compress
Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.
compress appears in the code Syntology harvested for 35 papers, as 11 distinct code bodies found in 35 places (a place is one code body under one paper). Of the 35 papers, 30 with a sample that ran: 4 with a run with no instrument failure, 26 where every run was a failure of Syntology's instrument. 0 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 compress 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 11 distinct code bodies named compress: 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 3 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:
Licence is a property of each copy, so it is counted per place: 25 of the 35 places are pointer only (Syntology does not serve that copy's text); at 12 of those 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
35 papers shown of 35, newest first; 35 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 4 papers added by Syntology; 2 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.
| Paper | Date | File | Status Syntology | Licence |
|---|---|---|---|---|
| Thinned Mean Field Langevin Dynamics added by Syntology | 2026-05 (from id) | hudsonchen/thinned_mfld/utils/kt.py b8179bb351b7af3d |
ran | no licence file found · pointer only |
| LoReC: Rethinking Large Language Models for Graph Data Analysis added by Syntology | 2026-04 (from id) | Git-King-Zhan/LoReC/lorec-gpt/graphgpt/model/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | no licence file found · pointer only |
| DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment added by Syntology | 2026-03 (from id) | lm-sys/FastChat/fastchat/model/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | Apache-2.0 (permissive) here; the stored copy is pointer only |
| Garbage Attention in Large Language Models: <BOS> Sink Heads and Sink-aware Pruning added by Syntology | 2026-01 (from id) | CASIA-LMC-Lab/FLAP/lib/prune.py 1e3629d8fc0ca6c7 |
unverified | Apache-2.0 (permissive) |
| Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models | 26 Sep 2024 | hui-po-wang/LM-GC/compressors/png.py a97701702e1a2e67 |
ran · our draft was wrong | MIT (permissive) |
| Exploring Design Choices for Building Language-Specific LLMs | 20 Jun 2024 | atutej/token-language-adaptation/FastChat/fastchat/model/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | no licence file found · pointer only |
| FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models | 7 Jun 2024 | rui-ye/fedllm-bench/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | no licence file found · pointer only |
| Debiased Distribution Compression | 18 Apr 2024 | identical code first harvested elsewhere 9a913678c56785e8 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | licence of this copy not recorded |
| StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models | 12 Mar 2024 | openbmb/toolbench/toolbench/model/compression.py 386536152177a379 |
unverified | Apache-2.0 (permissive) |
| Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference | 7 Mar 2024 | BirgerMoell/SwedishLLMBenchmark/fastchat/model/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | Apache-2.0 (permissive) here; the stored copy is pointer only |
| Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents | 4 Mar 2024 | yifan-song793/eto/fastchat/model/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | no licence file found · pointer only |
| UrbanGPT: Spatio-Temporal Large Language Models | 25 Feb 2024 | hkuds/urbangpt/urbangpt/model/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | Apache-2.0 (permissive) here; the stored copy is pointer only |
| Graph Diffusion Policy Optimization | 26 Feb 2024 | sail-sg/gdpo/model/diffusion_discrete.py 4d13d6ce3ccd0cc1 |
unverified | no licence file found · pointer only |
| Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmetic | 19 Feb 2024 | declare-lab/red-instruct/starling_training/fastchat/model/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | Apache-2.0 (permissive) here; the stored copy is pointer only |
| GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning | 3 Feb 2024 | WEIYanbin1999/GITA/fastchat/model/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | no licence file found · pointer only |
| RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning | 16 Jan 2024 | Junjie-Ye/RoTBench/Code/model/compression.py 386536152177a379 |
unverified | Apache-2.0 (permissive) |
| VIoTGPT: Learning to Schedule Vision Tools in LLMs towards Intelligent Video Internet of Things | 1 Dec 2023 | zhongyy/viotgpt/train/compression.py 386536152177a379 |
unverified | no licence file found · pointer only |
| Exploring the Reliability of Large Language Models as Customized Evaluators for Diverse NLP Tasks | 30 Oct 2023 | qtli/coeval/webapp/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | Apache-2.0 (permissive) here; the stored copy is pointer only |
| JudgeLM: Fine-tuned Large Language Models are Scalable Judges | 26 Oct 2023 | hitz-zentroa/eval-MCG-COLING-2025/evaluation/JudgeLM-main/judgelm/model/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | Apache-2.0 (permissive) here; the stored copy is pointer only |
| GraphGPT: Graph Instruction Tuning for Large Language Models | 19 Oct 2023 | HKUDS/GraphGPT/graphgpt/model/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | Apache-2.0 (permissive) here; the stored copy is pointer only |
| Language Modeling Is Compression | 19 Sep 2023 | google-deepmind/language_modeling_is_compression/compressors/png.py a97701702e1a2e67 |
ran · our draft was wrong | Apache-2.0 (permissive) |
| 3D-LLM: Injecting the 3D World into Large Language Models | 24 Jul 2023 | umass-foundation-model/3d-llm/3DLanguage_data/ChatCaptioner_based/quetion_model.py 80dde39da1ba3708 |
ran · our draft was wrong | MIT recorded; this copy not marked cleared · pointer only |
| Phoenix: Democratizing ChatGPT across Languages | 20 Apr 2023 | freedomintelligence/llmzoo/llmzoo/deploy/webapp/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | Apache-2.0 (permissive) here; the stored copy is pointer only |
| FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU | 13 Mar 2023 | fminference/flexgen/flexllmgen/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | Apache-2.0 (permissive) here; the stored copy is pointer only |
| Compress Then Test: Powerful Kernel Testing in Near-linear Time | 14 Jan 2023 | identical code first harvested elsewhere 9a913678c56785e8 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | licence of this copy not recorded |
| Self-attention Does Not Need $O(n^2)$ Memory | 10 Dec 2021 | stability-ai/fastchat/fastchat/model/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | Apache-2.0 (permissive) here; the stored copy is pointer only |
| Distribution Compression in Near-linear Time | 15 Nov 2021 | microsoft/goodpoints/goodpoints/compress.py 9a913678c56785e8 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | MIT (permissive) |
| Generalized Kernel Thinning | 4 Oct 2021 | identical code first harvested elsewhere 9a913678c56785e8 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | licence of this copy not recorded |
| Unsupervised Hashing with Contrastive Information Bottleneck | 13 May 2021 | qiuzx2/CIBHash/model/CIBHash.py 9d8f8e1077379f49 |
ran · our draft was wrong | MIT (permissive) |
| Kernel Thinning | 12 May 2021 | identical code first harvested elsewhere 9a913678c56785e8 |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | licence of this copy not recorded |
| Event Outlier Detection in Continuous Time | 19 Dec 2019 | siqil/CPPOD/summarize_results_std.py 2889e16a4eb04885 |
ran | MIT (permissive) |
| Deep Signature Transforms | 21 May 2019 | anh-tong/signax/src/signax/utils.py 240a22a9a6f347bd |
ran | MIT (permissive) |
| Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression | 20 Mar 2019 | mauriceqch/pcc_geo_cnn/src/compress.py 68ecd4d88b382314 |
ran | MIT (permissive) |
| ACL Anthology id 2025.emnlp-main.1337 | RazvanDu/CopySpec/FastChat/fastchat/model/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | MIT (permissive) here; the stored copy is pointer only | |
| ACL Anthology id 2024.findings-emnlp.559 | hitz-zentroa/cn-eval/evaluation/JudgeLM-main/judgelm/model/compression.py 80dde39da1ba3708 |
ran · our draft was wrong | Apache-2.0 (permissive) here; the stored copy is pointer only |
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