SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.02460 · 2020

DeText: A Deep Text Ranking Framework with BERT

arXiv · PDF · Open in the Atlas

Code that ran

6 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 6 have no contract verdict; 0 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/2008.02460.json · badge: /api/ran/2008.02460.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
linkedin/detext canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_elem_diff_for_user_doc Ran
ran on a synthesized input
linkedin/detext/src/detext/layers/interaction_layer.py
code served (permissive licence) · get_code("727b60595ef2a241")
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 SymbolicTensor. 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 tensorflow as tf

# Set random seed for reproducibility
tf.random.set_seed(0)

# Define small tensors with distinct dimensions
batch_size = 2
group_size = 3
num_doc_fields = 4
num_user_fields = 5
num_deep = 6

# Create doc_ftrs with shape [batch_size, group_size, num_doc_fields, num_deep]
doc_ftrs = tf.random.normal([batch_size, group_size, num_doc_fields, num_deep])

# Create user_ftrs with shape [batch_size, num_user_fields, num_deep]
user_ftrs = tf.random.normal([batch_size, num_user_fields, num_deep])

ARGS = {
    'doc_ftrs': doc_ftrs,
    'user_ftrs': user_ftrs,
    'num_doc_fields': num_doc_fields,
    'num_user_fields': num_user_fields,
    'num_deep': num_deep
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SymbolicTensor — a SymbolicTensor 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
compute_hadamard_prod_for_user_doc Ran
ran on a synthesized input
linkedin/detext/src/detext/layers/interaction_layer.py
code served (permissive licence) · get_code("91e8385962b3d548")
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 SymbolicTensor. 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 tensorflow as tf

# Set random seed for reproducibility
tf.random.set_seed(0)

# Define dimensions with distinct values to avoid ambiguity
batch_size = 2
group_size = 3
num_doc_fields = 4
num_user_fields = 5
num_deep = 6

# Create doc_ftrs with shape [batch_size, group_size, num_doc_fields, num_deep]
doc_ftrs = tf.random.normal([batch_size, group_size, num_doc_fields, num_deep])

# Create user_ftrs with shape [batch_size, num_user_fields, num_deep]
user_ftrs = tf.random.normal([batch_size, num_user_fields, num_deep])

ARGS = {
    'doc_ftrs': doc_ftrs,
    'user_ftrs': user_ftrs,
    'num_doc_fields': num_doc_fields,
    'num_user_fields': num_user_fields,
    'num_deep': num_deep,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SymbolicTensor — a SymbolicTensor 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
compute_num_sim_ftrs Ran
ran on a synthesized input
linkedin/detext/src/detext/layers/interaction_layer.py
code served (permissive licence) · get_code("82e169006d1c66be")
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 int, ndim 0, dtype family int, 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
import numpy as np

torch.manual_seed(0)

# Construct arguments for compute_num_sim_ftrs
ARGS = {
    'sim_func_names': ['inner', 'concat', 'hadamard', 'diff'],
    'num_doc_fields': 3,
    'num_user_fields': 2,
    'num_deep': 4
}
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 int, ndim 0, dtype family int, 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
concat_on_last_axis_dense Ran
ran on a synthesized input
linkedin/detext/src/detext/layers/feature_grouper.py
code served (permissive licence) · get_code("503b84a0eaf159e1")
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 SymbolicTensor. 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 tensorflow as tf
import numpy as np

# Create small dense tensors with distinct shapes to probe dimensions
tensor1 = tf.constant([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]], dtype=tf.float32)  # shape (2, 3)
tensor2 = tf.constant([[7.0, 8.0], [9.0, 10.0]], dtype=tf.float32)  # shape (2, 2)
tensor3 = tf.constant([[11.0], [12.0]], dtype=tf.float32)  # shape (2, 1)

tensor_list = [tensor1, tensor2, tensor3]

ARGS = {
    "tensor_list": tensor_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SymbolicTensor — a SymbolicTensor 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
concat_on_last_axis_sparse Ran
ran on a synthesized input
linkedin/detext/src/detext/layers/feature_grouper.py
code served (permissive licence) · get_code("ac8d5df370fb7447")
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 SparseTensor. 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 tensorflow as tf

# Create small sparse tensors to concatenate
# sparse tensors have indices, values, and dense_shape

# First sparse tensor: 2x3 matrix
indices1 = [[0, 0], [1, 2]]
values1 = [1.0, 2.0]
dense_shape1 = [2, 3]
sparse_tensor1 = tf.SparseTensor(indices=indices1, values=values1, dense_shape=dense_shape1)

# Second sparse tensor: 2x4 matrix (different last dimension)
indices2 = [[0, 1], [1, 3]]
values2 = [3.0, 4.0]
dense_shape2 = [2, 4]
sparse_tensor2 = tf.SparseTensor(indices=indices2, values=values2, dense_shape=dense_shape2)

# Create list of sparse tensors
tensor_list = [sparse_tensor1, sparse_tensor2]

ARGS = {
    "tensor_list": tensor_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SparseTensor — a SparseTensor output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SparseTensor 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
create_conv_layer Ran
ran on a synthesized input
linkedin/detext/src/detext/layers/cnn_layer.py
code served (permissive licence) · get_code("d2991efcc21f42b4")
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 tensorflow as tf

ARGS = {
    'name_prefix': 'conv_layer',
    'filter_window_sizes': [3, 5, 7],
    'num_units': 4,
    'num_filters': 16
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — 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
apply_cnn_on_text Not yet run
unverified (harvested, no recorded run)
linkedin/detext/src/detext/layers/cnn_layer.py
code served (permissive licence) · get_code("b75e09919639454f")
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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Ranking is the most important component in a search system. Mostsearch systems deal with large amounts of natural language data,hence an effective ranking system requires a deep understandingof text semantics. Recently, deep learning based natural languageprocessing (deep NLP) models have generated promising results onranking systems. BERT is one of the most successful models thatlearn contextual embedding, which has been applied to capturecomplex query-document relations for search ranking. However,this is generally done by exhaustively interacting each query wordwith each document word, which is inefficient for online servingin search product systems. In this paper, we investigate how tobuild an efficient BERT-based ranking model for industry use cases.The solution is further extended to a general ranking framework,DeText, that is open sourced and can be applied to various rankingproductions. Offline and online experiments of DeText on threereal-world search systems present significant improvement overstate-of-the-art approaches.

For agents

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

get_harvested_code_for_paper("2008.02460")
get_code_for_paper("2008.02460")
have("2008.02460")

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

curl https://syntology.ai/api/ran/2008.02460.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.02460.svg)](https://syntology.ai/paper/2008.02460)

Connect an agent — have() is free.