SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.10033 · 2019

Personalizing Dialogue Agents via Meta-Learning

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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; 4 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 1 failure of our instrument; 1 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/1905.10033.json · badge: /api/ran/1905.10033.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
HLTCHKUST/PAML canonical (classifier label)
classifier basis: census
11 ran · 1 no recorded run
FunctionStatusWhere it lives
DistJaccard Ran
ran on a synthesized input
HLTCHKUST/PAML/utils/data_reader.py
code served (permissive licence) · get_code("1ef5d5f71be92207")
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

def DistJaccard(str1, str2):
    str1 = set(str1.split())
    str2 = set(str2.split())
    return float(len(str1 & str2)) / len(str1 | str2)

ARGS = {
    "str1": "hello world foo bar",
    "str2": "hello world baz qux"
}
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
accuracy Ran
ran, honoured the contract we drafted
HLTCHKUST/PAML/utils/load_bert.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
convert_examples_to_features Ran
ran; our contract draft was wrong, not the code
HLTCHKUST/PAML/utils/load_bert.py
code served (permissive licence) · get_code("b3feaffc79a790e6")
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 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 logging

logging.basicConfig(level=logging.INFO)

class MockExample:
    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

class MockTokenizer:
    def __init__(self):
        self.vocab = {
            '[CLS]': 101,
            '[SEP]': 102,
            'hello': 1,
            'world': 2,
            'this': 3,
            'is': 4,
            'a': 5,
            'test': 6,
            'example': 7,
            'text': 8,
        }
    
    def tokenize(self, text):
        if text is None:
            return []
        return text.lower().split()
    
    def convert_tokens_to_ids(self, tokens):
        return [self.vocab.get(token, 0) for token in tokens]

examples = [
    MockExample(guid='0', text_a='hello world', text_b='this is test', label='positive'),
    MockExample(guid='1', text_a='example text', text_b=None, label='negative'),
]

label_list = ['positive', 'negative']
max_seq_length = 16
tokenizer = MockTokenizer()

ARGS = {
    'examples': examples,
    'label_list': label_list,
    'max_seq_length': max_seq_length,
    'tokenizer': tokenizer,
}
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 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
create_str_array Ran
ran on a synthesized input
HLTCHKUST/PAML/utils/data_reader.py
code served (permissive licence) · get_code("43a77a0fee1c78c9")
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
import torch.utils.data as data

torch.manual_seed(0)

# Analyze the function:
# - Takes a parameter 'data' which is a dict
# - Iterates over data.items() -> needs dict with key-value pairs
# - For each v in data.values(): accesses v[0][0] which should be iterable (joined with ' ')
# - v[0] is indexed, so v is a sequence/list
# - v[0][0] is a sequence of strings (joined with ' ')

# Construct the data dict with appropriate structure
data_dict = {
    'key1': [
        [['hello', 'world', 'test']],  # v[0][0] is a list of strings
    ],
    'key2': [
        [['foo', 'bar']],  # v[0][0] is a list of strings
    ],
    'key3': [
        [['alpha', 'beta', 'gamma', 'delta']],  # v[0][0] is a list of strings
    ],
}

ARGS = {
    'data': data_dict
}
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
dist_matrix Ran
ran on a synthesized input
HLTCHKUST/PAML/utils/data_reader.py
code served (permissive licence) · get_code("65035f6a4a984f2e")
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 2, 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 numpy as np

# The function dist_matrix takes array_str as parameter
# array_str is iterated over with enumerate and each element s_r and s_c is passed to DistJaccard
# DistJaccard expects strings that can be split by whitespace
# So array_str should be a list/array of strings

ARGS = {
    "array_str": [
        "hello world test",
        "hello foo bar",
        "test data science"
    ]
}
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 list, ndim 2, 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
dup_batch Ran
ran on a synthesized input
HLTCHKUST/PAML/utils/beam_ptr.py
code served (permissive licence) · get_code("7174231a087096c0")
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

torch.manual_seed(0)

# Create a minimal batch dictionary that satisfies the function's requirements
batch = {
    'input_batch': torch.randn(5, 2),  # [seq_len=5, batch_size=2]
    'target_batch': torch.randn(5, 2),  # [seq_len=5, batch_size=2]
    'input_ext_vocab_batch': torch.randn(5, 2),  # [seq_len=5, batch_size=2]
    'target_ext_vocab_batch': torch.randn(5, 2),  # [seq_len=5, batch_size=2]
    'article_oovs': [['oov1', 'oov2'], ['oov3']],  # list of oov lists for each batch item
    'max_art_oovs': 3,  # scalar
    'input_txt': ['input text 0', 'input text 1'],  # list of strings
    'target_txt': ['target text 0', 'target text 1'],  # list of strings
    'input_lengths': torch.tensor([4, 3]),  # [batch_size=2]
    'target_lengths': torch.tensor([4, 3]),  # [batch_size=2]
}

# Parameters for the function
idx = 0  # index into the batch dimension
dup_times = 3  # number of times to duplicate

ARGS = {
    'batch': batch,
    'idx': idx,
    'dup_times': dup_times,
}
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
position_encoding Ran
ran, honoured the contract we drafted
HLTCHKUST/PAML/model/common_layer.py
code served (permissive licence) · get_code("e6dc8a206c0c47a8")
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 ndarray, ndim 2, dtype family float, shape (10, 8) 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

ARGS = {
    "sentence_size": 10,
    "embedding_dim": 8,
}
Setup block drafted by
a language model, Claude Haiku 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 ndarray, ndim 2, dtype family float, shape (10, 8) — shape (10, 8) 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
rouge_n Ran
ran, honoured the contract we drafted
HLTCHKUST/PAML/utils/metric.py
code served (permissive licence) · get_code("ee28f00102414dc1")
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, 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 itertools

# Define small stand-in data for the rouge_n function
evaluated_sentences = [
    "the cat sat on the mat",
    "a dog ran in the park"
]

reference_sentences = [
    "the cat is on the mat",
    "the dog ran through the park"
]

n = 2

ARGS = {
    "evaluated_sentences": evaluated_sentences,
    "reference_sentences": reference_sentences,
    "n": n
}
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 tuple, ndim 1, dtype family float — a tuple 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
sequence_mask Ran
ran on a synthesized input
HLTCHKUST/PAML/utils/beam_omt.py
code served (permissive licence) · get_code("414d6410e1b754b0")
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, shape (2, 3) 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

torch.manual_seed(0)

# sequence_mask expects:
# - sequence_length: a tensor with .data, .size(0), .is_cuda, .unsqueeze()
# - max_len: optional int or None

# Create a small batch of sequence lengths
sequence_length = torch.tensor([3, 2], dtype=torch.long)

ARGS = {
    "sequence_length": sequence_length,
    "max_len": None
}
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, shape (2, 3) — shape (2, 3) 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
warmup_linear Ran
ran, honoured the contract we drafted
HLTCHKUST/PAML/utils/load_bert.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
wer Ran
ran on a synthesized input
HLTCHKUST/PAML/utils/metric.py
code served (permissive licence) · get_code("65dff947bbcbac08")
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 numpy

# The wer function takes two parameters: r and h
# Both should be sequences (lists) of words/tokens
# r is the reference (ground truth) sequence
# h is the hypothesis (predicted) sequence
# The function implements edit distance (Levenshtein distance) to calculate WER

ARGS = {
    "r": "what is it".split(),  # reference: ["what", "is", "it"]
    "h": "what is".split(),      # hypothesis: ["what", "is"]
}
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 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
moses_multi_bleu Not yet run
unverified (harvested, no recorded run)
HLTCHKUST/PAML/utils/metric.py
code served (permissive licence) · get_code("ba2c0325e50bd0b8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 8 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 8 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
accuracy 21 other papers
5 dated earlier, 2 the same month, 14 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
warmup_linear 19 other papers
5 dated earlier, 14 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
position_encoding 5 other papers
5 later
1908.07687 (2019-08)
MoEL: Mixture of Empathetic Listeners
2003.12738 (2020-03)
Variational Transformers for Diverse Response Generation
2010.01454 (2020-10)
MIME: MIMicking Emotions for Empathetic Response Generation
and 2 more not named here
rouge_n 5 other papers
1 dated earlier, 4 later
1805.09461 (2018-05)
Deep Reinforcement Learning For Sequence to Sequence Models
1908.07687 (2019-08)
MoEL: Mixture of Empathetic Listeners
2020.findings-emnlp.289 (2020 (year only))
Towards Zero-Shot Conditional Summarization with Adaptive Multi-Task Fine-Tuning
and 2 more not named here
convert_examples_to_features 3 other papers
3 later
1909.02635 (2019-09)
Effective Use of Transformer Networks for Entity Tracking
1910.14659 (2019-10)
Masked Language Model Scoring
2001.00137 (2020-01)
Stacked DeBERT: All Attention in Incomplete Data for Text Classification
sequence_mask 3 other papers
3 later
1908.07687 (2019-08)
MoEL: Mixture of Empathetic Listeners
2003.12738 (2020-03)
Variational Transformers for Diverse Response Generation
2010.01454 (2020-10)
MIME: MIMicking Emotions for Empathetic Response Generation
wer 3 other papers
2 dated earlier, 1 later
1804.08217 (2018-04)
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems
1901.04713 (2019-01)
Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
1908.07687 (2019-08)
MoEL: Mixture of Empathetic Listeners
moses_multi_bleu 1 other paper
1 later
1908.07687 (2019-08)
MoEL: Mixture of Empathetic Listeners

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 personalized dialogue models use human designed persona descriptions to improve dialogue consistency. Collecting such descriptions from existing dialogues is expensive and requires hand-crafted feature designs. In this paper, we propose to extend Model-Agnostic Meta-Learning (MAML)(Finn et al., 2017) to personalized dialogue learning without using any persona descriptions. Our model learns to quickly adapt to new personas by leveraging only a few dialogue samples collected from the same user, which is fundamentally different from conditioning the response on the persona descriptions. Empirical results on Persona-chat dataset (Zhang et al., 2018) indicate that our solution outperforms non-meta-learning baselines using automatic evaluation metrics, and in terms of human-evaluated fluency and consistency.

For agents

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

get_harvested_code_for_paper("1905.10033")
get_code_for_paper("1905.10033")
have("1905.10033")

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

curl https://syntology.ai/api/ran/1905.10033.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.10033.svg)](https://syntology.ai/paper/1905.10033)

Connect an agent — have() is free.