SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.01718 · 2019

End-to-End Open-Domain Question Answering with BERTserini

arXiv · PDF · Open in the Atlas

Code that ran

8 of 8 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; 1 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 3 failures of our instrument; 0 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/1902.01718.json · badge: /api/ran/1902.01718.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
rsvp-ai/bertserini canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
FunctionStatusWhere it lives
to_list Ran
ran; our contract draft was wrong, not the code
rsvp-ai/bertserini/bertserini/train/run_squad.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from AI-secure/InfoBERT, is pointer only (licence: NONE) · get_code("9df40357afea56cc")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from AI-secure/InfoBERT, and GitHub detected no licence in that repository 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.

choose_best_answer Ran
ran on a synthesized input
rsvp-ai/bertserini/bertserini/utils/utils.py
code served (permissive licence) · get_code("20bfdca6b0a6c2a7")
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 dict. 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 numpy as np

def score_computer(paragraph_score, phrase_score, paragraph_score_weight, phrase_score_weight):
    """Simple score computation function"""
    return paragraph_score * paragraph_score_weight + phrase_score * phrase_score_weight

# Create sample answer data structures
answer1 = {
    'answer': 'Paris',
    'paragraph_score': 0.8,
    'phrase_score': 0.7,
    'sentence': 'Paris is the capital of France.'
}

answer2 = {
    'answer': 'London',
    'paragraph_score': 0.6,
    'phrase_score': 0.5,
    'sentence': 'London is the capital of England.'
}

answer3 = {
    'answer': 'Berlin',
    'paragraph_score': 0.75,
    'phrase_score': 0.65,
    'sentence': 'Berlin is the capital of Germany.'
}

final_answers = [answer1, answer2, answer3]

ARGS = {
    'final_answers': final_answers,
    'score_computer': score_computer,
    'paragraph_score_weight': 0.6,
    'phrase_score_weight': 0.4,
    'mode': 'origin'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
compute_exact Ran
ran, honoured the contract we drafted
rsvp-ai/bertserini/bertserini/utils/utils_squad_metrics.py
code served (permissive licence) · get_code("9026d9da5d085bd4")
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 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 re
import string

def normalize_answer(s):
    """Lower text and remove punctuation, articles and extra whitespace."""

    def remove_articles(text):
        regex = re.compile('\\b(a|an|the)\\b', re.UNICODE)
        return re.sub(regex, ' ', text)

    def white_space_fix(text):
        return ' '.join(text.split())

    def remove_punc(text):
        exclude = set(string.punctuation)
        return ''.join((ch for ch in text if ch not in exclude))

    def lower(text):
        return text.lower()
    return white_space_fix(remove_articles(remove_punc(lower(s))))

def compute_exact(a_gold, a_pred):
    return int(normalize_answer(a_gold) == normalize_answer(a_pred))

ARGS = {
    "a_gold": "The quick brown fox jumps over the lazy dog.",
    "a_pred": "the quick brown fox jumps over the lazy dog"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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
get_best_answer Ran
ran on a synthesized input
rsvp-ai/bertserini/bertserini/utils/utils_new.py
code served (permissive licence) · get_code("4dcd04d7f6a7d02a")
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 Answer. 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 torch
import torch.nn as nn

torch.manual_seed(0)

class Answer:
    def __init__(self, score_value):
        self.score_value = score_value
        self.total_score = 0
    
    def aggregate_score(self, weight):
        self.total_score = self.score_value * weight

candidate1 = Answer(10.0)
candidate2 = Answer(20.0)
candidate3 = Answer(15.0)

candidates = [candidate1, candidate2, candidate3]

ARGS = {
    "candidates": candidates,
    "weight": 0.5
}
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 Answer — a Answer output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Answer 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
get_tokens Ran
ran; our contract draft was wrong, not the code
rsvp-ai/bertserini/bertserini/utils/utils_squad_metrics.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from saptarshi059/cdqa-project, is pointer only (licence: NONE) · get_code("aa6bc32d9c17a2f1")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from saptarshi059/cdqa-project, and GitHub detected no licence in that repository 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.

normalize_answer Ran
ran; our contract draft was wrong, not the code
rsvp-ai/bertserini/bertserini/utils/utils_squad_metrics.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from saptarshi059/cdqa-project, is pointer only (licence: NONE) · get_code("6a96435eba311b08")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from saptarshi059/cdqa-project, and GitHub detected no licence in that repository 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.

strip_accents Ran
ran on a synthesized input
rsvp-ai/bertserini/bertserini/utils/utils.py
code served (permissive licence) · get_code("b668a6a9dda0f7b1")
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 str. 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 unicodedata

def strip_accents(text):
    return ''.join((char for char in unicodedata.normalize('NFKD', text) if unicodedata.category(char) != 'Mn'))

ARGS = {
    'text': 'café naïve résumé'
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
weighted_score Ran
ran on a synthesized input
rsvp-ai/bertserini/bertserini/utils/utils.py
code served (permissive licence) · get_code("167ccd707d8de0a4")
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
import numpy as np

torch.manual_seed(0)

# The function takes 4 parameters:
# - paragraph_score: a numeric value (likely float or tensor)
# - phrase_score: a numeric value (likely float or tensor)
# - paragraph_weight: a numeric value with default 0.5
# - phrase_weight: a numeric value with default 0.5

# The function multiplies scores by weights and adds them
# This works with floats, ints, or tensors

# Create simple numeric values
paragraph_score = 0.8
phrase_score = 0.6
paragraph_weight = 0.4
phrase_weight = 0.6

ARGS = {
    "paragraph_score": paragraph_score,
    "phrase_score": phrase_score,
    "paragraph_weight": paragraph_weight,
    "phrase_weight": phrase_weight,
}
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 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

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 4 later) and 4 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
to_list 41 other papers
41 later
1910.06188 (2019-10)
Q8BERT: Quantized 8Bit BERT
1911.02984 (2019-11)
The TechQA Dataset
2002.08795 (2020-02)
How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents
and 38 more not named here
normalize_answer 37 other papers
2 dated earlier, 35 later · 1 only as an assembly brick
1808.07042 (2018-08)
CoQA: A Conversational Question Answering Challenge
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1908.00059 (2019-08)
GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
and 34 more not named here
get_tokens 25 other papers
1 dated earlier, 24 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1908.08962 (2019-08)
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
1910.01244 (2019-10)
Linking artificial and human neural representations of language
and 22 more not named here
compute_exact 11 other papers
11 later
2004.07347 (2020-04)
HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data
2105.02692 (2021-05)
Learning to Perturb Word Embeddings for Out-of-distribution QA
2109.08133 (2021-09)
Phrase Retrieval Learns Passage Retrieval, Too
and 8 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 demonstrate an end-to-end question answering system that integrates BERT with the open-source Anserini information retrieval toolkit. In contrast to most question answering and reading comprehension models today, which operate over small amounts of input text, our system integrates best practices from IR with a BERT-based reader to identify answers from a large corpus of Wikipedia articles in an end-to-end fashion. We report large improvements over previous results on a standard benchmark test collection, showing that fine-tuning pretrained BERT with SQuAD is sufficient to achieve high accuracy in identifying answer spans.

For agents

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

get_harvested_code_for_paper("1902.01718")
get_code_for_paper("1902.01718")
have("1902.01718")

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

curl https://syntology.ai/api/ran/1902.01718.json

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

[![Syntology run record](https://syntology.ai/api/ran/1902.01718.svg)](https://syntology.ai/paper/1902.01718)

Connect an agent — have() is free.