sample_tokens
Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.
sample_tokens appears in the code Syntology harvested for 16 papers, as 13 distinct code bodies found in 17 places (a place is one code body under one paper). Of the 16 papers, 15 with a sample that ran: 4 with a run with no instrument failure, 11 where every run was a failure of Syntology's instrument. 3 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 sample_tokens 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 13 distinct code bodies named sample_tokens: 12 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 1 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: 12 of the 17 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 “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
16 papers shown of 16, newest first; 17 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 12 papers added by Syntology. 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 |
|---|---|---|---|---|
| Self-Speculation for Faster Reasoning Models added by Syntology | 2026-08 (from id) | Ravi-VK/SSR/vllm/benchmarks/benchmark_prefix_caching.py b534d2300709c9f8 |
ran · honoured contract | no licence file found · pointer only |
| Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation added by Syntology | 2026-06 (from id) | PunchlineAAAA/DICE/dream/generation_utils.py 1891fed3a1008763 |
ran; the contract check could not run (RAISES) | MIT (permissive) |
| TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models added by Syntology | 2026-06 (from id) | PKU-ML/TrustLDM/generate_functions/generate_dream.py acdf3b906c266dee |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted | CC-BY-SA-4.0 (copyleft) · pointer only |
| LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systems added by Syntology | 2026-05 (from id) | ideas-labo/llmsys-hpobench/sampler/Engine/vllm_sampler/benchmark/benchmark_prefix_caching.py 493b76d45cef9f16 |
ran · honoured contract | GPL-3.0 (copyleft) · pointer only |
| DPRM: A Plug-in Token-Ordering Module for Discrete Diffusion Models added by Syntology | 27 Apr 2026 | VITA-MLLM/Omni-Diffusion/omni_diffusion/models/dream/generation_utils.py 9b617164ca2a5c37 |
ran; the contract check could not run (RAISES) fingerprinted | no licence file found · pointer only |
| R 2 -dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction added by Syntology | 2026-04 (from id) | GATECH-EIC/R2-dLLM/dream/model/generation_utils.py 1891fed3a1008763 |
ran; the contract check could not run (RAISES) | no licence file found · pointer only |
| DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference added by Syntology | 2026-04 (from id) | X-Xia0828/DepCap/dream/model/generation_utils.py 1891fed3a1008763 |
ran; the contract check could not run (RAISES) | no licence file found · pointer only |
| Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models added by Syntology | 2026-02 (from id) | duterscmy/SOAR/eval_dream7b/generation_utils_soar.py b25f93a91b055a16 |
ran; the contract check could not run (RAISES) fingerprinted | no licence file found · pointer only |
| DAWN: Dependency-Aware Fast Inference for Diffusion LLMs added by Syntology | 2026-02 (from id) | lizhuo-luo/DAWN/dream/model/generation_utils.py 1891fed3a1008763 |
ran; the contract check could not run (RAISES) | MIT (permissive) |
| Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding added by Syntology | 2026-01 (from id) | xiaoshideta/Streaming-dLLM/OpenPangu/inference/generation_utils_streaming.py e79ea35422da626b |
ran; the contract check could not run (RAISES) · metamorphic tier: invariant | no licence file found · pointer only |
| Latent Speech-Text Transformer added by Syntology | 2025-10 (from id) | facebookresearch/lst/lst/generate.py 294621d07f3c12f0 |
ran | licence not identified · pointer only |
| AdaBlock-dLLM: SEMANTIC-AWARE DIFFUSION LLM INFERENCE VIA ADAPTIVE BLOCK SIZE added by Syntology | 2025-09 (from id) | lgxi24/AdaBlock-dLLM/dream/model/generation_utils_adablock.py bf0792b4bae5f006 |
ran; the contract check could not run (RAISES) | Apache-2.0 (permissive) |
| Byte Latent Transformer: Patches Scale Better Than Tokens | 13 Dec 2024 | facebookresearch/blt/bytelatent/generate.py 294621d07f3c12f0 |
ran | no licence file found · pointer only |
| Do Unlearning Methods Remove Information from Language Model Weights? | 11 Oct 2024 | aghyad-deeb/unlearning_evaluation/unlearn_corpus.py ee7b95c55394f703 |
ran · our draft was wrong | no licence file found · pointer only |
| Do Unlearning Methods Remove Information from Language Model Weights? | 11 Oct 2024 | aghyad-deeb/unlearning_evaluation/finetune_corpus.py 9fcc0dfdb46714f9 |
ran · our draft was wrong | no licence file found · pointer only |
| Multi-Objective GFlowNets | 23 Oct 2022 | samuelstanton/lambo/lambo/models/mlm.py 54c3c0fbd89ebc72 |
unverified | Apache-2.0 (permissive) |
| MaskGIT: Masked Generative Image Transformer | 8 Feb 2022 | alibaba/graph-gpt/src/utils/generation_utils.py 3028b4a113e4e8f8 |
ran; the contract check could not run (RAISES) | 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