SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2607.01023 · 2026

Evidence-Supported Credit Risk Report Generation Using News-Centric Financial Knowledge Graph

Ying Chen, Ziwei Xu, Ryutaro Ichise, Oscar Araque, Rocío Jiménez-Villén

arXiv · PDF

Code that ran

3 of 3 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; 0 no recorded run), measured 2026-11-22; 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/2607.01023.json · badge: /api/ran/2607.01023.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
ichise-laboratory/FINKG-news canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
format_events Ran
ran; our contract draft was wrong, not the code
ichise-laboratory/FINKG-news/FinKG-News-Framework/2.1-run_event_detection.py
code served (permissive licence) · get_code("4999330ace30caa0")
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

# Create sample events data
events = [
    {
        'event_type': 'user_login',
        'timestamp': '2024-01-15T10:30:00',
        'user_id': 123,
        'status': 'success'
    },
    {
        'event_type': 'data_fetch',
        'timestamp': '2024-01-15T10:31:15',
        'records': 42,
        'duration_ms': 250
    }
]

ARGS = {
    'events': events
}
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
get_event_chunks Ran
ran, honoured the contract we drafted
ichise-laboratory/FINKG-news/FinKG-News-Framework/2.1-run_event_detection.py
code served (permissive licence) · get_code("ad8a0bcae454c4dc")
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.

# First, let's populate the global events list that the function uses
events = [
    {'event_id': '2015_event_001', 'name': 'Event 1'},
    {'event_id': '2016_event_002', 'name': 'Event 2'},
    {'event_id': '2017_event_003', 'name': 'Event 3'},
    {'event_id': '2018_event_004', 'name': 'Event 4'},
    {'event_id': '2019_event_005', 'name': 'Event 5'},
    {'event_id': '2020_event_006', 'name': 'Event 6'},
    {'event_id': '2021_event_007', 'name': 'Event 7'},
    {'event_id': '2022_event_008', 'name': 'Event 8'},
    {'event_id': '2023_event_009', 'name': 'Event 9'},
    {'event_id': '2024_event_010', 'name': 'Event 10'},
]

event_chunk_size = 20

def get_event_chunks(news_year, event_chunk_size=20):
    events_filtered = [event for event in events if int(event['event_id'].split('_')[0]) <= int(news_year)]
    chunk_size = 20
    event_list_chunks = [events_filtered[i:i + event_chunk_size] for i in range(0, len(events_filtered), chunk_size)]
    return event_list_chunks

# Define ARGS with all parameters
ARGS = {
    'news_year': '2020',
    'event_chunk_size': 20
}
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 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_system_prompt Ran
ran; our contract draft was wrong, not the code
ichise-laboratory/FINKG-news/FinKG-News-Framework/2.1-run_event_detection.py
code served (permissive licence) · get_code("bacadcaa2c825138")
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
import numpy as np

# Construct valid arguments for get_system_prompt function
# The function takes 'events' parameter which should be a list of event dictionaries

events = [
    {
        "event_id": "2023_27",
        "event": "Somalia admitted to East African Community.",
        "date": "2023-04-16",
        "region": "Africa"
    },
    {
        "event_id": "2023_12",
        "event": "2023 Ecuadorian political crisis.",
        "date": "2023-01-09",
        "region": "South America"
    },
    {
        "event_id": "2023_08",
        "event": "Turkey-Syria earthquakes kill thousands.",
        "date": "2023-02-06",
        "region": "Middle East"
    },
    {
        "event_id": "2023_15",
        "event": "Ukraine receives main battle tanks from Western allies.",
        "date": "2023-01-25",
        "region": "Europe"
    },
    {
        "event_id": "2023_20",
        "event": "ChatGPT released to public.",
        "date": "2022-11-30",
        "region": "Global"
    },
    {
        "event_id": "2023_01",
        "event": "Israel-Hamas war begins.",
        "date": "2023-10-07",
        "region": "Middle East"
    }
]

ARGS = {
    "events": events
}
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 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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 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.

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

Financial markets evolve in response to real-world events reported in news, yet these drivers often remain implicit in text. To better explain market dynamics, event-market relations must be explicitly modeled through factual, company-centric, and environment-aware knowledge graphs. We present FinKG-News, a framework that automatically constructs such graphs by extracting news events as anchors linked to companies. Using FinKG-News as grounded evidence that integrates events, news, and company data, we develop an in-context learning architecture for credit risk report generation across three core financial dimensions. Automatic and human evaluations show that automated hallucination detection and quality assessment remain unreliable, making expert judgment indispensable. Our approach consistently outperforms baselines, improving quality by 19%-34% while reducing hallucinations. The source code and project resources are publicly available at: https://github.com/ichise-laboratory/FINKG-news.

For agents

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

get_harvested_code_for_paper("2607.01023")
get_code_for_paper("2607.01023")
have("2607.01023")

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

curl https://syntology.ai/api/ran/2607.01023.json

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

[![Syntology run record](https://syntology.ai/api/ran/2607.01023.svg)](https://syntology.ai/paper/2607.01023)

Connect an agent — have() is free.