SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.09661 · 2018

Personalized Language Model for Query Auto-Completion

arXiv · PDF · Open in the Atlas

Code that ran

2 of 7 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 2 have no contract verdict; 0 failures of our instrument; 5 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/1804.09661.json · badge: /api/ran/1804.09661.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
ajaech/query_completion canonical (classifier label)
classifier basis: census
2 ran · 5 no recorded run
FunctionStatusWhere it lives
GetRankInList Ran
ran on a synthesized input
ajaech/query_completion/code/metrics.py
code served (permissive licence) · get_code("006abe43970b6bf7")
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 float, ndim 0, dtype family float, shape () 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)

# Analyze the function:
# - query: a single item that will be checked for membership in qlist
# - qlist: a list-like object that supports:
#   - membership testing (in operator)
#   - .index() method to find position
# 
# The function returns a rank score based on position in list

# Create simple test data
query = "apple"
qlist = ["banana", "apple", "cherry", "date"]

ARGS = {
    "query": query,
    "qlist": qlist
}
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 float, ndim 0, dtype family float, shape () — shape () 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
LoadData Ran
ran on a synthesized input
ajaech/query_completion/code/dataset.py
code served (permissive licence) · get_code("3dce6534f889f948")
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 DataFrame. 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 datetime
import pandas
import tempfile
import os
import gzip

# Create temporary gzip-compressed TSV files with the expected format
temp_dir = tempfile.mkdtemp()

# Create first test file
filename1 = os.path.join(temp_dir, 'test1.tsv.gz')
with gzip.open(filename1, 'wt') as f:
    f.write('user1\thello world\t2023-01-15 09:30:00\n')
    f.write('user2\tgoodbye\t2023-01-15 14:45:00\n')

# Create second test file
filename2 = os.path.join(temp_dir, 'test2.tsv.gz')
with gzip.open(filename2, 'wt') as f:
    f.write('user3\ttest query\t2023-01-16 22:15:00\n')
    f.write('user1\tanother search\t2023-01-17 03:00:00\n')

ARGS = {
    'filenames': [filename1, filename2],
    'split': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
FastLoadDynamic Not yet run
unverified (harvested, no recorded run)
ajaech/query_completion/code/mpc_baseline.py
code served (permissive licence) · get_code("b5468ea35486ebda")
How it ran

no invocation recorded.

FirstNonMatch Not yet run
unverified (harvested, no recorded run)
ajaech/query_completion/code/beam.py
code served (permissive licence) · get_code("f7b743d864558020")
How it ran

no invocation recorded.

GetCompletions Not yet run
unverified (harvested, no recorded run)
ajaech/query_completion/code/beam.py
code served (permissive licence) · get_code("d2f2be1f1ed4d5e0")
How it ran

no invocation recorded.

GetPrefixLen Not yet run
unverified (harvested, no recorded run)
ajaech/query_completion/code/helper.py
code served (permissive licence) · get_code("8aa3413f430b1b0d")
How it ran

no invocation recorded.

InitBeam Not yet run
unverified (harvested, no recorded run)
ajaech/query_completion/code/beam.py
code served (permissive licence) · get_code("20750482b8f16c0c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 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.

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

Query auto-completion is a search engine feature whereby the system suggests completed queries as the user types. Recently, the use of a recurrent neural network language model was suggested as a method of generating query completions. We show how an adaptable language model can be used to generate personalized completions and how the model can use online updating to make predictions for users not seen during training. The personalized predictions are significantly better than a baseline that uses no user information.

For agents

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

get_harvested_code_for_paper("1804.09661")
get_code_for_paper("1804.09661")
have("1804.09661")

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

curl https://syntology.ai/api/ran/1804.09661.json

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

[![Syntology run record](https://syntology.ai/api/ran/1804.09661.svg)](https://syntology.ai/paper/1804.09661)

Connect an agent — have() is free.