SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.14898 · 2023

PIVOINE: Instruction Tuning for Open-world Information Extraction

arXiv · PDF · Open in the Atlas

Code that ran

2 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; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 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/2305.14898.json · badge: /api/ran/2305.14898.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
lukeming-tsinghua/instruction-tuning-for-open-world-ie canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
augmentation Ran
ran on a synthesized input
lukeming-tsinghua/instruction-tuning-for-open-world-ie/processed_pretrained_data/augment_utils.py
code served (permissive licence) · get_code("38cb4bd179a0bf91")
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 function. 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 json
import copy

def sample_augmentation_func(entities, triplets, **kwargs):
    """A sample augmentation function that returns modified entities, triplets, prompt, and aug_infos"""
    # Simple augmentation: return the entities and triplets as-is with metadata
    new_entities = entities
    new_triplets = triplets
    prompt = "Sample augmentation prompt"
    aug_infos = {"augmented": True, "count": len(entities)}
    return new_entities, new_triplets, prompt, aug_infos

def func(record, **kwargs):
    """The decorated function to be tested"""
    record = copy.deepcopy(record)
    targets = json.loads(record['targets'])
    entities = targets['entities']
    triplets = targets['triplets']
    aug_sample = sample_augmentation_func(entities, triplets, **kwargs)
    if not aug_sample:
        return
    new_entities, new_triplets, prompt, aug_infos = aug_sample
    targets['entities'] = new_entities
    targets['triplets'] = new_triplets
    record['targets'] = json.dumps(targets)
    record['inputs'] = record['inputs']
    record['prompt'] = prompt
    record['aug_type'] = sample_augmentation_func.__name__
    record['aug_info'] = aug_infos
    return record

# Construct valid arguments for the augmentation function
ARGS = {
    'func': sample_augmentation_func,
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
transform Ran
ran on a synthesized input
lukeming-tsinghua/instruction-tuning-for-open-world-ie/processed_pretrained_data/preprocess_func.py
code served (permissive licence) · get_code("ba169667bd0928d0")
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 json
from collections import defaultdict, OrderedDict

# Construct a sample that matches the expected structure
sample = {
    'id': 'sample_1',
    'title': 'Sample Title',
    'cleaned_text': ['This', 'is', 'a', 'sample', 'text'],
    'ents': [
        [
            {
                'mention': 'Apple',
                'title': 'Apple Inc.',
                'type': 'Company',
                'description': {'english': 'A technology company'},
                'aliases': {'english': ['AAPL', 'Apple Computer']}
            },
            {
                'mention': 'Steve Jobs',
                'title': 'Steven Paul Jobs',
                'type': 'Person',
                'description': {'english': 'Co-founder of Apple'},
                'aliases': {'english': ['Jobs']}
            }
        ]
    ],
    'triplets': [
        {
            'head': {'mention': 'Steve Jobs'},
            'tail': {'mention': 'Apple'},
            'relations': [{'title': 'founded'}]
        }
    ],
    'n_ents': 2
}

ARGS = {
    'sample': sample,
    'key_map': {'text': 'mention', 'mention': 'mention', 'title': 'title', 'type': 'type', 'description': 'description', 'aliases': 'aliases'},
    'add_ent_num': False
}
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 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
aug_default Not yet run
unverified (harvested, no recorded run)
lukeming-tsinghua/instruction-tuning-for-open-world-ie/processed_pretrained_data/augment_utils.py
code served (permissive licence) · get_code("cdbbe8bc4084f31a")
How it ran

no invocation recorded.

aug_ent_num Not yet run
unverified (harvested, no recorded run)
lukeming-tsinghua/instruction-tuning-for-open-world-ie/processed_pretrained_data/augment_utils.py
code served (permissive licence) · get_code("66dd6517939f44a3")
How it ran

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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

We consider the problem of Open-world Information Extraction (Open-world IE), which extracts comprehensive entity profiles from unstructured texts. Different from the conventional closed-world setting of Information Extraction (IE), Open-world IE considers a more general situation where entities and relations could be beyond a predefined ontology. More importantly, we seek to develop a large language model (LLM) that is able to perform Open-world IE to extract desirable entity profiles characterized by (possibly fine-grained) natural language instructions. We achieve this by finetuning LLMs using instruction tuning. In particular, we construct INSTRUCTOPENWIKI, a substantial instruction tuning dataset for Open-world IE enriched with a comprehensive corpus, extensive annotations, and diverse instructions. We finetune the pretrained BLOOM models on INSTRUCTOPENWIKI and obtain PIVOINE, an LLM for Open-world IE with strong instruction-following capabilities. Our experiments demonstrate that PIVOINE significantly outperforms traditional closed-world methods and other LLM baselines, displaying impressive generalization capabilities on both unseen instructions and out-of-ontology cases. Consequently, PIVOINE emerges as a promising solution to tackle the open-world challenge in IE effectively.

For agents

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

get_harvested_code_for_paper("2305.14898")
get_code_for_paper("2305.14898")
have("2305.14898")

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

curl https://syntology.ai/api/ran/2305.14898.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.14898.svg)](https://syntology.ai/paper/2305.14898)

Connect an agent — have() is free.