Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-17T05:07:11.466066Z
Paper Citation Record · LEDGER
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
As of 6 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 3 inbound Pith citation observations for arXiv:2511.22972.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-05-15T09:15:50.963123Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-05-15T09:19:54.464232Z
Reference resolution
21 of 21 outbound references displayed
- verified exact15
- verified fuzzy1
- unresolved0
- parse uncertain0
- malformed identifier1
- metadata mismatch4
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 8172ff97-6160-4cbc-bb31-521e7f4d0b1a · outbound
This paper cites Gemini: A Family of Highly Capable Multimodal Models.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Gemini: A Family of Highly Capable Multimodal Models
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-17T05:09:03.780723Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 31a55e2a-9d3a-4712-9788-611ce7dacbeb · outbound
This paper cites Program Synthesis with Large Language Models.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Program Synthesis with Large Language Models
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T05:09:03.745755Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation c46c2991-c572-4211-b15b-d31f89d9ab5c · outbound
This paper cites Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T05:09:03.775841Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 413a27f1-88a1-4083-b6ff-1a9331431889 · outbound
This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T05:09:03.808780Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation c6a87b66-6dbd-4f83-bd1c-5881de73624c · outbound
This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Accelerating Large Language Model Decoding with Speculative Sampling
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T05:09:03.761385Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 712cebaa-ca4e-46c6-80e1-553d17dfb44c · outbound
This paper cites Evaluating Large Language Models Trained on Code.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Evaluating Large Language Models Trained on Code
Reference 7
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T05:09:03.750084Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 4445bcaf-1ef3-46dc-a46b-ddd881f616af · outbound
This paper cites Training Verifiers to Solve Math Word Problems.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Training Verifiers to Solve Math Word Problems
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T05:09:03.799486Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 93c3df7d-3953-4030-91f5-2b0dfd3578f0 · outbound
This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 9
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-17T05:09:03.788954Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 50854dfe-dc10-4317-98f4-50cccf816acc · outbound
This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 10
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-17T05:09:03.475660Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 06910a95-1da4-4eae-b5ec-64dc5ce0b3ae · outbound
This paper cites Evangelos Georganas, Dhiraj D.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Evangelos Georganas, Dhiraj D
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T05:09:03.771081Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation f9cb5908-6f59-4772-9756-0a9849356ca0 · outbound
This paper cites ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T05:09:03.485715Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 3e80f517-d4d7-4aa7-9563-1caa98825594 · outbound
This paper cites RULER: What's the Real Context Size of Your Long-Context Language Models?.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match RULER: What's the Real Context Size of Your Long-Context Language Models?
Reference 14
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-17T05:09:03.785097Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation c8d2880c-a608-44bd-be8a-2a2920a5cdfd · outbound
This paper cites Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
Reference 15
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T05:09:03.795885Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation cbdde34a-5e9f-4eed-9072-bd081c03cfe0 · outbound
This paper cites Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T05:09:03.754843Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 91d0b220-781b-4192-be11-eae8687ed036 · outbound
This paper cites Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T05:09:03.804396Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d811335e-0d9d-4ca4-b0cf-d056caa6c54e · outbound
This paper cites Language Models are Multilingual Chain-of-Thought Reasoners.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Language Models are Multilingual Chain-of-Thought Reasoners
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T05:09:03.766728Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 2e049f2f-afdf-44a6-9d78-305f99dacd05 · outbound
This paper cites Ryan Sun, Tianyi Zhou, Xun Chen, and Lichao Sun.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Ryan Sun, Tianyi Zhou, Xun Chen, and Lichao Sun
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T05:09:04.496150Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 499baecc-02e5-4f57-91e1-cfe18d9b68e9 · outbound
This paper cites URLhttps: //doi.org/10.18653/v1/2024.emnlp-main.1148.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match URLhttps: //doi.org/10.18653/v1/2024.emnlp-main.1148
Reference 21
- Resolution
- verified exact
- doi, observed 2026-05-17T05:09:03.471487Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 4c897bd9-efe3-421f-b496-36dc66255365 · outbound
This paper cites Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment
Reference 22
- Resolution
- malformed identifier
- doi_truncated, observed 2026-05-17T05:09:03.479748Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 79813471-7e0e-46ce-9ec8-46b7cb0a9e0d · outbound
This paper cites ParallelSpec: Parallel Drafter for Efficient Speculative Decoding.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match ParallelSpec: Parallel Drafter for Efficient Speculative Decoding
Reference 23
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T05:09:03.814354Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a1f92b26-94b7-44bf-b1ac-757325279a95 · outbound
This paper cites Qwen2 Technical Report.
Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match Qwen2 Technical Report
Reference 24
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T05:09:03.792087Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Pith citing papers
Observation e37c3666-00a1-4de1-a180-978fd13fd808 · inbound
HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness cites this paper.
HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T09:19:54.467551Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation baae65b6-ce81-4ba2-b6ec-d5cf5ff4daba · inbound
Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference cites this paper.
Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
Reference 3
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-10T13:30:26.830792Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation c5a5bf05-9b3f-40f6-9a57-5b7a0c6ed6de · inbound
WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference cites this paper.
WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
Reference 22
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T12:25:22.822107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.