SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.00796 · 2020

A Simple Language Model for Task-Oriented Dialogue

arXiv · PDF · Open in the Atlas

Code that ran

13 of 14 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, 2 violated it and 7 have no contract verdict; 4 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/2005.00796.json · badge: /api/ran/2005.00796.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/simpletod canonical (classifier label)
classifier basis: census
13 ran · 1 no recorded run
FunctionStatusWhere it lives
create_position_ids_from_input_ids Ran
ran on a synthesized input
salesforce/simpletod/models/modeling_utils.py
code served (permissive licence) · get_code("d4f3546f2ecff417")
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 2, dtype family int, shape (2, 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 torch

torch.manual_seed(0)

# Create small input_ids tensor (batch_size=2, sequence_length=4)
# Values should be token IDs, with some padding tokens
input_ids = torch.tensor([
    [1, 2, 0, 0],  # sequence with padding at end
    [3, 4, 5, 0]   # sequence with padding at end
], dtype=torch.long)

# padding_idx is typically 0 in most tokenizers
padding_idx = 0

ARGS = {
    "input_ids": input_ids,
    "padding_idx": padding_idx
}
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 Tensor, ndim 2, dtype family int, shape (2, 4) — shape (2, 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
fixDelex Ran
ran on a synthesized input
salesforce/simpletod/preprocess_multiwoz.py
code served (permissive licence) · get_code("9db2246dbf2fe48c")
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 torch
import numpy as np

# Construct valid arguments for fixDelex function

filename = "test_dialogue.json"

# data structure: needs 'log' key with list of dicts containing 'text' keys
data = {
    'log': [
        {'text': 'I need a restaurant_123'},
        {'text': 'Show me a hotel_456'},
        {'text': 'Find an attraction_789'}
    ]
}

# data2 structure: nested dict with filename (without .json) as key, 
# then str(idx_acts) as key, containing a dict with dialogue acts
data2 = {
    'test_dialogue': {
        '0': {
            'Restaurant': {'food': 'Italian'},
            'Hotel': {'stars': 4}
        },
        '1': {
            'Attraction': {'type': 'museum'}
        },
        '2': {
            'Restaurant': {'area': 'city centre'}
        }
    }
}

# idx: index into data['log']
idx = 0

# idx_acts: index for accessing dialogue acts in data2
idx_acts = 0

ARGS = {
    'filename': filename,
    'data': data,
    'data2': data2,
    'idx': idx,
    'idx_acts': idx_acts
}
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 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
get_belief Ran
ran on a synthesized input
salesforce/simpletod/utils/simpletod.py
code served (permissive licence) · get_code("6593f647e65bca52")
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 torch

torch.manual_seed(0)

ARGS = {
    "sent": "<|belief|>domain hotel, type restaurant<|action|>book<|endofbelief|>"
}
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 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
get_belief_dbsearch Ran
ran on a synthesized input
salesforce/simpletod/utils/simpletod.py
code served (permissive licence) · get_code("d273f88c13f089a1")
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 torch

def get_belief_dbsearch(sent):
    if '<|belief|>' in sent:
        tmp = sent.strip(' ').split('<|belief|>')[-1].split('<|endofbelief|>')[0]
    else:
        return []
    tmp = tmp.strip(' .,')
    tmp = tmp.replace('<|endofbelief|>', '')
    tmp = tmp.replace('<|endoftext|>', '')
    belief = tmp.split(',')
    new_belief = []
    for bs in belief:
        bs = bs.strip(' .,')
        if bs not in new_belief:
            new_belief.append(bs)
    return new_belief

ARGS = {
    'sent': 'This is a test <|belief|>belief1, belief2, belief3<|endofbelief|> and more text'
}
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 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
get_belief_openaigpt Ran
ran on a synthesized input
salesforce/simpletod/utils/simpletod.py
code served (permissive licence) · get_code("817ada1e305378b6")
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 torch

torch.manual_seed(0)

# The function get_belief_openaigpt takes a single parameter 'sent' which is a string
# It parses the string looking for '< | belief | >' markers and extracts belief text
# between that marker and '< | action | >' marker, then splits by commas and cleans up

# Test case 1: String with belief markers
sent_with_belief = "Some text < | belief | > belief1, belief2, belief3 < | action | > action text"

ARGS = {
    "sent": sent_with_belief
}
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 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
hf_bucket_url Ran
ran; our contract draft was wrong, not the code
salesforce/simpletod/models/file_utils.py
code served (permissive licence) · get_code("b2be6c932ce41084")
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 torch

ARGS = {
    'identifier': 'bert-base-uncased',
    'postfix': 'pytorch_model.bin',
    'cdn': False
}
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 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
is_ascii Ran
ran, violated the contract we drafted
salesforce/simpletod/preprocess_multiwoz.py
code served (permissive licence) · get_code("1b465b9239cb631c")
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 bool, 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.

ARGS = {
    "s": "Hello, World! This is an ASCII string with numbers 12345 and symbols @#$%"
}
Setup block drafted by
a language model, Claude Sonnet 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 bool, 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
is_remote_url Ran
ran, violated the contract we drafted
salesforce/simpletod/models/file_utils.py
code served (permissive licence) · get_code("4381d1f588a7f42a")
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 bool, 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
from urllib.parse import urlparse

ARGS = {
    'url_or_filename': 'https://example.com/model.pth'
}
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 bool, 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
postprocess_gpt2 Ran
ran on a synthesized input
salesforce/simpletod/evaluate_multiwoz.py
code served (permissive licence) · get_code("9b5c8cad10804374")
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 torch

# Based on the function body, generated_raw_data is a dict where:
# - keys are some identifier strings
# - values are dicts containing:
#   - 'target_turn_belief': list of lists of strings
#   - 'generated_turn_belief': list of lists of strings
#   - 'generated_belief': list of strings
#   - 'generated_response': list of strings
#   - 'generated_action': list of strings
#   - 'target_action': list of strings

generated_raw_data = {
    "dialogue_001": {
        "target_turn_belief": [
            ["hotel name the cambridge", "hotel area centre"],
            ["hotel stars 5 star"]
        ],
        "generated_turn_belief": [
            ["hotel name the cambridge", "hotel area centre"],
            ["hotel stars 5 star", "restaurant food italian"]
        ],
        "generated_belief": [
            "hotel name the cambridge",
            "hotel area centre",
            "restaurant food italian"
        ],
        "generated_response": [
            "The Cambridge is in the city centre.",
            "It is a 5 star hotel."
        ],
        "generated_action": [
            "inform",
            "inform"
        ],
        "target_action": [
            "inform",
            "inform"
        ]
    },
    "dialogue_002": {
        "target_turn_belief": [
            ["train destination cambridge", "train departure time 14:30"],
            ["taxi type black cab"]
        ],
        "generated_turn_belief": [
            ["train destination cambridge"],
            ["taxi type black cab", "attraction name king's college"]
        ],
        "generated_belief": [
            "train destination cambridge",
            "taxi type black cab"
        ],
        "generated_response": [
            "There are trains to Cambridge.",
            "A black cab is available."
        ],
        "generated_action": [
            "inform",
            "inform"
        ],
        "target_action": [
            "inform",
            "inform"
        ]
    }
}

ARGS = {
    "generated_raw_data": generated_raw_data
}
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 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
prune_linear_layer Ran
ran; our contract draft was wrong, not the code
salesforce/simpletod/models/modeling_utils.py
code served (permissive licence) · get_code("d30d6c3098df2c42")
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 Linear. 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
from torch import nn

torch.manual_seed(0)

# Create a linear layer to prune
# Using distinct sizes: input_features=3, output_features=4
layer = nn.Linear(in_features=3, out_features=4, bias=True)

# Create an index tensor to select which output features to keep
# Selecting 2 out of 4 output features
index = torch.tensor([0, 2], dtype=torch.long)

# dim=0 means we're pruning along the output dimension (rows of weight matrix)
dim = 0

ARGS = {
    "layer": layer,
    "index": index,
    "dim": dim,
}
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 Linear — a Linear output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Linear 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
remove_model_mismatch_and_db_data Ran
ran on a synthesized input
salesforce/simpletod/evaluate_multiwoz.py
code served (permissive licence) · get_code("489b09c8fef69f12")
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 torch

# Construct minimal valid arguments for remove_model_mismatch_and_db_data

dial_name = 'MUL0116.json'

# target_beliefs is a list of dicts indexed by turn number
# Each dict maps domain names to belief state dicts
target_beliefs = [
    {},  # turn 0
    {
        'hotel': {
            'type': 'guesthouse',
            'area': 'centre'
        },
        'restaurant': {
            'name': 'charlie chan',
            'area': 'north'
        }
    },  # turn 1
    {
        'hotel': {
            'type': 'hotel',
            'parking': 'yes'
        },
        'attraction': {
            'name': 'trinity college',
            'type': 'college'
        }
    }   # turn 2
]

# pred_beliefs maps domain names to belief state dicts
pred_beliefs = {
    'hotel': {
        'name': 'lovell lodge',
        'type': 'guesthouse',
        'area': 'centre',
        'parking': 'no'
    },
    'restaurant': {
        'name': 'charlie chan',
        'area': 'north',
        'pricerange': 'cheap'
    },
    'attraction': {
        'name': 'trinity college',
        'type': 'attraction'
    }
}

domain = 'hotel'

t = 1

ARGS = {
    'dial_name': dial_name,
    'target_beliefs': target_beliefs,
    'pred_beliefs': pred_beliefs,
    'domain': domain,
    't': t
}
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 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
top_k_top_p_filtering Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
salesforce/simpletod/models/modeling_utils.py
code served (permissive licence) · get_code("8e873fc150477bd1")
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 2, dtype family float; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:14:48Z. 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 torch.nn.functional as F

torch.manual_seed(0)

# Create small logits tensor: (batch_size=2, vocab_size=4)
logits = torch.randn(2, 4)

# Define ARGS dictionary with all parameters
ARGS = {
    "logits": logits,
    "top_k": 2,
    "top_p": 0.9,
    "filter_value": -float('Inf'),
    "min_tokens_to_keep": 1
}
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 Tensor, ndim 2, dtype family float — no output shape is stated: no later run recorded an output shape for this sample (observed_output and metamorphic_properties carry none; shape_contract and output_contract record ndim only)
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 syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
url_to_filename Ran
ran; our contract draft was wrong, not the code
salesforce/simpletod/models/file_utils.py
code served (permissive licence) · get_code("e827d94caab33f59")
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.

from hashlib import sha256

ARGS = {
    "url": "https://example.com/model.weights",
    "etag": "abc123def456"
}
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
load_tf_weights_in_gpt2 Not yet run
unverified (harvested, no recorded run)
salesforce/simpletod/models/modeling_gpt2.py
code served (permissive licence) · get_code("c4bac98236c1fc2c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 7 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 1 the same month, 7 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.

FunctionAlso present inEarliest-datedOthers named
prune_linear_layer 29 other papers
8 dated earlier, 2 the same month, 18 later, 1 same year, order not determinable
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.08230 (2019-06)
Evaluating Protein Transfer Learning with TAPE
1906.08237 (2019-06)
XLNet: Generalized Autoregressive Pretraining for Language Understanding
and 26 more not named here
top_k_top_p_filtering 21 other papers
1 dated earlier, 20 later
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2009.06367 (2020-09)
GeDi: Generative Discriminator Guided Sequence Generation
2104.04039 (2021-04)
Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes
and 18 more not named here
url_to_filename 12 other papers
2 dated earlier, 10 later
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2004.09297 (2020-04)
MPNet: Masked and Permuted Pre-training for Language Understanding
2009.06978 (2020-09)
Dialogue Response Ranking Training with Large-Scale Human Feedback Data
and 9 more not named here
is_ascii 9 other papers
1 dated earlier, 7 later, 1 same year, order not determinable
1911.08151 (2019-11)
Retrospective and Prospective Mixture-of-Generators for Task-oriented Dialogue Response Generation
2020.acl-main.53 (2020 (year only))
Efficient Dialogue State Tracking by Selectively Overwriting Memory
2101.09374 (2021-01)
Slot Self-Attentive Dialogue State Tracking
and 6 more not named here
hf_bucket_url 8 other papers
2 dated earlier, 6 later
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2004.09297 (2020-04)
MPNet: Masked and Permuted Pre-training for Language Understanding
2009.12719 (2020-09)
Stylized Dialogue Response Generation Using Stylized Unpaired Texts
and 5 more not named here
is_remote_url 7 other papers
2 dated earlier, 5 later
1909.11942 (2019-09)
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
2004.09297 (2020-04)
MPNet: Masked and Permuted Pre-training for Language Understanding
2009.12719 (2020-09)
Stylized Dialogue Response Generation Using Stylized Unpaired Texts
and 4 more not named here
load_tf_weights_in_gpt2 5 other papers
5 later
2009.06367 (2020-09)
GeDi: Generative Discriminator Guided Sequence Generation
2009.12719 (2020-09)
Stylized Dialogue Response Generation Using Stylized Unpaired Texts
2104.04039 (2021-04)
Plug-and-Blend: A Framework for Controllable Story Generation with Blended Control Codes
and 2 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 2026-11-21.

Repositories linked to this paper

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

Abstract

Task-oriented dialogue is often decomposed into three tasks: understanding user input, deciding actions, and generating a response. While such decomposition might suggest a dedicated model for each sub-task, we find a simple, unified approach leads to state-of-the-art performance on the MultiWOZ dataset. SimpleTOD is a simple approach to task-oriented dialogue that uses a single, causal language model trained on all sub-tasks recast as a single sequence prediction problem. This allows SimpleTOD to fully leverage transfer learning from pre-trained, open domain, causal language models such as GPT-2. SimpleTOD improves over the prior state-of-the-art in joint goal accuracy for dialogue state tracking, and our analysis reveals robustness to noisy annotations in this setting. SimpleTOD also improves the main metrics used to evaluate action decisions and response generation in an end-to-end setting: inform rate by 8.1 points, success rate by 9.7 points, and combined score by 7.2 points.

For agents

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

get_harvested_code_for_paper("2005.00796")
get_code_for_paper("2005.00796")
have("2005.00796")

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

curl https://syntology.ai/api/ran/2005.00796.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.00796.svg)](https://syntology.ai/paper/2005.00796)

Connect an agent — have() is free.