Home › Code › build_chat

build_chat

Syntologyentry name in harvested coderead from the graph 2026-09-24

build_chat appears in the code Syntology harvested for 29 papers, as 23 distinct code bodies found in 36 places (a place is one code body under one paper). At least one of them ran in 19 of the papers; 1 of the code bodies carries a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named build_chat do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 15 of the 23 distinct code bodies named build_chat; 8 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
1ran · fixture could not drive it
11ran
8unverified
1fingerprinted

Licence is a property of each copy, so it is counted per place: 11 of the 36 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

29 papers shown of 29, newest first; 36 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 3 papers added by Syntology; 3 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
CASK: Core-Aware Selective KV Compression for Reasoning Traces added by Syntology 2026-04 (from id) THUDM/LongBench/LongBench/pred.py 324506640e971548 unverified MIT (permissive)
CASK: Core-Aware Selective KV Compression for Reasoning Traces added by Syntology 2026-04 (from id) THUDM/LongBench/LongBench/retrieval/pred.py 2e148fc130561394 unverified MIT (permissive)
CASK: Core-Aware Selective KV Compression for Reasoning Traces added by Syntology 2026-04 (from id) THUDM/LongBench/LongBench/summ/compress.py 04b0e165da9a0405 unverified MIT (permissive)
Stacked from One: Multi-Scale Self-Injection for Context Window Extension added by Syntology 2026-03 (from id) Clement25/SharedLLM/LongBenchTest/summ/compress.py 04b0e165da9a0405 unverified no licence file found · pointer only
Stacked from One: Multi-Scale Self-Injection for Context Window Extension added by Syntology 2026-03 (from id) Clement25/SharedLLM/LongBenchTest/pred.py 9fc77302e79f7b27 unverified no licence file found · pointer only
Mamba Modulation On the Length Generalization of Mamba added by Syntology 2025-09 (from id) gnepul-ace/mamba_modulation/Mamba/LongBench/pred.py 324506640e971548 unverified MIT (permissive)
Draft-based Approximate Inference for LLMs 10 Jun 2025 identical code first harvested elsewhere 3ddd62fbad41e698 ran · our draft was wrong fingerprinted licence of this copy not recorded
HeavyWater and SimplexWater: Watermarking Low-Entropy Text Distributions 6 Jun 2025 identical code first harvested elsewhere f59d3f952a8d5950 ran · our draft was wrong licence of this copy not recorded
KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction 29 May 2025 zefan-cai/kvcache-factory/run_longbench.py 3ddd62fbad41e698 ran · our draft was wrong fingerprinted MIT (permissive)
AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge 18 Dec 2024 bobxwu/antileak-bench/LLMs/LLM.py 79f2a98626bab3df unverified no licence file found · pointer only
Pushing the Limits of Large Language Model Quantization via the Linearity Theorem 26 Nov 2024 goodevening13/aquakv/evaluate_longbench.py c3b06c2ebcf2af2d unverified Apache-2.0 (permissive)
Squeezed Attention: Accelerating Long Context Length LLM Inference 14 Nov 2024 SqueezeAILab/SqueezedAttention/squeezedattention/utils.py 66d002e5d75a1496 unverified no licence file found · pointer only
Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning 25 Oct 2024 fyyfu/headkv/run_longbench.py 3ddd62fbad41e698 ran · our draft was wrong fingerprinted no licence file found · pointer only
SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction 17 Oct 2024 sail-sg/simlayerkv/LongBench/pred.py 324506640e971548 unverified no licence file found · pointer only
TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention 7 Oct 2024 DerrickYLJ/TidalDecode/experiments/LongBench/pred.py 1707cb62894075a9 ran Apache-2.0 (permissive)
Discovering the Gems in Early Layers: Accelerating Long-Context LLMs with 1000x Input Token Reduction 25 Sep 2024 salesforceairesearch/gemfilter/eval/LongBench/pred.py 8339145374a403f3 ran Apache-2.0 (permissive)
Post-Training Sparse Attention with Double Sparsity 11 Aug 2024 andy-yang-1/doublesparse/LongBench/pred.py c9d682400f2b2384 ran MIT (permissive)
Less is More: Sparse Watermarking in LLMs with Enhanced Text Quality 17 Jul 2024 mail-research/sparse-llm-watermarking/pred.py ee4afb2d89ea94b5 ran MIT (permissive)
KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches 1 Jul 2024 henryzhongsc/longctx_bench/pipeline/model_utils.py 3b19a66bec30b1b9 ran MIT (permissive)
Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference 16 Jun 2024 mit-han-lab/Quest/evaluation/LongBench/pred.py 324506640e971548 unverified MIT (permissive)
QuickLLaMA: Query-aware Inference Acceleration for Large Language Models 11 Jun 2024 dvlab-research/q-llm/benchmark/pred.py 899f8b2f018b4018 ran no licence file found · pointer only
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model 7 May 2024 shadowpa0327/Palu/run_long_bench.py 9d1a542959f8346c ran · fixture could not drive it MIT (permissive)
SnapKV: LLM Knows What You are Looking for Before Generation 22 Apr 2024 fasterdecoding/snapkv/experiments/LongBench/pred_snap.py ead90df220ef482e ran Apache-2.0 (permissive)
SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget 7 Apr 2024 hetailang/squeezeattention/pred.py 2e148fc130561394 unverified no licence file found · pointer only
InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory 7 Feb 2024 thunlp/infllm/benchmark/pred.py 899f8b2f018b4018 ran MIT (permissive)
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache 5 Feb 2024 jy-yuan/kivi/pred_long_bench.py ef82bf5af4441329 ran MIT (permissive)
Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training 15 Nov 2023 hejunqing/never-lost-in-the-middle/Lost_Retrieval/src/pred_single.py 251720ea85d2ca71 ran MIT (permissive)
Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training 15 Nov 2023 hejunqing/never-lost-in-the-middle/LongBench/src/baichuan_pred_shuffle.py 7024e12377186e51 ran MIT (permissive)
Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training 15 Nov 2023 hejunqing/never-lost-in-the-middle/LongBench/src/pred_chatglm.py 7439724189daf2cb ran MIT (permissive)
Never Lost in the Middle: Mastering Long-Context Question Answering with Position-Agnostic Decompositional Training 15 Nov 2023 hejunqing/never-lost-in-the-middle/LongBench/src/pred_shuffle_reader.py 0af745ab8b003692 unverified MIT (permissive)
WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models 13 Nov 2023 THU-KEG/WaterBench/pred.py ed4be202f208766c ran · violated contract MIT (permissive)
WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models 13 Nov 2023 dortsur/heavywater_simplexwater/pred.py f59d3f952a8d5950 ran · our draft was wrong MIT (permissive)
Robust Distortion-free Watermarks for Language Models 28 Jul 2023 identical code first harvested elsewhere f59d3f952a8d5950 ran · our draft was wrong licence of this copy not recorded
arXiv:aaai_34662 maxindian/3D-RPE-Long-Contex-Modeling/longbench-eval.py f59d3f952a8d5950 ran · our draft was wrong Apache-2.0 (permissive)
arXiv:2025.findings-emnlp.429 zhzihao/QPruningKV/run_longbench.py 3ddd62fbad41e698 ran · our draft was wrong fingerprinted MIT (permissive)
arXiv:2025.emnlp-main.443 adlnlp/Gali/longbench/pred.py 324506640e971548 unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections