SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.07421 · 2019

SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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; 2 honoured the contract we drafted, 1 violated it and 2 have no contract verdict; 2 failures of our instrument; 2 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/1907.07421.json · badge: /api/ran/1907.07421.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
SKTBrain/SUMBT canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
nikitacs16/xlift_dst reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran, honoured the contract we drafted
SKTBrain/SUMBT/code/main-multislot-ewc.py
code served (permissive licence) · get_code("eb725d5794b15f6b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned int64, 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 numpy as np

# Create sample outputs from a model (e.g., logits for 2 samples, 5 classes)
out = np.array([
    [0.1, 0.3, 0.8, 0.2, 0.1],  # argmax = 2
    [0.9, 0.1, 0.2, 0.3, 0.05]  # argmax = 0
])

# Create corresponding labels
labels = np.array([2, 0])

ARGS = {
    'out': out,
    'labels': labels
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int64, 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
clones Ran
ran; our contract draft was wrong, not the code
SKTBrain/SUMBT/code/BeliefTrackerSlotQueryMultiSlotTransformer.py
pointer only (licence: MIT); the stored copy get_code serves, from smiles724/molformer, is pointer only (licence: NONE) · get_code("cf78c734df121970")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from smiles724/molformer, 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.

convert_examples_to_features Ran
ran on a synthesized input
SKTBrain/SUMBT/code/main-multislot.py
code served (permissive licence) · get_code("12f577629e0dd0b5")
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 logging

logging.basicConfig(level=logging.INFO)

# Create a minimal tokenizer stand-in
class MinimalTokenizer:
    def __init__(self):
        self.vocab = {
            '[CLS]': 101,
            '[SEP]': 102,
            '[PAD]': 0,
            'hello': 1,
            'world': 2,
            'good': 3,
            'bye': 4,
        }
    
    def tokenize(self, text):
        # Simple tokenizer that splits on spaces and handles '#'
        tokens = text.split()
        result = []
        for token in tokens:
            if token == '#':
                result.append('[SEP]')
            else:
                result.append(token.lower())
        return result
    
    def convert_tokens_to_ids(self, tokens):
        ids = []
        for token in tokens:
            ids.append(self.vocab.get(token, 0))
        return ids

# Create minimal example objects
class Example:
    def __init__(self, guid, text_a, text_b, label):
        self.guid = guid
        self.text_a = text_a
        self.text_b = text_b
        self.label = label

# Create examples for 2 dialogues with 3 turns each
examples = [
    Example(guid='dial-0-0', text_a='hello world', text_b='good morning', label=['none', 'none']),
    Example(guid='dial-0-1', text_a='how are you', text_b=None, label=['none', 'dontcare']),
    Example(guid='dial-0-2', text_a='good bye', text_b=None, label=['none', 'none']),
    Example(guid='dial-1-0', text_a='hello there', text_b='yes', label=['none', 'none']),
    Example(guid='dial-1-1', text_a='what is this', text_b=None, label=['dontcare', 'none']),
    Example(guid='dial-1-2', text_a='goodbye', text_b=None, label=['none', 'none']),
]

# Label list with two slots
label_list = [
    ['none', 'dontcare', 'do not care'],
    ['none', 'dontcare', 'do not care'],
]

ARGS = {
    'examples': examples,
    'label_list': label_list,
    'max_seq_length': 16,
    'tokenizer': MinimalTokenizer(),
    'max_turn_length': 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 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
get_label_embedding Ran
ran on a synthesized input
SKTBrain/SUMBT/code/main-multislot-ewc.py
code served (permissive licence) · get_code("289ac90910019aec")
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

class MockTokenizer:
    def tokenize(self, text):
        # Simple mock: split by spaces
        return text.split()
    
    def convert_tokens_to_ids(self, tokens):
        # Simple mock: map each token to a unique id
        token_to_id = {
            '[CLS]': 101,
            '[SEP]': 102,
            'hello': 1,
            'world': 2,
            'test': 3,
            'label': 4,
        }
        return [token_to_id.get(token, 5) for token in tokens]

torch.manual_seed(0)

labels = ['hello world', 'test label']
max_seq_length = 8
tokenizer = MockTokenizer()
device = 'cpu'

ARGS = {
    'labels': labels,
    'max_seq_length': max_seq_length,
    'tokenizer': tokenizer,
    'device': device,
}
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
subsequent_mask Ran
ran, violated the contract we drafted
SKTBrain/SUMBT/code/BeliefTrackerSlotQueryMultiSlotTransformer.py
code served (permissive licence) · get_code("79e53d4ea458987d")
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 Tensor, ndim 3, dtype family float, shape (1, 4, 4) 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 numpy as np
import torch

torch.manual_seed(0)

# The function takes a single parameter 'size' which is used to create
# a numpy array of shape (1, size, size) and then converted to a torch tensor.
# We need to provide a small integer value for size.

size = 4

ARGS = {
    "size": size
}
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 Tensor, ndim 3, dtype family float, shape (1, 4, 4) — shape (1, 4, 4) 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
to_device Ran
ran; our contract draft was wrong, not the code
nikitacs16/xlift_dst/multiwoz_sumbt/convlab2/util/train_util.py
pointer only (licence: NONE) · get_code("83cea58119436bee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nikitacs16/xlift_dst 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.

warmup_linear Ran
ran, honoured the contract we drafted
SKTBrain/SUMBT/code/main-multislot.py
code served (permissive licence) · get_code("c58d57224530d17e")
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 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)

# The function warmup_linear takes two parameters:
# - x: a numeric value (float) representing a position/step in training
# - warmup: a float representing the warmup threshold (default 0.002)
# 
# The function uses x and warmup in simple arithmetic comparisons and operations,
# so we just need numeric values.

ARGS = {
    "x": 0.001,
    "warmup": 0.002
}
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 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
convert_examples_to_features Not yet run
unverified (harvested, no recorded run)
SKTBrain/SUMBT/code/main-multislot-ewc.py
code served (permissive licence) · get_code("cc4b867df9657676")
How it ran

no invocation recorded.

get_label_embedding Not yet run
unverified (harvested, no recorded run)
nikitacs16/xlift_dst/multiwoz_sumbt/convlab2/dst/sumbt/multiwoz/sumbt.py
pointer only (licence: NONE) · get_code("a36ab0a94e8329a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nikitacs16/xlift_dst 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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 4 later) and 5 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
clones 79 other papers
13 dated earlier, 2 the same month, 64 later · 11 only as an assembly brick
1411.4555 (2014-11)
Show and Tell: A Neural Image Caption Generator
1612.00563 (2016-12)
Self-critical Sequence Training for Image Captioning
1706.03762 (2017-06)
Attention Is All You Need
and 76 more not named here
accuracy 21 other papers
9 dated earlier, 12 later
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.08746 (2019-01)
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
1904.03323 (2019-04)
Publicly Available Clinical BERT Embeddings
and 18 more not named here
subsequent_mask 21 other papers
5 dated earlier, 16 later
1411.4555 (2014-11)
Show and Tell: A Neural Image Caption Generator
1612.00563 (2016-12)
Self-critical Sequence Training for Image Captioning
1707.07998 (2017-07)
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
and 18 more not named here
warmup_linear 19 other papers
8 dated earlier, 11 later
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1803.03376 (2018-03)
Learning Approximate Inference Networks for Structured Prediction
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
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

In goal-oriented dialog systems, belief trackers estimate the probability distribution of slot-values at every dialog turn. Previous neural approaches have modeled domain- and slot-dependent belief trackers, and have difficulty in adding new slot-values, resulting in lack of flexibility of domain ontology configurations. In this paper, we propose a new approach to universal and scalable belief tracker, called slot-utterance matching belief tracker (SUMBT). The model learns the relations between domain-slot-types and slot-values appearing in utterances through attention mechanisms based on contextual semantic vectors. Furthermore, the model predicts slot-value labels in a non-parametric way. From our experiments on two dialog corpora, WOZ 2.0 and MultiWOZ, the proposed model showed performance improvement in comparison with slot-dependent methods and achieved the state-of-the-art joint accuracy.

For agents

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

get_harvested_code_for_paper("1907.07421")
get_code_for_paper("1907.07421")
have("1907.07421")

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

curl https://syntology.ai/api/ran/1907.07421.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.07421.svg)](https://syntology.ai/paper/1907.07421)

Connect an agent — have() is free.