SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.08678 · 2021

RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering

arXiv · PDF · Open in the Atlas

Code that ran

2 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 0 have no contract verdict; 2 failures of our instrument; 0 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/2109.08678.json · badge: /api/ran/2109.08678.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
salesforce/rng-kbqa canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
lmap Ran
ran; our contract draft was wrong, not the code
salesforce/rng-kbqa/framework/run_generator.py
code served (permissive licence) · get_code("599d7419b72e40aa")
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 int; 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 torch
import numpy as np
from typing import Callable, Dict, List, Optional, Tuple, Iterable

torch.manual_seed(0)

# Simple callable function that transforms an element
def simple_function(x):
    return x * 2

# Create an iterable - can be a list
test_iterable = [1, 2, 3, 4, 5]

ARGS = {
    "f": simple_function,
    "x": test_iterable,
}
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 list, ndim 1, dtype family int — 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
predict_loop_per_instance Ran
ran; our contract draft was wrong, not the code
salesforce/rng-kbqa/framework/run_ranker.py
code served (permissive licence) · get_code("50a95a3a86b8c957")
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 tuple. 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
from torch.utils.data import DataLoader, SequentialSampler, TensorDataset

torch.manual_seed(0)

# Create a minimal model that returns logits
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 2)
    
    def forward(self, input_ids, token_type_ids=None, attention_mask=None):
        # Return tuple with logits as first element
        logits = self.linear(input_ids.float())
        return (logits,)

# Create minimal args object
class Args:
    def __init__(self):
        self.eval_batch_size = 2
        self.device = 'cpu'
        self.model_type = 'bert'  # Use a model_type that keeps token_type_ids

args_obj = Args()

# Create small encoded_candidates
# Format: (input_ids, token_type_ids, attention_mask, labels)
batch_size = 2
seq_length = 4

input_ids = torch.randint(0, 100, (batch_size, seq_length))
token_type_ids = torch.randint(0, 2, (batch_size, seq_length))
attention_mask = torch.ones(batch_size, seq_length)
labels = torch.randint(0, 2, (batch_size,))

encoded_candidates = (input_ids, token_type_ids, attention_mask, labels)

# Create model
model = MinimalModel()

ARGS = {
    'args': args_obj,
    'model': model,
    'encoded_candidates': encoded_candidates
}
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 tuple — a tuple 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

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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 1 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
lmap 9 other papers
6 dated earlier, 1 the same month, 2 later
2007.08426 (2020-07)
Investigating Pretrained Language Models for Graph-to-Text Generation
2104.08400 (2021-04)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs
2104.08691 (2021-04)
The Power of Scale for Parameter-Efficient Prompt Tuning
and 6 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

Existing KBQA approaches, despite achieving strong performance on i.i.d. test data, often struggle in generalizing to questions involving unseen KB schema items. Prior ranking-based approaches have shown some success in generalization, but suffer from the coverage issue. We present RnG-KBQA, a Rank-and-Generate approach for KBQA, which remedies the coverage issue with a generation model while preserving a strong generalization capability. Our approach first uses a contrastive ranker to rank a set of candidate logical forms obtained by searching over the knowledge graph. It then introduces a tailored generation model conditioned on the question and the top-ranked candidates to compose the final logical form. We achieve new state-of-the-art results on GrailQA and WebQSP datasets. In particular, our method surpasses the prior state-of-the-art by a large margin on the GrailQA leaderboard. In addition, RnG-KBQA outperforms all prior approaches on the popular WebQSP benchmark, even including the ones that use the oracle entity linking. The experimental results demonstrate the effectiveness of the interplay between ranking and generation, which leads to the superior performance of our proposed approach across all settings with especially strong improvements in zero-shot generalization.

For agents

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

get_harvested_code_for_paper("2109.08678")
get_code_for_paper("2109.08678")
have("2109.08678")

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

curl https://syntology.ai/api/ran/2109.08678.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.08678.svg)](https://syntology.ai/paper/2109.08678)

Connect an agent — have() is free.