Home › Code › last_token_pool

last_token_pool

Syntologyentry name in harvested code

Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

last_token_pool appears in the code Syntology harvested for 18 papers, as 13 distinct code bodies found in 19 places (a place is one code body under one paper). Of the 18 papers, 18 with a sample that ran: 1 with a run with no instrument failure, 17 where every run was a failure of Syntology's instrument. 8 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 last_token_pool 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 last_token_pool: 13 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 12 where Syntology's instrument failed) · 0 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
0ran · violated contract
9ran · our draft was wrong
3ran; the contract check could not run
1ran
0unverified
8fingerprinted

Licence is a property of each copy, so it is counted per place: 8 of the 19 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

18 papers shown of 18, newest first; 19 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 7 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.

PaperDateFileStatus SyntologyLicence
Beyond Scale and Generation: Understanding Language Model-based Entity Matching added by Syntology 2026-07 (from id) Jantory/llm-trained-matcher/probe_geometry.py f92d0a29632c86a4 ran · our draft was wrong no licence file found · pointer only
MERIT: Matching Expertise via Rubric-Informed Training for Reviewer Assignment added by Syntology 2026-05 (from id) Luli3220/MERIT/MERIT-Retriever/train/preprocess_topk.py 337c7c257862b7cb ran · our draft was wrong no licence file found · pointer only
Topic Is Not Agenda: A Citation-Community Audit of Text Embeddings added by Syntology 2026-05 (from id) junseon-yoo/topic-not-agenda/code/embeddings/embed_qwen3.py f0ae4e135bfc9af9 ran · our draft was wrong fingerprinted MIT (permissive)
ChunQiuTR: Time-Keyed Temporal Retrieval in Classical Chinese Annals added by Syntology 2026-04 (from id) xbdxwyh/ChunQiuTR/src/models_temporal_dual.py 456b917630e4c937 ran · our draft was wrong fingerprinted MIT (permissive)
According to Me: Long-Term Personalized Referential Memory QA added by Syntology 2026-03 (from id) JingbiaoMei/ATM-Bench/memqa/retrieve/retrievers.py b15d6769e9f3531d ran · our draft was wrong fingerprinted MIT (permissive)
Doc-to-LoRA: Learning to Instantly Internalize Contexts added by Syntology 2026-02 (from id) SakanaAI/doc-to-lora/src/ctx_to_lora/modeling/text_to_lora.py b6c4cb90c7bfeae1 ran; the contract check could not run (RAISES) MIT (permissive)
Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation added by Syntology 2025-10 (from id) dhrupadb/semantic_isotropy/lib/python/semantic_isotropy/metrics/isotropy.py 2ded070fabe7bdc7 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal Reasoning 24 Feb 2025 THUlawtech/JUREX/LCR_experiment/FlagEmbedding/flag_models.py 2ded070fabe7bdc7 ran · our draft was wrong fingerprinted MIT (permissive)
Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency 28 Oct 2024 Miracle-Messi/Isa-AutoFormal/equiv_checker/score_label.py 2ded070fabe7bdc7 ran · our draft was wrong fingerprinted no licence file found · pointer only
Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis 9 Jul 2024 ecnu-sea/SEA/evaluate_sea_a.py e144fbfe3c2921e2 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs 15 Jul 2024 mail-research/metallm-wrapper/get_embedding_mmlu.py 2ded070fabe7bdc7 ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only
From Distributional to Overton Pluralism: Investigating Large Language Model Alignment 25 Jun 2024 thomlake/investigating-alignment/create_embeddings.py 5e828ee14762bb7a ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only
A Fine-tuning Dataset and Benchmark for Large Language Models for Protein Understanding 8 Jun 2024 tsynbio/proteinlmdataset/benchmark/embedding_model.py 2ded070fabe7bdc7 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval 21 Apr 2024 kyriemao/ChatRetriever/src/kindred/models/model_utils.py 427e092aff588e25 ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only
RAR-b: Reasoning as Retrieval Benchmark 9 Apr 2024 gowitheflow-1998/rar-b/rarb/mcr_utils/model_utils.py 2ded070fabe7bdc7 ran · our draft was wrong fingerprinted no licence file found · pointer only
RAR-b: Reasoning as Retrieval Benchmark 9 Apr 2024 gowitheflow-1998/rar-b/rarb/rarb_models/e5mistral.py 880b8d7cf30596ca ran · our draft was wrong no licence file found · pointer only
Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism 20 Feb 2024 artefactory/abstention-reranker/abstention_reranker/compute_mistral_biencoder.py 2ded070fabe7bdc7 ran · our draft was wrong fingerprinted MIT (permissive)
LM-Cocktail: Resilient Tuning of Language Models via Model Merging 22 Nov 2023 flagopen/flagembedding/FlagEmbedding/inference/embedder/decoder_only/base.py c32ab879efe1d4b5 ran · our draft was wrong fingerprinted MIT (permissive)
Fine-Tuning LLaMA for Multi-Stage Text Retrieval 12 Oct 2023 texttron/tevatron/src/tevatron/megatron/engine.py cd7cef6e9418ab5d ran Apache-2.0 (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