no invocation recorded.

invF Not yet run
unverified (harvested, no recorded run)
klee972/exec-filter/nlvr/allennlp-semparse-nlvr-v2/DeepComparison/ASD.py
code served (permissive licence) · get_code("e4e2cb65e11d2117")
How it ran

no invocation recorded.

invG Not yet run
unverified (harvested, no recorded run)
klee972/exec-filter/nlvr/allennlp-semparse-nlvr-v2/DeepComparison/ASD.py
code served (permissive licence) · get_code("ce002f2c60f1814c")
How it ran

no invocation recorded.

invGnew Not yet run
unverified (harvested, no recorded run)
klee972/exec-filter/nlvr/allennlp-semparse-nlvr-v2/DeepComparison/ASD.py
code served (permissive licence) · get_code("f0f0ed61f42e5651")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 8 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 8 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

The problem of spurious programs is a longstanding challenge when training a semantic parser from weak supervision. To eliminate such programs that have wrong semantics but correct denotation, existing methods focus on exploiting similarities between examples based on domain-specific knowledge. In this paper, we propose a domain-agnostic filtering mechanism based on program execution results. Specifically, for each program obtained through the search process, we first construct a representation that captures the program's semantics as execution results under various inputs. Then, we run a majority vote on these representations to identify and filter out programs with significantly different semantics from the other programs. In particular, our method is orthogonal to the program search process so that it can easily augment any of the existing weakly supervised semantic parsing frameworks. Empirical evaluations on the Natural Language Visual Reasoning and WIKITABLEQUESTIONS demonstrate that applying our method to the existing semantic parsers induces significantly improved performances. Code is available at https://github.com/klee972/exec-filter.

For agents

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

get_harvested_code_for_paper("2311.01161")
get_code_for_paper("2311.01161")
have("2311.01161")

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

curl https://syntology.ai/api/ran/2311.01161.json

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

[![Syntology run record](https://syntology.ai/api/ran/2311.01161.svg)](https://syntology.ai/paper/2311.01161)

Connect an agent — have() is free.