SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.10909 · 2019

Interactive Language Learning by Question Answering

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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 8 have no contract verdict; 2 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/1908.10909.json · badge: /api/ran/1908.10909.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
xingdi-eric-yuan/qait_public canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
attribute_to_question Ran
ran on a synthesized input
xingdi-eric-yuan/qait_public/game_generator.py
pointer only (licence: MIT) · get_code("918dc7f48ab39b03")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, xingdi-eric-yuan/qait_public, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

build_argparser Ran
ran on a synthesized input
xingdi-eric-yuan/qait_public/challenge.py
pointer only (licence: MIT) · get_code("d041e96025cea355")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, xingdi-eric-yuan/qait_public, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

compute_mask Ran
ran; our contract draft was wrong, not the code
xingdi-eric-yuan/qait_public/layers.py
pointer only (licence: MIT) · get_code("91eb0af694a5d554")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, xingdi-eric-yuan/qait_public, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

generate_location_question Ran
ran on a synthesized input
xingdi-eric-yuan/qait_public/game_generator.py
pointer only (licence: MIT) · get_code("c8c3bab24970ba1f")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, xingdi-eric-yuan/qait_public, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

get_attribute_reward Ran
ran on a synthesized input
xingdi-eric-yuan/qait_public/reward_helper.py
pointer only (licence: MIT) · get_code("31a1a36dc620fe67")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, xingdi-eric-yuan/qait_public, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

masked_mean Ran
ran on a synthesized input
xingdi-eric-yuan/qait_public/layers.py
pointer only (licence: MIT) · get_code("4feae955776e4043")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, xingdi-eric-yuan/qait_public, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

masked_softmax Ran
ran; our contract draft was wrong, not the code
xingdi-eric-yuan/qait_public/layers.py
code served (permissive licence) · get_code("e5002de1b930b693")
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

torch.manual_seed(0)

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

# Create an optional mask tensor with same shape
m = torch.ones(2, 4)

# Define ARGS dict with all parameters
ARGS = {
    "x": x,
    "m": m,
    "axis": -1
}
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
preproc Ran
ran on a synthesized input
xingdi-eric-yuan/qait_public/generic.py
pointer only (licence: MIT) · get_code("779f827b9e2410ad")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, xingdi-eric-yuan/qait_public, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

to_np Ran
ran on a synthesized input
xingdi-eric-yuan/qait_public/generic.py
pointer only (licence: MIT); the stored copy get_code serves, from xingdi-eric-yuan/imrc_graph_public, is pointer only (licence: MIT) · get_code("499aa017b9e14605")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, xingdi-eric-yuan/qait_public, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

to_pt Ran
ran on a synthesized input
xingdi-eric-yuan/qait_public/generic.py
pointer only (licence: MIT); the stored copy get_code serves, from xingdi-eric-yuan/imrc_graph_public, is pointer only (licence: MIT) · get_code("f947fb149bc50f58")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, xingdi-eric-yuan/qait_public, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

check_reasoning_path_reward_sequence Not yet run
unverified (harvested, no recorded run)
xingdi-eric-yuan/qait_public/reward_helper.py
pointer only (licence: MIT) · get_code("09b5e97aa17e3fff")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, xingdi-eric-yuan/qait_public, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 3 the same month, 4 later) and 7 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
compute_mask 3 other papers
1 the same month, 2 later
1908.10449 (2019-08)
Interactive Machine Comprehension with Information Seeking Agents
2010.03768 (2020-10)
ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
2109.00077 (2021-09)
Interactive Machine Comprehension with Dynamic Knowledge Graphs
masked_softmax 2 other papers
2 later
2010.03768 (2020-10)
ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
2206.09670 (2022-06)
Benchmarking Constraint Inference in Inverse Reinforcement Learning
to_np 2 other papers
1 the same month, 1 later
1908.10449 (2019-08)
Interactive Machine Comprehension with Information Seeking Agents
2109.00077 (2021-09)
Interactive Machine Comprehension with Dynamic Knowledge Graphs
to_pt 2 other papers
1 the same month, 1 later
1908.10449 (2019-08)
Interactive Machine Comprehension with Information Seeking Agents
2109.00077 (2021-09)
Interactive Machine Comprehension with Dynamic 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

Humans observe and interact with the world to acquire knowledge. However, most existing machine reading comprehension (MRC) tasks miss the interactive, information-seeking component of comprehension. Such tasks present models with static documents that contain all necessary information, usually concentrated in a single short substring. Thus, models can achieve strong performance through simple word- and phrase-based pattern matching. We address this problem by formulating a novel text-based question answering task: Question Answering with Interactive Text (QAit). In QAit, an agent must interact with a partially observable text-based environment to gather information required to answer questions. QAit poses questions about the existence, location, and attributes of objects found in the environment. The data is built using a text-based game generator that defines the underlying dynamics of interaction with the environment. We propose and evaluate a set of baseline models for the QAit task that includes deep reinforcement learning agents. Experiments show that the task presents a major challenge for machine reading systems, while humans solve it with relative ease.

For agents

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

get_harvested_code_for_paper("1908.10909")
get_code_for_paper("1908.10909")
have("1908.10909")

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

curl https://syntology.ai/api/ran/1908.10909.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.10909.svg)](https://syntology.ai/paper/1908.10909)

Connect an agent — have() is free.