SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.03598 · 2021

SciFive: a text-to-text transformer model for biomedical literature

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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 4 have no contract verdict; 1 failure 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/2106.03598.json · badge: /api/ran/2106.03598.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
justinphan3110/SciFive canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran on a synthesized input
justinphan3110/SciFive/biot5x/src/metrics.py
code served (permissive licence) · get_code("1be5efa4c923f993")
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 sklearn.metrics
import numpy as np

torch_manual_seed = 0

# Create simple targets and predictions for accuracy calculation
# targets: true labels (1D array)
# predictions: predicted labels (1D array)

targets = np.array([0, 1, 1, 0, 1, 0])
predictions = np.array([0, 1, 0, 0, 1, 1])

ARGS = {
    'targets': targets,
    'predictions': predictions
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
dot_product_attention Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
justinphan3110/SciFive/biot5x/configs/t5/layers.py
code served (permissive licence) · get_code("dac0288079ac279f")
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 ArrayImpl, ndim 4, dtype family float, shape (2, 3, 2, 6) 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 jax
import jax.numpy as jnp
from jax import random

# Set seed for reproducibility
key = random.PRNGKey(0)

# Dimensions
batch = 2
q_length = 3
kv_length = 4
num_heads = 2
qk_depth_per_head = 5
v_depth_per_head = 6

# Create query, key, value tensors with distinct sizes
query = jnp.ones((batch, q_length, num_heads, qk_depth_per_head), dtype=jnp.float32)
key = jnp.ones((batch, kv_length, num_heads, qk_depth_per_head), dtype=jnp.float32)
value = jnp.ones((batch, kv_length, num_heads, v_depth_per_head), dtype=jnp.float32)

# Create bias (optional) - broadcastable to [batch, num_heads, q_length, kv_length]
bias = jnp.zeros((batch, num_heads, q_length, kv_length), dtype=jnp.float32)

# Generate dropout RNG key
dropout_rng = random.PRNGKey(1)

# Define arguments
ARGS = {
    "query": query,
    "key": key,
    "value": value,
    "bias": bias,
    "dropout_rng": dropout_rng,
    "dropout_rate": 0.1,
    "deterministic": False,
    "dtype": jnp.float32,
    "float32_logits": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 4, dtype family float, shape (2, 3, 2, 6) — shape (2, 3, 2, 6) 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
f1 Ran
ran on a synthesized input
justinphan3110/SciFive/biot5x/src/metrics.py
code served (permissive licence) · get_code("12ff36b88687dd69")
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
import sklearn.metrics

torch.manual_seed(0)

# For f1_score, we need:
# - targets: array-like of true labels
# - predictions: array-like of predicted labels
# - average: str parameter for the averaging method

# Create small multi-class classification data
# 5 samples, 3 classes
targets = np.array([0, 1, 2, 0, 1])
predictions = np.array([0, 1, 1, 0, 1])

ARGS = {
    'targets': targets,
    'predictions': predictions,
    'average': 'micro'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, 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
make_attention_mask Ran
ran on a synthesized input
justinphan3110/SciFive/biot5x/configs/t5/layers.py
code served (permissive licence) · get_code("1184cae8ca10c644")
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 ArrayImpl, ndim 4, dtype family float, shape (2, 1, 3, 2) 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 jax.numpy as jnp

# Create small query and key input arrays
# query_input shape: [batch, len_q]
query_input = jnp.array([[1.0, 2.0, 3.0],
                         [4.0, 5.0, 6.0]])  # shape: (2, 3)

# key_input shape: [batch, len_kv]
key_input = jnp.array([[1.0, 2.0],
                       [3.0, 4.0]])  # shape: (2, 2)

# Pairwise function - using jnp.multiply as default
pairwise_fn = jnp.multiply

# Extra batch dims
extra_batch_dims = 0

# Data type
dtype = jnp.float32

ARGS = {
    "query_input": query_input,
    "key_input": key_input,
    "pairwise_fn": pairwise_fn,
    "extra_batch_dims": extra_batch_dims,
    "dtype": dtype
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 4, dtype family float, shape (2, 1, 3, 2) — shape (2, 1, 3, 2) 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
make_causal_mask Ran
ran on a synthesized input
justinphan3110/SciFive/biot5x/configs/t5/layers.py
code served (permissive licence) · get_code("94c13ffc5f28dfba")
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 ArrayImpl, ndim 4, dtype family float, shape (2, 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 jax.numpy as jnp

# Create a small input array for make_causal_mask
# Shape: [batch, len] where batch=2, len=4
x = jnp.ones((2, 4), dtype=jnp.float32)

# Define all parameters for make_causal_mask
ARGS = {
    "x": x,
    "extra_batch_dims": 0,
    "dtype": jnp.float32,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ArrayImpl, ndim 4, dtype family float, shape (2, 1, 4, 4) — shape (2, 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

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 2 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
dot_product_attention 5 other papers
5 later
2112.00791 (2021-12)
Controlling Conditional Language Models without Catastrophic Forgetting
2206.05408 (2022-06)
Multi-instrument Music Synthesis with Spectrogram Diffusion
2212.04356 (2022-12)
Robust Speech Recognition via Large-Scale Weak Supervision
and 2 more not named here
make_attention_mask 2 other papers
2 later
2112.00791 (2021-12)
Controlling Conditional Language Models without Catastrophic Forgetting
2206.05408 (2022-06)
Multi-instrument Music Synthesis with Spectrogram Diffusion
make_causal_mask 1 other paper
1 later
2112.00791 (2021-12)
Controlling Conditional Language Models without Catastrophic Forgetting

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 this report, we introduce SciFive, a domain-specific T5 model that has been pre-trained on large biomedical corpora. Our model outperforms the current SOTA methods (i.e. BERT, BioBERT, Base T5) on tasks in named entity relation, relation extraction, natural language inference, and question-answering. We show that text-generation methods have significant potential in a broad array of biomedical NLP tasks, particularly those requiring longer, more complex outputs. Our results support the exploration of more difficult text generation tasks and the development of new methods in this area

For agents

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

get_harvested_code_for_paper("2106.03598")
get_code_for_paper("2106.03598")
have("2106.03598")

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

curl https://syntology.ai/api/ran/2106.03598.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.03598.svg)](https://syntology.ai/paper/2106.03598)

Connect an agent — have() is free.