SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.01069 · 2019

A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization

arXiv · PDF · Open in the Atlas

Code that ran

21 of 36 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; 2 honoured the contract we drafted, 2 violated it and 1 has no contract verdict; 16 failures of our instrument; 15 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/1902.01069.json · badge: /api/ran/1902.01069.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
naver/sqlova canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
qjay612/meta_learning_NL2SQL reimplementation (classifier label)
classifier basis: classifier_2025
15 ran · 7 no recorded run
tanmay1618/text_to_sql_bert reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
TooTouch/SPARTA application (classifier label)
classifier basis: classifier_2025
0 ran · 8 no recorded run
FunctionStatusWhere it lives
swish Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from jeonsworld/ViT-pytorch
pointer only · get_code("0f786c407fb1ee4c")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for 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.

LSTM Ran
ran on a synthesized input · constructed an object; no result was computed
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("ac5d84fb34186021")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

Loss_sa Ran
ran, violated the contract we drafted
naver/sqlova/sqlova/model/nl2sql/wikisql_models.py
code served (permissive licence) · get_code("3a0aeab0cd5f1c02")
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) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn.functional as F

torch.manual_seed(0)

# s_sa should be a tensor of logits with shape (batch_size, num_classes)
# The function applies cross_entropy, which expects:
# - input: (N, C) where N is batch size, C is number of classes
# - target: (N,) with class indices
s_sa = torch.randn(2, 4)  # batch_size=2, num_classes=4

# g_sa should be a list/array of target class indices
# cross_entropy expects long tensor with shape (N,)
g_sa = [0, 2]  # batch_size=2, valid class indices for 4 classes

ARGS = {
    "s_sa": s_sa,
    "g_sa": g_sa,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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
Loss_sc Ran
ran, violated the contract we drafted
naver/sqlova/sqlova/model/nl2sql/wikisql_models.py
code served (permissive licence) · get_code("176903678b9957e9")
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) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn.functional as F

torch.manual_seed(0)

# s_sc: logits tensor for cross_entropy (batch_size, num_classes)
# cross_entropy expects (N, C) where N is batch size, C is number of classes
s_sc = torch.randn(2, 4)

# g_sc: ground truth labels (batch_size,)
# cross_entropy expects long tensor with class indices
g_sc = [0, 2]

ARGS = {
    "s_sc": s_sc,
    "g_sc": g_sc,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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
Loss_sw_se Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
naver/sqlova/sqlova/model/nl2sql/wikisql_models.py
code served (permissive licence) · get_code("068dc7002d3e96a4")
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) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn as nn

torch.manual_seed(0)

# Batch size and sequence/dimension parameters
bS = 2  # batch size
max_h_len = 5  # max history length
n_conds = 4  # maximum number of conditions
mL = 6  # max length for word value positions
n_classes_sc = 3  # number of classes for select column
n_classes_sa = 4  # number of classes for select aggregation
n_classes_wn = 5  # number of classes for where number
n_classes_wo = 7  # number of classes for where operator

# s_sc: [bS, n_classes_sc] - logits for select column
s_sc = torch.randn(bS, n_classes_sc)

# s_sa: [bS, n_classes_sa] - logits for select aggregation
s_sa = torch.randn(bS, n_classes_sa)

# s_wn: [bS, n_classes_wn] - logits for where number
s_wn = torch.randn(bS, n_classes_wn)

# s_wc: [bS, max_h_len] - logits for where column
s_wc = torch.randn(bS, max_h_len)

# s_wo: [bS, n_conds, n_classes_wo] - logits for where operator
s_wo = torch.randn(bS, n_conds, n_classes_wo)

# s_wv: [bS, n_conds, mL, 2] - logits for where value start/end
s_wv = torch.randn(bS, n_conds, mL, 2)

# g_sc: [bS] - ground truth for select column
g_sc = [0, 2]

# g_sa: [bS] - ground truth for select aggregation
g_sa = [1, 3]

# g_wn: [bS] - ground truth for where number (number of conditions)
g_wn = [2, 1]

# g_wc: [[col_indices], [col_indices]] - ground truth for where columns
g_wc = [[0, 2], [1]]

# g_wo: [[op_indices], [op_indices]] - ground truth for where operators
g_wo = [[1, 3], [2]]

# g_wvi: [[[start, end], ...], [[start, end], ...]] - ground truth for where value indices
# For b=0: 2 conditions, for b=1: 1 condition
g_wvi = [
    [[1, 3], [2, 4]],  # batch 0: 2 conditions with start/end positions
    [[0, 2]]           # batch 1: 1 condition with start/end positions
]

ARGS = {
    "s_sc": s_sc,
    "s_sa": s_sa,
    "s_wn": s_wn,
    "s_wc": s_wc,
    "s_wo": s_wo,
    "s_wv": s_wv,
    "g_sc": g_sc,
    "g_sa": g_sa,
    "g_wn": g_wn,
    "g_wc": g_wc,
    "g_wo": g_wo,
    "g_wvi": g_wvi,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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
build_mask Ran
ran; our contract draft was wrong, not the code
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("5d0aa1b1e4f523a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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_sc_sa_pairs Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("d4e958304e9d9cd3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

convert_val_index_wp_to_string Ran
ran; our contract draft was wrong, not the code
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("ae7374b246065c73")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

encode_header Ran
ran; our contract draft was wrong, not the code
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("5d61fcf60d724be7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

encode_question Ran
ran; our contract draft was wrong, not the code
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("5bdce29c753f1649")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

gelu Ran
ran, honoured the contract we drafted
tanmay1618/text_to_sql_bert/modeling_bert.py
pointer only (licence: NONE) · get_code("fdc64f4c72036ae4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tanmay1618/text_to_sql_bert when it was checked. 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.

load_tf_weights_in_bert Ran
ran; our contract draft was wrong, not the code
tanmay1618/text_to_sql_bert/modeling_bert.py
pointer only (licence: NONE) · get_code("0c145728a35789fa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tanmay1618/text_to_sql_bert when it was checked. 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.

merge_val_to_english Ran
ran; our contract draft was wrong, not the code
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("57026522c11734ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

pooling Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("eb5186ba7911c429")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

pred_sel_col_for_beam Ran
ran; our contract draft was wrong, not the code
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("2f695c2ab714eb6a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

pred_where_col Ran
ran; our contract draft was wrong, not the code
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("65e08da52bb4da90")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

pred_where_num Ran
ran, honoured the contract we drafted
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("0f10e61b084db2c9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

pred_where_op Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("7a5f57930ec795b6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

pred_where_val_beam Ran
ran; our contract draft was wrong, not the code
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("3a8f7933be76eb6b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

remap_sc_idx Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("c98ecfdf5528adb3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

topk_multi_dim Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("73606ccc893d7732")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

SAP Not yet run
unverified (harvested, no recorded run)
TooTouch/SPARTA/SQLova/sqlova/model/nl2sql/wikisql_models.py
pointer only (licence: NONE) · get_code("cdf03242032636be")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TooTouch/SPARTA when it was checked. 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.

SCP Not yet run
unverified (harvested, no recorded run)
TooTouch/SPARTA/SQLova/sqlova/model/nl2sql/wikisql_models.py
pointer only (licence: NONE) · get_code("a763d4e5c8fee70a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TooTouch/SPARTA when it was checked. 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.

SelectAggregation Not yet run
unverified (harvested, no recorded run)
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("2f6b1d0d0eddc156")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

SelectColumn Not yet run
unverified (harvested, no recorded run)
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("d32f9af1a31a554c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

Seq2SQL Not yet run
unverified (harvested, no recorded run)
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("a2b9129ba9fabf46")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

Seq2SQL_v1 Not yet run
unverified (harvested, no recorded run)
TooTouch/SPARTA/SQLova/sqlova/model/nl2sql/wikisql_models.py
pointer only (licence: NONE) · get_code("6fa2b6ffbbd7a34d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TooTouch/SPARTA when it was checked. 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.

WCP Not yet run
unverified (harvested, no recorded run)
TooTouch/SPARTA/SQLova/sqlova/model/nl2sql/wikisql_models.py
pointer only (licence: NONE) · get_code("3445c5709b9efe59")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TooTouch/SPARTA when it was checked. 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.

WNP Not yet run
unverified (harvested, no recorded run)
TooTouch/SPARTA/SQLova/sqlova/model/nl2sql/wikisql_models.py
pointer only (licence: NONE) · get_code("13d3b06dde73507c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TooTouch/SPARTA when it was checked. 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.

WOP Not yet run
unverified (harvested, no recorded run)
TooTouch/SPARTA/SQLova/sqlova/model/nl2sql/wikisql_models.py
pointer only (licence: NONE) · get_code("6afa611f06e6153d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TooTouch/SPARTA when it was checked. 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.

WVP_se Not yet run
unverified (harvested, no recorded run)
TooTouch/SPARTA/SQLova/sqlova/model/nl2sql/wikisql_models.py
pointer only (licence: NONE) · get_code("8a301f33757b7b7d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TooTouch/SPARTA when it was checked. 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.

WhereColumn Not yet run
unverified (harvested, no recorded run)
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("599d8d43c163313c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

WhereNumber Not yet run
unverified (harvested, no recorded run)
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("a8c231a782002eb4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

WhereOperator Not yet run
unverified (harvested, no recorded run)
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("866f4764788d2be3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

WhereValue Not yet run
unverified (harvested, no recorded run)
qjay612/meta_learning_NL2SQL/src/models/model_wikisql.py
pointer only (licence: NONE) · get_code("f86a9d196e17299e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, qjay612/meta_learning_NL2SQL when it was checked. 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.

topk_multi_dim Not yet run
unverified (harvested, no recorded run)
TooTouch/SPARTA/SQLova/sqlova/model/nl2sql/wikisql_models.py
pointer only (licence: NONE) · get_code("747aeef5152d47f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TooTouch/SPARTA when it was checked. 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 36 samples lifted from this paper's linked repositories, 36 carry a function identity and 0 do not. Of the 36 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 2 the same month, 3 later) and 33 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
swish 206 other papers
6 dated earlier, 1 the same month, 199 later · 44 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1805.12114 (2018-05)
Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
1809.01357 (2018-09)
Zero Shot Learning for Code Education: Rubric Sampling with Deep Learning Inference
and 203 more not named here
gelu 198 other papers
3 dated earlier, 1 the same month, 194 later · 32 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.10125 (2019-01)
Glyce: Glyph-vectors for Chinese Character Representations
and 195 more not named here
load_tf_weights_in_bert 19 other papers
1 dated earlier, 18 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2002.01808 (2020-02)
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
and 16 more not named here

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 present SQLova, the first Natural-language-to-SQL (NL2SQL) model to achieve human performance in WikiSQL dataset. We revisit and discuss diverse popular methods in NL2SQL literature, take a full advantage of BERT {Devlin et al., 2018) through an effective table contextualization method, and coherently combine them, outperforming the previous state of the art by 8.2% and 2.5% in logical form and execution accuracy, respectively. We particularly note that BERT with a seq2seq decoder leads to a poor performance in the task, indicating the importance of a careful design when using such large pretrained models. We also provide a comprehensive analysis on the dataset and our model, which can be helpful for designing future NL2SQL datsets and models. We especially show that our model's performance is near the upper bound in WikiSQL, where we observe that a large portion of the evaluation errors are due to wrong annotations, and our model is already exceeding human performance by 1.3% in execution accuracy.

For agents

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

get_harvested_code_for_paper("1902.01069")
get_code_for_paper("1902.01069")
have("1902.01069")

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

curl https://syntology.ai/api/ran/1902.01069.json

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

[![Syntology run record](https://syntology.ai/api/ran/1902.01069.svg)](https://syntology.ai/paper/1902.01069)

Connect an agent — have() is free.