SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2607.17849 · 2026

AlphaOracle: Oracle bone script decipherment via human-workflow-inspired deep learning

Xiang Bai, Pengjie Wang, Yuliang Liu, Xinyu Wang, Lianwen Jin, Haisu Guan, Huanxin Yang, Yongge Liu, Xingchen Liu, Kaile Zhang, Jinpeng Wan, Handong Zheng, and 2 more

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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 1 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/2607.17849.json · badge: /api/ran/2607.17849.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
Yuliang-Liu/AlphaOracle canonical (classifier label)
classifier basis: census
11 ran · 1 no recorded run
FunctionStatusWhere it lives
Normalize Ran
ran; our contract draft was wrong, not the code
Yuliang-Liu/AlphaOracle/models/Morphological_analysis/OBSD/unet.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Xingyu-Zheng/BiDM, is pointer only (licence: NONE) · get_code("c3a6b977022957cb")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Xingyu-Zheng/BiDM, and GitHub detected no licence in that repository when it was checked. 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. A run is recorded.

adjust_learning_rate Ran
ran, honoured the contract we drafted
Yuliang-Liu/AlphaOracle/models/Morphological_analysis/OBSD/OBSD_utils/lr_sched.py
code served (permissive licence) · get_code("3a774664bfc712ec")
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 torch.nn as nn
import torch.optim as optim

torch.manual_seed(0)

# Create a small model to optimize
model = nn.Linear(4, 2)

# Create an optimizer
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Add a parameter group with lr_scale to test that code path
optimizer.add_param_group({'params': [nn.Parameter(torch.randn(3, 4))], 'lr_scale': 0.5})

# Create args dict with all required parameters
ARGS = {
    'optimizer': optimizer,
    'epoch': 5,
    'args': type('Args', (), {
        'warmup_epochs': 2,
        'epochs': 10,
        'lr': 0.1,
        'min_lr': 0.001,
        'lr_schedule': 'cosine'
    })()
}
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 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
calculate_psnr Ran
ran; our contract draft was wrong, not the code
Yuliang-Liu/AlphaOracle/models/Rubbing_parsing/ConversionDiT/evaluate_tokenizer.py
code served (permissive licence) · get_code("7890f73a78eea59b")
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

torch.manual_seed(0)

# Create two small tensors representing original and processed images
# Both should have the same shape for the subtraction operation
original = torch.randint(0, 256, (2, 4), dtype=torch.float32)
processed = torch.randint(0, 256, (2, 4), dtype=torch.float32)

ARGS = {
    "original": original,
    "processed": processed,
}
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 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
content_sha1 Ran
ran; our contract draft was wrong, not the code
Yuliang-Liu/AlphaOracle/models/Philological_Grounding/ingest_cli.py
code served (permissive licence) · get_code("e91c9421be7fbab9")
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 hashlib

def content_sha1(text: str) -> str:
    return hashlib.sha1((text or '').encode('utf-8')).hexdigest()

ARGS = {
    'text': 'Hello, World!'
}
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 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
data_transform Ran
ran, honoured the contract we drafted
Yuliang-Liu/AlphaOracle/models/Morphological_analysis/OBSD/ddm.py
code served (permissive licence) · get_code("1711055882a8cb05")
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, 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 torch
import numpy as np

torch.manual_seed(0)

# Create a small tensor as input
X = torch.tensor([[1.0, 2.0, 3.0, 4.0],
                   [5.0, 6.0, 7.0, 8.0]])

ARGS = {
    "X": X
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
encode_images Ran
ran; our contract draft was wrong, not the code
Yuliang-Liu/AlphaOracle/models/Rubbing_parsing/ConversionDiT/evaluate_tokenizer.py
code served (permissive licence) · get_code("381ca8cdd4eb322a")
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, 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a minimal model that supports the encode interface
class MockVAE(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 8)
    
    def encode(self, images):
        # Return a distribution-like object with a sample() method
        return MockPosterior()

class MockPosterior:
    def sample(self):
        # Return a tensor with shape matching expected latent dimensions
        return torch.randn(2, 4, dtype=torch.float32)

class MockLatentDist:
    def sample(self):
        return torch.randn(2, 4, dtype=torch.float32)

class MockSDVAE(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 8)
    
    def encode(self, images):
        # Return an object with latent_dist attribute
        result = type('obj', (object,), {'latent_dist': MockLatentDist()})()
        return result

# Create test data
model = MockVAE()
images = torch.randn(2, 3, 4, 4)  # batch=2, channels=3, height=4, width=4

ARGS = {
    'model': model,
    'images': images,
    'model_type': 'vavae'
}
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, 4) — shape (2, 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
get_timestep_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Yuliang-Liu/AlphaOracle/models/Morphological_analysis/OBSD/unet.py
code served (permissive licence) · get_code("ff5184c0617d7735")
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, 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 torch
import math

torch.manual_seed(0)

# Construct arguments for get_timestep_embedding
timesteps = torch.tensor([0, 5], dtype=torch.int64)  # batch size 2
embedding_dim = 4  # small even dimension

ARGS = {
    "timesteps": timesteps,
    "embedding_dim": embedding_dim,
}
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, 4) — shape (2, 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
inverse_data_transform Ran
ran; our contract draft was wrong, not the code
Yuliang-Liu/AlphaOracle/models/Morphological_analysis/OBSD/ddm.py
code served (permissive licence) · get_code("444601dceca73c5e")
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, 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 torch

torch.manual_seed(0)

# The function takes a tensor X and applies a transformation
# It clamps the result of (X + 1.0) / 2.0 to the range [0.0, 1.0]
# X should be a tensor

X = torch.randn(2, 4)

ARGS = {
    "X": X
}
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, 4) — shape (2, 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
load_checkpoint Ran
ran, honoured the contract we drafted
Yuliang-Liu/AlphaOracle/models/Morphological_analysis/OBSD/OBSD_utils/logging.py
code served (permissive licence) · get_code("60c85826a345d8ed")
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, 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 torch
import tempfile
import os

torch.manual_seed(0)

# Create a temporary checkpoint file
temp_dir = tempfile.mkdtemp()
checkpoint_path = os.path.join(temp_dir, "model.pt")

# Create a simple tensor and save it as a checkpoint
sample_tensor = torch.randn(2, 4)
torch.save(sample_tensor, checkpoint_path)

# Define arguments for load_checkpoint
ARGS = {
    "path": checkpoint_path,
    "device": 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, 4) — shape (2, 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
load_config Ran
ran; our contract draft was wrong, not the code
Yuliang-Liu/AlphaOracle/models/Rubbing_parsing/ConversionDiT/inference.py
code served (permissive licence) · get_code("e4e95e8e9e7f2e5f")
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 os
import tempfile
import yaml
import torch

torch.manual_seed(0)

# Create a temporary YAML config file
temp_dir = tempfile.mkdtemp()
config_path = os.path.join(temp_dir, "config.yaml")

# Write a sample YAML config file
sample_config = {
    "model": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 10,
    "layers": [64, 128, 256]
}

with open(config_path, 'w') as f:
    yaml.dump(sample_config, f)

ARGS = {
    "config_path": config_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, yaml — 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
nonlinearity Ran
ran; our contract draft was wrong, not the code
Yuliang-Liu/AlphaOracle/models/Morphological_analysis/OBSD/unet.py
code served (permissive licence) · get_code("3137073275f8c21a")
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 Tensor, ndim 2, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# The function takes a single parameter 'x' which is used with:
# - multiplication operator (*)
# - torch.sigmoid() function
# This means x should be a tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
decode_to_images Not yet run
unverified (harvested, no recorded run)
Yuliang-Liu/AlphaOracle/models/Rubbing_parsing/ConversionDiT/evaluate_tokenizer.py
code served (permissive licence) · get_code("39b0e822d5931da6")
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 (8 with at least one paper dated earlier, 2 the same month, 1 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
nonlinearity 156 other papers
155 dated earlier, 1 the same month · 25 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 153 more not named here
get_timestep_embedding 91 other papers
89 dated earlier, 1 the same month, 1 later · 7 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 88 more not named here
Normalize 90 other papers
90 dated earlier · 32 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 87 more not named here
data_transform 4 other papers
4 dated earlier
2207.14626 (2022-07)
Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models
2306.00306 (2023-06)
Low-Light Image Enhancement with Wavelet-based Diffusion Models
2406.00684 (2024-06)
Deciphering Oracle Bone Language with Diffusion Models
and 1 more not named here
inverse_data_transform 4 other papers
4 dated earlier
2207.14626 (2022-07)
Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models
2306.00306 (2023-06)
Low-Light Image Enhancement with Wavelet-based Diffusion Models
2406.00684 (2024-06)
Deciphering Oracle Bone Language with Diffusion Models
and 1 more not named here
adjust_learning_rate 3 other papers
3 dated earlier
2502.17437 (2025-02)
Fractal Generative Models
2503.10568 (2025-03)
Autoregressive Image Generation with Randomized Parallel Decoding
2605.27102 (2026-05)
JLT: Clean-Latent Prediction in Latent Diffusion Transformers
load_checkpoint 3 other papers
3 dated earlier
2207.14626 (2022-07)
Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models
2306.00306 (2023-06)
Low-Light Image Enhancement with Wavelet-based Diffusion Models
2407.08939 (2024-07)
LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models
load_config 1 other paper
1 dated earlier
2510.00685 (2025-10)
Stochastic Self-Organization in Multi-Agent Systems

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

Approximately 3,000 of the 4,500 oracle bone script (OBS) characters remain undeciphered due to fragmentary inscriptions and sparse evidence. Current AI approaches fail to replicate expert workflows that integrate form analysis, contextual semantics, and philological reasoning. We introduce AlphaOracle, a human-workflow-inspired framework that systematizes OBS decipherment using the largest digitized corpus to date. Its multi-stage pipeline comprises: (i) rubbing parsing; (ii) radical-based morphological analysis with diachronic modeling; (iii) contextual retrieval with semantic alignment; and (iv) philological validation against classical sources. Each stage generates explicit, confidence-weighted evidence chains, culminating in interpretable reports for scholarly verification. Across multiple test characters, AlphaOracle's readings strongly agreed with expert interpretations. In a study of 86 domain specialists, it reduced analysis time by 64% and 79% of participants rated it highly useful. Notably, AlphaOracle resolves the character "勞" as a toponymic or clan designation, offering concrete revisions to Shang administrative and social interpretations. These results suggest that computational methods aligned with philological practice can facilitate OBS research and provide a conceptual reference for studies of other undeciphered scripts.

For agents

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

get_harvested_code_for_paper("2607.17849")
get_code_for_paper("2607.17849")
have("2607.17849")

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

curl https://syntology.ai/api/ran/2607.17849.json

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

[![Syntology run record](https://syntology.ai/api/ran/2607.17849.svg)](https://syntology.ai/paper/2607.17849)

Connect an agent — have() is free.