SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2604.06997 · 2026

ChunQiuTR: Time-Keyed Temporal Retrieval in Classical Chinese Annals

Zijian He, Jie Ren, Keze Wang, Yihao Wang

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure 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/2604.06997.json · badge: /api/ran/2604.06997.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
xbdxwyh/ChunQiuTR community
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
QwenTimeDualEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
xbdxwyh/ChunQiuTR/src/models_temporal_dual.py
code served (permissive licence) · get_code("d2cbb939b26b7f4d")
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 an instance of its own class, QwenTimeDualEncoder: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
from unittest.mock import MagicMock

torch.manual_seed(0)

# Create a minimal mock AutoModel that has the required interface
class MockQwenModel(nn.Module):
    def __init__(self, hidden_size=64):
        super().__init__()
        self.config = MagicMock()
        self.config.hidden_size = hidden_size
        self.hidden_size = hidden_size
        # Add a simple projection layer to simulate encoder behavior
        self.proj = nn.Linear(8, hidden_size)
    
    def __call__(self, input_ids, attention_mask):
        # Simulate encoder output
        batch_size = input_ids.shape[0]
        seq_len = input_ids.shape[1]
        # Return last_hidden_state with shape (batch_size, seq_len, hidden_size)
        output = torch.randn(batch_size, seq_len, self.hidden_size)
        return MagicMock(last_hidden_state=output)

# Monkey-patch AutoModel.from_pretrained to return our mock
from transformers import AutoModel
original_from_pretrained = AutoModel.from_pretrained
AutoModel.from_pretrained = lambda model_name_or_path, **kwargs: MockQwenModel(hidden_size=64)

ARGS = {
    "model_name_or_path": "Qwen/Qwen3-Embedding-0.6B",
    "normalize": True,
    "num_gong": 10,
    "num_year": 5,
    "num_month": 12,
    "use_time_context_pred": False,
    "time_emb_dim": 64,
    "use_time_rel_bias": False,
    "time_rel_dim": 32,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type QwenTimeDualEncoder — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a QwenTimeDualEncoder 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
last_token_pool Ran
ran; our contract draft was wrong, not the code
xbdxwyh/ChunQiuTR/src/models_temporal_dual.py
code served (permissive licence) · get_code("456b917630e4c937")
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)

# Create small tensors for testing
batch_size = 2
seq_length = 5
hidden_dim = 4

# Case 1: left padding (all sequences are full length)
# attention_mask where last column is all 1s (left padding case)
last_hidden_states = torch.randn(batch_size, seq_length, hidden_dim)
attention_mask = torch.ones(batch_size, seq_length, dtype=torch.long)

ARGS = {
    "last_hidden_states": last_hidden_states,
    "attention_mask": attention_mask,
}
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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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
last_token_pool
brick of this paper's assembly: data_transform
8 other papers
8 dated earlier
2402.12997 (2024-02)
Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism
2404.06347 (2024-04)
RAR-b: Reasoning as Retrieval Benchmark
2406.05540 (2024-06)
A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding
and 5 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 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Retrieval shapes how language models access and ground knowledge in retrieval-augmented generation (RAG). In historical research, the target is often not an arbitrary relevant passage, but the exact record for a specific regnal month, where temporal consistency matters as much as topical relevance. This is especially challenging for Classical Chinese annals, where time is expressed through terse, implicit, non-Gregorian reign phrases that must be interpreted from surrounding context, so semantically plausible evidence can still be temporally invalid. We introduce ChunQi-uTR, a time-keyed retrieval benchmark built from the Spring and Autumn Annals and its exegetical tradition. ChunQiuTR organizes records by month-level reign keys and includes chrono-near confounders that mirror realistic retrieval failures. We further propose CTD (Calendrical Temporal Dual-encoder), a timeaware dual-encoder that combines Fourierbased absolute calendrical context with relative offset biasing. Experiments show consistent gains over strong semantic dual-encoder baselines under time-keyed evaluation, supporting retrieval-time temporal consistency as a key prerequisite for faithful downstream historical RAG. Our code and datasets are available at github.com/xbdxwyh/ChunQiuTR.

For agents

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

get_harvested_code_for_paper("2604.06997")
get_code_for_paper("2604.06997")
have("2604.06997")

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

curl https://syntology.ai/api/ran/2604.06997.json

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

[![Syntology run record](https://syntology.ai/api/ran/2604.06997.svg)](https://syntology.ai/paper/2604.06997)

Connect an agent — have() is free.