Home › Code › get_tokens

get_tokens

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.

get_tokens appears in the code Syntology harvested for 40 papers, as 19 distinct code bodies found in 41 places (a place is one code body under one paper). Of the 40 papers, 36 with a sample that ran: 14 with a run with no instrument failure, 22 where every run was a failure of Syntology's instrument. 10 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 get_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 19 distinct code bodies named get_tokens: 15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 4 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
4ran · our draft was wrong
0ran; the contract check could not run
11ran
4unverified
10fingerprinted

Licence is a property of each copy, so it is counted per place: 27 of the 41 places are pointer only (Syntology does not serve that copy's text); at 16 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

40 papers shown of 40, newest first; 41 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; 5 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
The Embedder's Dilemma: LLMs Are Better, but at What Cost? added by Syntology 2026-08 (from id) embeddings-benchmark/embedders-dilemma/llm_judge/evaluators/llm_rag_evaluator.py 2d6aa73765f8c641 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States added by Syntology 2026-08 (from id) zazamrykh/internal_probing/src/dataset/squad_eval.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
ReFact: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning added by Syntology 2026-07 (from id) NEUIR/REFACT/verl/verl/utils/reward_score/evdience_reward.py ef36c60282378811 ran · our draft was wrong MIT (permissive)
OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources added by Syntology 2026-05 (from id) JinheonBaek/OmniRetrieval/src/evaluation/metrics.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Foundational Large Language Models for Materials Research 12 Dec 2024 M3RG-IITD/llamat/src/Kshot-val.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
SiReRAG: Indexing Similar and Related Information for Multihop Reasoning 9 Dec 2024 SalesforceAIResearch/SiReRAG/evaluate_musique.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted no licence file found · pointer only
Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models 12 Oct 2024 intuit-ai-research/knowledge-infused-ai/synthetic-knowledge-ingestion/finetuning/ft_llama_factory.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only
A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders 22 Sep 2024 lasr-spelling/sae-spelling/sae_spelling/vocab.py 927eb86571fdf5f4 ran MIT (permissive)
A Language Model's Guide Through Latent Space 22 Feb 2024 dvruette/concept-guidance/concept_guidance/activations.py b168d5fa90d9b20d ran MIT (permissive)
Towards Efficient Methods in Medical Question Answering using Knowledge Graph Embeddings 15 Jan 2024 saptarshi059/cdqa-project/covid_qa_baseline.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted no licence file found · pointer only
Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning 16 Nov 2023 nusnlp/complex-tr/prompt_experiment/sem_metric/evaluate.py 72ae17e5ad61f6cb ran fingerprinted no licence file found · pointer only
Diversify Question Generation with Retrieval-Augmented Style Transfer 23 Oct 2023 gouqi666/RAST/eval_squad.py 011d5cd744886e9d ran fingerprinted no licence file found · pointer only
Knowledge-Augmented Language Model Verification 19 Oct 2023 jinheonbaek/kalmv/metrics.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted no licence file found · pointer only
Knowledge-Augmented Language Model Verification 19 Oct 2023 JinheonBaek/KALMV/models/verifiers.py a2c23eaf23140be2 ran · our draft was wrong fingerprinted no licence file found · pointer only
MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Models 8 Oct 2023 weiyifan1023/MenatQA/src/utils.py 575722a6543d189e ran fingerprinted no licence file found · pointer only
RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation 6 Oct 2023 carriex/recomp/eval_utils.py 496046a8354a8130 ran fingerprinted MIT (permissive)
$\rm SP^3$: Enhancing Structured Pruning via PCA Projection 31 Aug 2023 hyx1999/sp3/bert/metric/squad_v2.py 72ae17e5ad61f6cb ran fingerprinted no licence file found · pointer only
End-to-End Beam Retrieval for Multi-Hop Question Answering 17 Aug 2023 canghongjian/beam_retriever/gpt_turbo_exp.py 8a4f13df2795176e ran fingerprinted Apache-2.0 (permissive)
Open Data on GitHub: Unlocking the Potential of AI 9 Jun 2023 rajpurkar/SQuAD-explorer/evaluate-v2.0.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogs 20 May 2023 ynandwan/pmi-faith/faithfulness-metrics/src/compute_faithfulness_api.py 9c6cb7a5a08fbe5d unverified Apache-2.0 (permissive)
Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models 17 May 2023 bunsenfeng/knowledge_card/eval_datasets/MidtermQA/odqa_utils.py 496046a8354a8130 ran fingerprinted MIT (permissive)
Phrase Retrieval Learns Passage Retrieval, Too 16 Sep 2021 princeton-nlp/DensePhrases/densephrases/utils/squad_metrics.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only
A Dataset for Answering Time-Sensitive Questions 13 Aug 2021 wenhuchen/time-sensitive-qa/utils.py 575722a6543d189e ran fingerprinted BSD-3-Clause (permissive) here; the stored copy is pointer only
Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions? 2 Jun 2021 allenai/ethical-interventions/mutils.py db2b74b069046e20 ran Apache-2.0 (permissive)
Equilibrium and non-Equilibrium regimes in the learning of Restricted Boltzmann Machines 28 May 2021 AurelienDecelle/TorchRBM/rbm/fasta_utils.py 7eff798ee21e285c ran fingerprinted MIT (permissive)
Learning to Perturb Word Embeddings for Out-of-distribution QA 6 May 2021 seanie12/SWEP/squad_metrics.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Annotating and Modeling Fine-grained Factuality in Summarization 9 Apr 2021 tagoyal/factuality-datasets/evaluate_generated_outputs.py 702775d840e23942 unverified no licence file found · pointer only
Towards Interpreting BERT for Reading Comprehension Based QA 18 Oct 2020 identical code first harvested elsewhere aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted licence of this copy not recorded
Open-Domain Question Answering Goes Conversational via Question Rewriting 10 Oct 2020 apple/ml-qrecc/utils/evaluate_qa.py 119c6dab40b4b162 ran fingerprinted Apache-2.0 (permissive)
The Depth-to-Width Interplay in Self-Attention 22 Jun 2020 uf-hobi-informatics-lab/GatorTron/finetuning/qa/evaluate-squad-v2.0.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Revisiting Pre-Trained Models for Chinese Natural Language Processing 29 Apr 2020 ymcui/Chinese-PreTrained-XLNet/src/squad_utils.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only
HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data 15 Apr 2020 identical code first harvested elsewhere aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted licence of this copy not recorded
Linking artificial and human neural representations of language 2 Oct 2019 hans/nn-decoding/bin/eval_squad.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models 23 Aug 2019 somiltg/bert/evaluate-v2.0.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only
End-to-End Open-Domain Question Answering with BERTserini 5 Feb 2019 rsvp-ai/bertserini/bertserini/utils/utils_squad_metrics.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 11 Oct 2018 Zehui127/SQUAD_BERT/SQUAD/evaluate-v2.0.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only
AAAI id aaai_16733 rajammanabrolu/WorldGeneration/neural-based/KG-extraction/utils_squad_evaluate.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
ACL Anthology id 2024.findings-emnlp.365 UKPLab/m2qa/Experiments/M2QA_Metric/m2qa_metric.py c74510c72823459a unverified Apache-2.0 (permissive)
ACL Anthology id 2023.findings-eacl.134 UniversalPropositions/PriMeSRL-Eval/src/proposed/conversion.py d0749cdadb55fd4f ran Apache-2.0 (permissive)
ACL Anthology id 2023.emnlp-main.803 yisunlp/Anti-CF/utils/metrics.py aa6bc32d9c17a2f1 ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only
ACL Anthology id 2022.findings-emnlp.48 souvikdgp16/FADE/datasets/calculate_unigram_probability.py 0af007f9a8c6b6db 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 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