Pith. sign in

Paper Citation Record · LEDGER

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models

As of 13 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 3 inbound Pith citation observations for arXiv:2412.12687.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2412.12687 v3

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T13:55:45.235032Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:59:02.769207Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-06T17:05:02.945302Z

Reference resolution

15 of 15 outbound references displayed

  • verified exact0
  • verified fuzzy6
  • unresolved9
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8982ab12-7561-4c0e-b348-5c320e3df8a3 · outbound

This paper cites Training Compute-Optimal Large Language Models.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models Training Compute-Optimal Large Language Models

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-11T13:55:45.163262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T13:55:45.163262Z digest=sha256:0333986ad88c654dbe7c7a95677ce9f0bc0621f2f42d2509c69e7cb98f54e19c

Observation dbcb050e-499a-4e27-896e-3bdf9460e414 · outbound

This paper cites Harnessing the power of llms in practice: A survey on chatgpt and beyond,.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models Harnessing the power of llms in practice: A survey on chatgpt and beyond,

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:55:45.471463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-11T13:55:45.169883Z digest=sha256:577c9508617f49630a0f3d93fad230b2cd0d4c2915b293a39f9b4f5b4fdc6813

Observation 7f57e927-76ce-4e92-afd8-0cfaa7c3dae9 · outbound

This paper cites Llm-pruner: On the structural pruning of large language models,.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models Llm-pruner: On the structural pruning of large language models,

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:55:45.454338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-11T13:55:45.174399Z digest=sha256:e7bb3cfc4e763bda125bdb67c7874cab6c465a3e8f2286e1e066e2bac4c71a35

Observation 09eb085e-17ca-4abc-ac74-87654ef31a8f · outbound

This paper cites LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-11T13:55:45.180184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T13:55:45.180184Z digest=sha256:3842f01f93a215dc6478541429002c00ecacd3608de3006ef3fc79f7b972d465

Observation dcd60f6c-a7d5-47c5-80ca-f0d8753e08a4 · outbound

This paper cites DistillSpec: Improving Speculative Decoding via Knowledge Distillation.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models DistillSpec: Improving Speculative Decoding via Knowledge Distillation

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-11T13:55:45.185076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T13:55:45.185076Z digest=sha256:9eb60f312734aea9eec645bf93ff316dd9cf6ae05c863980f08fd1188e3dfcf6

Observation ee27de9a-7b8e-40d6-a3a6-8b1cb174733d · outbound

This paper cites Hybrid slm and llm for edge-cloud collaborative inference,.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models Hybrid slm and llm for edge-cloud collaborative inference,

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:55:45.439985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-11T13:55:45.192117Z digest=sha256:017915ab62fbc4fd981dd99abadfbce5baad5cb5e088c4f717f24f151e9d12fb

Observation c396383c-43c3-4c48-ade8-bc941dcefdbf · outbound

This paper cites Fast inference from transform- ers via speculative decoding,.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models Fast inference from transform- ers via speculative decoding,

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:55:45.425572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-11T13:55:45.197135Z digest=sha256:374d66e2967490778b9f7a104f6bcc5b2005df5269105df4f6f5e75f9d1bfa1a

Observation f219e540-4030-46ea-afaa-e526d3f5f1f6 · outbound

This paper cites Understanding the metropolis-hastings algorithm,.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models Understanding the metropolis-hastings algorithm,

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-11T13:55:45.202129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T13:55:45.202129Z digest=sha256:6a880f45ba147d9a935e411759d00914a895e0860434c7384e61aca318c0a393

Observation e9f3a79e-7c5c-460c-957d-995813ec170a · outbound

This paper cites Dropout as a bayesian approximation: Representing model uncertainty in deep learning,.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models Dropout as a bayesian approximation: Representing model uncertainty in deep learning,

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-11T13:55:45.206967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T13:55:45.206967Z digest=sha256:1c7d791f762acf8785c3ad7dfb6c186d11a0efde5def8e22728e409fd8cc1d0e

Observation 3f6f6ccc-3a78-4c15-a236-945adbca0013 · outbound

This paper cites Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-11T13:55:45.211650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T13:55:45.211650Z digest=sha256:9887b67f79ceea30ccd4e724d45b604ea8854bbc7926538eab547d6440b46e57

Observation 523e6b7f-88e4-4ba8-84b4-3e7d68e4accc · outbound

This paper cites SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-11T13:55:45.217207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T13:55:45.217207Z digest=sha256:5452fdc8ac281bd133bbc46f860062cab8479b62c143abe3ab75d5364358d115

Observation 69cb4e8e-17d4-4317-947e-13ae09a95eee · outbound

This paper cites Wordnet: a lexical database for english,.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models Wordnet: a lexical database for english,

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-11T13:55:45.222000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T13:55:45.222000Z digest=sha256:84f26bcb7ee785d2a29037ee59bbe66e56ef32111addeac538c6f9aaff0e0f12

Observation 6ec2920f-1329-4c20-889a-7ab334710ae2 · outbound

This paper cites Stanford alpaca: An instruction-following llama model,.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models Stanford alpaca: An instruction-following llama model,

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:55:45.381778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-11T13:55:45.226468Z digest=sha256:9e4bda0bab97f91e7ff6719cfb3ce53e7713955e1d51e25819f0befba58e6e23

Observation c08093f0-8d7e-4a69-899d-37120135de1a · outbound

This paper cites The flan collection: Designing data and methods for effective instruction tuning,.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models The flan collection: Designing data and methods for effective instruction tuning,

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T13:55:45.367543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-11T13:55:45.231224Z digest=sha256:81a32631093e22fe02cce8331c48024d9342f8e89e43f39bd71c3553a06520d5

Observation adda9605-51ae-48ae-b5d0-868fb525a047 · outbound

This paper cites Universal Sentence Encoder.

Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models Universal Sentence Encoder

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-11T13:55:45.235032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T13:55:45.235032Z digest=sha256:5f70c2cd9f6371ab944cb9fa68c4be8d46782d3491a2e2b60dadaafee1b0ecdc

Pith citing papers

Observation ef0da03f-33c7-4127-b10c-6dd7f4416723 · inbound

Prompting Wireless Networks: Reinforced In-Context Learning for Power Control cites this paper.

Prompting Wireless Networks: Reinforced In-Context Learning for Power Control Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-07T05:59:02.769207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T05:59:02.769207Z digest=sha256:717847ff152dc257e42091da0f2ad49a2832b092e434906d2bd1c74e2df260bc

Observation 18aed4b0-f397-4acc-9500-50d23ce2a4f0 · inbound

Low-Complexity Semantic Packet Aggregation for Token Communication via Lookahead Search cites this paper.

Low-Complexity Semantic Packet Aggregation for Token Communication via Lookahead Search Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-06T23:13:02.245722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T23:13:02.245722Z digest=sha256:184213ba97df2bbc71aca27529a9aa2054e48653f94139f55e2ee7c1cbe0c055

Observation 87813549-5074-4d4a-9217-32a086a73519 · inbound

DSSD: Efficient Edge-Device LLM Deployment and Collaborative Inference via Distributed Split Speculative Decoding cites this paper.

DSSD: Efficient Edge-Device LLM Deployment and Collaborative Inference via Distributed Split Speculative Decoding Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models

Reference 9

Resolution
verified exact
local_arxiv, observed 2026-08-06T17:05:03.040669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=arxiv_source observed=2026-08-06T17:05:02.637601Z digest=sha256:06f4d968fbaade2d17e177754c0d0507a244d291f2546e310a1ea5d8eea753bd