SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.00689 · EMNLP · 2020

An Imitation Game for Learning Semantic Parsers from User Interaction

Ziyu Yao, Huan Sun, Yu Su, Yiqi Tang, Wen-tau Yih

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure 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/2005.00689.json · badge: /api/ran/2005.00689.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
sunlab-osu/MISP marked official in Papers with Code
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
Agent Ran
ran on a synthesized input · constructed an object; no result was computed
sunlab-osu/MISP/MISP_SQL/agent.py
code served (permissive licence) · get_code("157e31aa80c0b736")
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 an instance of its own class, Agent: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

# Define stand-in classes for the required model components

class StandInWorldModel(nn.Module):
    """Minimal world model with required interface."""
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x):
        return self.linear(x)

class StandInErrorDetector(nn.Module):
    """Minimal error detector with required interface."""
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 2)
    
    def forward(self, x):
        return self.linear(x)

class StandInQuestionGenerator(nn.Module):
    """Minimal question generator with required interface."""
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 8)
    
    def forward(self, x):
        return self.linear(x)

class StandInUser:
    """Minimal user simulator with required interface."""
    def __init__(self):
        self.option_selections = []
    
    def get_answer(self, pointer, answer_sheet):
        return "yes"
    
    def record_user_feedback(self, tag, feedback, bool_qa=True):
        pass
    
    def get_selection(self, pointer, opt_answer_sheet, sel_none_of_above):
        return [1, 2]
    
    def get_gold_selection(self, pointer):
        return ([], [], 0, [])

# Instantiate the components
world_model = StandInWorldModel()
error_detector = StandInErrorDetector()
question_generator = StandInQuestionGenerator()

ARGS = {
    'world_model': world_model,
    'error_detector': error_detector,
    'question_generator': question_generator,
    'bool_mistake_exit': False,
    'bool_structure_question': False
}
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 Agent — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Agent 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
semantic_unit_segment Ran
ran; our contract draft was wrong, not the code
sunlab-osu/MISP/MISP_SQL/agent.py
code served (permissive licence) · get_code("b6d8294d8f20044a")
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 torch
import numpy as np

torch.manual_seed(0)

# The function semantic_unit_segment takes a tag_seq parameter
# It iterates through tag_seq, accessing tag_item[0] for each element
# It appends tag_item (the full item) to tag_item_lists
# It appends idx (an integer) to seg_pointers
# So tag_seq should be a sequence of items where each item is indexable (like tuples or lists)
# and the first element can be compared to OUTSIDE ('O')

# Create a small tag sequence with mixed 'O' and non-'O' tags
tag_seq = [
    ('O',),           # idx=0, will be skipped
    ('B-PER',),       # idx=1, will be included
    ('I-PER',),       # idx=2, will be included
    ('O',),           # idx=3, will be skipped
    ('B-LOC',),       # idx=4, will be included
]

ARGS = {
    'tag_seq': tag_seq
}
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 — 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 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.

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

Despite the widely successful applications, building a semantic parser is still a tedious process in practice with challenges from costly data annotation and privacy risks. We suggest an alternative, human-in-the-loop methodology for learning semantic parsers directly from users. A semantic parser should be introspective of its uncertainties and prompt for user demonstrations when uncertain. In doing so it also gets to imitate the user behavior and continue improving itself autonomously with the hope that eventually it may become as good as the user in interpreting their questions. To combat the sparsity of demonstrations, we propose a novel annotation-efficient imitation learning algorithm, which iteratively collects new datasets by mixing demonstrated states and confident predictions and retrains the semantic parser in a Dataset Aggregation fashion (Ross et al., 2011). We provide a theoretical analysis of its cost bound and also empirically demonstrate its promising performance on the text-to-SQL problem. 1

For agents

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

get_harvested_code_for_paper("2005.00689")
get_code_for_paper("2005.00689")
have("2005.00689")

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

curl https://syntology.ai/api/ran/2005.00689.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.00689.svg)](https://syntology.ai/paper/2005.00689)

Connect an agent — have() is free.