SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1808.09658 · 2018

APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 1 has no contract verdict; 0 failures of our instrument; 1 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/1808.09658.json · badge: /api/ran/1808.09658.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
UKPLab/emnlp2018-april canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
FunctionStatusWhere it lives
collect_props Ran
ran on a synthesized input
UKPLab/emnlp2018-april/summariser/data_processer/clauseIE_tree.py
code served (permissive licence) · get_code("f69a7b4a0aa67e48")
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 re

def collect_props(list_props):
    pruned_list = []
    for items in list_props:
        for prop1 in items:
            '\n            if pruned_list:\n                flag = 0\n                for prop2 in pruned_list:\n                    if re.search(prop2, prop1):\n                        flag = 1\n                if flag == 0:\n                    pruned_list.append(prop1)\n            else:\n            '
            pruned_list.append(prop1)
    return list(set(pruned_list))


# Construct valid arguments
# list_props is a list of items, where each item is iterable (contains prop1 values)
# The function iterates through each items, then through each prop1 in items
# So list_props should be a list of iterables (e.g., lists of strings)

ARGS = {
    "list_props": [
        ["prop_a", "prop_b", "prop_c"],
        ["prop_d", "prop_e"],
        ["prop_f"]
    ]
}
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
flatten_childtrees Not yet run
unverified (harvested, no recorded run)
UKPLab/emnlp2018-april/summariser/data_processer/clauseIE_tree.py
code served (permissive licence) · get_code("99d943eb843c3fc2")
How it ran

no invocation recorded.

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

We propose a method to perform automatic document summarisation without using reference summaries. Instead, our method interactively learns from users' preferences. The merit of preference-based interactive summarisation is that preferences are easier for users to provide than reference summaries. Existing preference-based interactive learning methods suffer from high sample complexity, i.e. they need to interact with the oracle for many rounds in order to converge. In this work, we propose a new objective function, which enables us to leverage active learning, preference learning and reinforcement learning techniques in order to reduce the sample complexity. Both simulation and real-user experiments suggest that our method significantly advances the state of the art. Our source code is freely available at https://github.com/UKPLab/emnlp2018-april.

For agents

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

get_harvested_code_for_paper("1808.09658")
get_code_for_paper("1808.09658")
have("1808.09658")

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

curl https://syntology.ai/api/ran/1808.09658.json

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

[![Syntology run record](https://syntology.ai/api/ran/1808.09658.svg)](https://syntology.ai/paper/1808.09658)

Connect an agent — have() is free.