SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2010.12812 · 2020

A Frustratingly Easy Approach for Entity and Relation Extraction

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 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/2010.12812.json · badge: /api/ran/2010.12812.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
princeton-nlp/PURE canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
0 ran · 1 no recorded run
FunctionStatusWhere it lives
compute_f1 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
princeton-nlp/PURE/run_relation.py
code served (permissive licence) · get_code("f39c75c8e38877a5")
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 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)

# preds: list of predictions (integers, where 0 means no prediction)
# labels: list of labels (integers, where 0 means no label)
# e2e_ngold: total number of gold labels for end-to-end evaluation (int or None)

preds = [0, 1, 2, 1, 0, 3, 2, 2]
labels = [0, 1, 2, 3, 0, 3, 2, 1]
e2e_ngold = 6

ARGS = {
    'preds': preds,
    'labels': labels,
    'e2e_ngold': e2e_ngold
}
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 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
convert_examples_to_features Ran
ran; our contract draft was wrong, not the code
princeton-nlp/PURE/run_relation.py
code served (permissive licence) · get_code("b4727e3523efb30b")
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 SimpleTokenizer:
    """Minimal tokenizer that implements required methods."""
    def tokenize(self, token):
        # Simple whitespace tokenization, return list of subword tokens
        return token.split() if token else []
    
    def convert_tokens_to_ids(self, tokens):
        # Map tokens to simple integer IDs
        token_to_id = {
            '[CLS]': 101,
            '[SEP]': 102,
            '[unused1]': 1,
            '[unused2]': 2,
            '[unused3]': 3,
            '[unused4]': 4,
            '[unused5]': 5,
            '[unused6]': 6,
            '[unused7]': 7,
            '[unused8]': 8,
            '[unused9]': 9,
            '[unused10]': 10,
            '[unused11]': 11,
            '[unused12]': 12,
        }
        ids = []
        for token in tokens:
            if token in token_to_id:
                ids.append(token_to_id[token])
            else:
                # Hash-based ID for unknown tokens
                ids.append(hash(token) % 1000 + 100)
        return ids

# Create minimal examples
examples = [
    {
        'id': 'ex1',
        'token': ['The', 'cat', 'sat', 'on', 'the', 'mat'],
        'subj_start': 1,
        'subj_end': 1,
        'obj_start': 5,
        'obj_end': 5,
        'subj_type': 'ANIMAL',
        'obj_type': 'LOCATION',
        'relation': 'located_at'
    },
    {
        'id': 'ex2',
        'token': ['John', 'works', 'at', 'Google'],
        'subj_start': 0,
        'subj_end': 0,
        'obj_start': 3,
        'obj_end': 3,
        'subj_type': 'PERSON',
        'obj_type': 'ORGANIZATION',
        'relation': 'works_for'
    }
]

# Create label2id mapping
label2id = {
    'located_at': 0,
    'works_for': 1,
    'no_relation': 2
}

# Create tokenizer
tokenizer = SimpleTokenizer()

# Create special_tokens dict
special_tokens = {}

ARGS = {
    'examples': examples,
    'label2id': label2id,
    'max_seq_length': 32,
    'tokenizer': tokenizer,
    'special_tokens': special_tokens,
    'unused_tokens': True
}
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
evaluate Ran
ran, honoured the contract we drafted
princeton-nlp/PURE/run_entity.py
code served (permissive licence) · get_code("136782e0f93a2faa")
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
import torch.nn as nn
import logging

logging.basicConfig(level=logging.INFO)

torch.manual_seed(0)

class MockModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def run_batch(self, batch, training=False):
        # batch is a list of samples
        # each sample has 'spans_label' key
        # return dict with 'pred_ner' key containing predictions
        batch_size = len(batch)
        # Generate predictions: list of lists of label predictions
        pred_ner = []
        for sample in batch:
            num_spans = len(sample['spans_label'])
            # Predictions are integers (label indices), 0 means no entity
            preds = [i % 3 for i in range(num_spans)]
            pred_ner.append(preds)
        return {'pred_ner': pred_ner}

# Create model
model = MockModel()

# Create batches - each batch is a list of samples
# Each sample has 'spans_label' which is a list of gold labels
batches = [
    [
        {'spans_label': [0, 1, 2, 0]},
        {'spans_label': [1, 1, 0, 2]},
    ],
    [
        {'spans_label': [2, 0, 1]},
        {'spans_label': [0, 1, 2, 1, 0]},
    ]
]

# Total gold entities (non-zero labels in all batches)
tot_gold = 0
for batch in batches:
    for sample in batch:
        for label in sample['spans_label']:
            if label != 0:
                tot_gold += 1

ARGS = {
    'model': model,
    'batches': batches,
    'tot_gold': tot_gold
}
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
simple_accuracy Not yet run
unverified (harvested, no recorded run)
this paper's copy was not recorded; identical code first harvested from ink-usc/expl-refinement
pointer only · get_code("3c241ecfe3749a6d")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 3 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
simple_accuracy 59 other papers
19 dated earlier, 2 the same month, 37 later, 1 same year, order not determinable
1506.05865 (2015-06)
LCSTS: A Large Scale Chinese Short Text Summarization Dataset
1509.01626 (2015-09)
Character-level Convolutional Networks for Text Classification *
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
and 56 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

End-to-end relation extraction aims to identify named entities and extract relations between them. Most recent work models these two subtasks jointly, either by casting them in one structured prediction framework, or performing multi-task learning through shared representations. In this work, we present a simple pipelined approach for entity and relation extraction, and establish the new state-of-the-art on standard benchmarks (ACE04, ACE05 and SciERC), obtaining a 1.7%-2.8% absolute improvement in relation F1 over previous joint models with the same pre-trained encoders. Our approach essentially builds on two independent encoders and merely uses the entity model to construct the input for the relation model. Through a series of careful examinations, we validate the importance of learning distinct contextual representations for entities and relations, fusing entity information early in the relation model, and incorporating global context. Finally, we also present an efficient approximation to our approach which requires only one pass of both entity and relation encoders at inference time, achieving an 8-16$\times$ speedup with a slight reduction in accuracy.

For agents

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

get_harvested_code_for_paper("2010.12812")
get_code_for_paper("2010.12812")
have("2010.12812")

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

curl https://syntology.ai/api/ran/2010.12812.json

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

[![Syntology run record](https://syntology.ai/api/ran/2010.12812.svg)](https://syntology.ai/paper/2010.12812)

Connect an agent — have() is free.