Home › Code › build_chat

build_chat

Syntologyentry name in harvested code

Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record.

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). Of the 29 papers, 29 with a sample that ran: 21 with a run with no instrument failure, 8 where every run was a failure of Syntology's instrument. 2 of the code bodies carry 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; get_code(code_sha256="…") returns this sample's fingerprint on the shared battery, with the battery's shuffled null and lift; not shown on this site (how to connect). "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

The 23 distinct code bodies named build_chat: 21 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. 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; the contract check could not run
17ran
2unverified
2fingerprinted

Licence is a property of each copy, so it is counted per place: 12 of the 36 places are pointer only (Syntology does not serve that copy's text); at 1 of them this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text (hover the licence cell for why). 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 “the contract check could not run” (RAISES, DEP_MISSING or TIMEOUT; hover a row's label for which) 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; “with no instrument failure” is honoured, violated and ran with no contract checked. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

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 their id only (arXiv: for an arXiv id; an id from another venue, such as ACL Anthology or AAAI, is named as that venue's id, never as an arXiv id). 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. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 ran 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 ran 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 ran 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 ran 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 ran 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 ran 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 ran Apache-2.0 (permissive)
Squeezed Attention: Accelerating Long Context Length LLM Inference 14 Nov 2024 SqueezeAILab/SqueezedAttention/squeezedattention/utils.py 66d002e5d75a1496 ran fingerprinted 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 ran 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 ran 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; the contract check could not run (DEP_MISSING) · metamorphic tier: deterministic 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 ran 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) here; the stored copy is pointer only
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
AAAI id aaai_34662 maxindian/3D-RPE-Long-Contex-Modeling/longbench-eval.py f59d3f952a8d5950 ran · our draft was wrong Apache-2.0 (permissive)
ACL Anthology id 2025.findings-emnlp.429 zhzihao/QPruningKV/run_longbench.py 3ddd62fbad41e698 ran · our draft was wrong fingerprinted MIT (permissive)
ACL Anthology id 2025.emnlp-main.443 adlnlp/Gali/longbench/pred.py 324506640e971548 ran 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is under a permissive licence, but the stored copy of the same code that Syntology serves is not cleared for its text. 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