Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-11T11:29:31.140926Z
Paper Citation Record · LEDGER
As of 12 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 4 inbound Pith citation observations for arXiv:2412.15431.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-11T11:29:31.140926Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-01T09:36:02.050940Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-04T08:29:42.348258Z
57 of 57 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 4fc767db-6097-480f-9ca2-4ddd594bcfb2 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Attention is all you need,
Reference 1
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 6ebbe078-29a0-462c-900b-1f3447c35fda · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fefaf2c8-7c54-4ca4-9738-0c1ddb171429 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Introducing ChatGPT,
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9494e2ce-983a-45e5-9bb6-823ad6b834f6 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Introducing Microsoft 365 Copilot – your copilot for work,
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 817d6e74-a2b4-472e-b454-6a2e4751f1eb · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models The technology behind Amazon’s GenAI- powered shopping assistant, Rufus,
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation f2c71ac7-8d0b-4a94-bc8c-3da225e1be67 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Detecting pretraining data from large language models,
Reference 6
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 5edc4450-bd60-4507-b0d3-b4f1e7f99866 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Did the neurons read your book? document-level membership inference for large language models,
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6a24313a-098f-442d-bc47-c906a9da8801 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Ex- tracting training data from large language models,
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 770c2767-ca8e-48b0-981a-c871d788ca57 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Formalizing and benchmarking prompt injection attacks and defenses,
Reference 9
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 42505ed7-5f82-459f-9b33-4015d6f274d3 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models What was your prompt? a remote keylogging attack on AI assistants,
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 51b151f3-95cc-45aa-8ad1-c6211c9451fc · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models The early bird catches the leak: Unveiling timing side channels in llm serving systems,
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 58fb2d33-029e-48b9-a7ea-37b804a4cbbf · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Privacy risks of speculative decoding in large language models,
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1f154f0a-e1bc-45c1-b181-5d96c64b9d0d · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Language Model Tokenizers Introduce Unfairness Between Languages,
Reference 13
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation c22ec721-d6a9-491d-8177-b77865f7f43f · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Do all languages cost the same? tokenization in the era of commercial language models,
Reference 14
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation c58bba13-9721-44cc-9284-ca19dcdb87e4 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Hello GPT-4o,
Reference 15
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 81f8e646-9ef8-42ab-b800-667f3e49469f · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Neural machine translation of rare words with subword units,
Reference 16
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 57e6aa42-f126-4925-9f22-1556ae7e7421 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Google’s neural machine translation system: Bridging the gap between human and machine translation,
Reference 17
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 3b2f7418-a2ca-48aa-8f56-dd7d82e9bc24 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Sentencepiece: A simple and lan- guage independent subword tokenizer and detokenizer for neural text processing,
Reference 18
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 4dd67faa-b667-44c6-aa12-575d2a2cffb2 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8bdbf1eb-0ead-4b76-840b-8b552eb0524d · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Beyond English-Centric Multilingual Machine Translation
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 38ab4665-d6b2-4442-bff1-ad99c2c5a1b0 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9cbe1ae1-dfa8-4638-8386-90e8ba6a1f01 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fb3492fd-1ca1-4c4a-98c4-a6d9c8c9ae84 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 75bb2bf0-81d9-4524-a0f9-c39fd929538e · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e65e6c48-d6ec-4559-88b1-74b6de95500e · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Bert: Pre- training of deep bidirectional transformers for language understand- ing,
Reference 25
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 8f1f1489-00f8-4edb-bbef-b318a0291e8d · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models BERT for Joint Intent Classification and Slot Filling
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 572906b0-fab9-44f4-bfb1-0389a3b3d64c · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models BERTopic: Neural topic modeling with a class-based TF-IDF procedure
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8def37b8-da79-4099-9622-2d81f7306d7f · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Universal language model fine-tuning for text classification,
Reference 28
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 0d55fba5-e0e0-46ce-af83-53061a151aa6 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Language models are few-shot learners,
Reference 29
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 5f0fb55c-c055-4aa6-8f60-f2ba1bafc2b8 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Calibrate before use: Improving few-shot performance of language models,
Reference 30
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation bfbd5404-f0a2-4ad1-b8fa-0429ec14a1ea · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1b5be227-a4b2-44b2-8b5e-c80e0584f84f · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Improving few-shot performance of language models via nearest neighbor calibration,
Reference 32
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 36916899-7c8b-402c-954f-c0e3bb460c46 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Fairness-guided Few-shot Prompting for Large Language Models
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation acfb845f-c39d-4216-9959-8a15a4a9df1e · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Translate text by using adaptive translation
Reference 34
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 6da953c1-0819-429f-a852-446c60b3c8cd · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models DeepL’s next-gen LLM outperforms ChatGPT-4, Google, and Microsoft for translation quality
Reference 35
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation ec20d879-7c46-4c5b-beba-0f0b4fbd6abd · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models General Data Protection Regulation - Article 4
Reference 36
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 511a0d26-f357-4d02-b596-e3383580f659 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Maximum likelihood from incomplete data via the em algorithm,
Reference 37
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fac37505-f001-4a07-a93b-55863926f2b6 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models On a measure of divergence between two multinomial populations,
Reference 38
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e601c6bb-4984-4234-a335-05efd1ff7b20 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Multilingual Translation with Extensible Multilingual Pretraining and Finetuning
Reference 39
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cdc011be-7cd0-4d8d-8a22-8a0d97e06062 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Tower: An open multilingual large language model for translation-related tasks,
Reference 40
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation d67fb694-9338-432c-a59d-2dd240bbb83f · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models No Language Left Behind: Scaling Human-Centered Machine Translation
Reference 41
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0092e762-d580-4712-aabb-80e52290f14e · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Europarl: A parallel corpus for statistical machine translation,
Reference 42
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation cddb1f3d-0c21-402b-be01-f06dabde35e5 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Einstein for Service
Reference 43
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation bd0492a3-716a-495d-a607-6e482d13119f · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Med-PaLM: A Medical Large Language Model - Google Research
Reference 44
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 1ce73bde-bb62-48a9-9628-f1b3abc43f71 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Super-naturalinstructions:generalization via declarative instructions on 1600+ tasks,
Reference 45
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 14415536-938a-486f-83ae-094030b9379c · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models GPT-4 Technical Report
Reference 46
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e159da0a-b0df-48f9-a014-2cf1e430eb6f · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Gemma 2: Improving open language models at a practical size,
Reference 47
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5a86f428-12cf-45f6-9b71-ca8ec890c3bf · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Llama 3 model card,
Reference 48
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 65acc5bd-fe7f-4732-8968-ead4c727b5f6 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Orca: A distributed serving system for Transformer-Based generative models,
Reference 49
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 646ca870-d0e7-46ee-b1bf-dd63c1931621 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Privacy side channels in machine learning systems,
Reference 50
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 674d2d26-8d9f-41c2-a021-1513c800c797 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Rendered insecure: Gpu side channel attacks are practical,
Reference 51
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1af5848d-5d4b-4272-b3b6-1743660da726 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Leaky dnn: Stealing deep-learning model secret with gpu context-switching side- channel,
Reference 52
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 9dbeaad4-fe15-4778-8ef6-405ef59bba42 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Also, generate label ’no’ for offensive statements that appear to be unintentional or non-offensive statements that are underhandedly offensive
Reference 57
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 18b14d21-0a2f-4ac1-b8b4-7cc08b5ff101 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Reference 2016
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f30158c9-9111-4e8c-87ab-99c996a1f491 · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Calibrate Before Use: Improving Few-Shot Performance of Language Models
Reference 2021
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6ff7e294-a79b-476e-bc94-4d3988e01e7a · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Improving Few-Shot Performance of Language Models via Nearest Neighbor Calibration
Reference 2022
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8f972a5f-d3ff-451e-aed9-5f49fa9249fc · outbound
Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models Tower: An Open Multilingual Large Language Model for Translation-Related Tasks
Reference 2024
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a0499bd1-41f8-48f2-8acd-5eddaf51ac9d · inbound
Security Considerations for Multi-agent Systems Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models
Reference 242
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation efd4d034-f887-4f8b-b5de-cde5b86e16f0 · inbound
OTRO: Oblivious Tokenization Path with Square-Root ORAM Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation a9ba69d2-1cbc-4f00-8582-ddc3442e8493 · inbound
Investigating The Security of Modern AI and Cloud Infrastructure Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models
Reference 148
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation d4fe5736-c98f-447a-86bd-c0fc3b0f9a93 · inbound
Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing Time Will Tell: Timing Side Channels via Output Token Count in Large Language Models
Reference 73
Source-reported events for the cited work
Unavailable: canonical work link unavailable.