Paper Citation Record · LEDGER

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving

As of 14 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2608.08910.

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

pith.paper-citation-record.v1
2608.08910 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:25:49.053461Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

33 of 33 outbound references displayed

verified exact7
verified fuzzy8
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ba1e43ad-105d-4d83-9f78-44783a43613b · outbound

This paper cites an unresolved cited work.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:48.943841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e23bd0e3-eba5-4abb-9225-bdaf50f2fc54 · outbound

This paper cites an unresolved cited work.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:25:49.558882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f453ecdf-41a9-4e67-af1a-e93a35a0ab9a · outbound

This paper cites DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-08-14T04:25:49.363122Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d8421cb7-b073-4ca3-863a-2b709357d963 · outbound

This paper cites tritllm: balanced-ternary quantization for LLMs — paper (rev.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving tritllm: balanced-ternary quantization for LLMs — paper (rev

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:49.547424Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 290bf4d1-c3bf-45ab-9d28-27f9771a0ba5 · outbound

This paper cites LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:48.959005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76b5f983-12d9-4650-ad68-66c32122b876 · outbound

This paper cites Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:48.962805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 370847ab-5ab9-4b62-b34b-6e54422ab121 · outbound

This paper cites BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-08-14T04:25:49.333783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 19ebbb6b-a435-4023-b8cf-559625b81bfe · outbound

This paper cites ExTernD: Expanded-Rank Ternary Decomposition Ternary LLM PTQ with Accuracy Approaching Any Quantization Level.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving ExTernD: Expanded-Rank Ternary Decomposition Ternary LLM PTQ with Accuracy Approaching Any Quantization Level

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-14T04:25:49.320786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d21944b5-cc16-43ce-935c-cfef44c94a56 · outbound

This paper cites Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-08-14T04:25:49.307878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 26ec7687-02be-495e-980f-84fc7537b3c3 · outbound

This paper cites Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:48.976211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9f03262-c3e7-49dc-905a-24bd99ac3b2e · outbound

This paper cites QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:48.979500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41dbcc43-cdf7-41d7-8345-a8e43031b87e · outbound

This paper cites QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:48.982852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5d832f4-0518-4089-a8d9-3d8423848cc7 · outbound

This paper cites an unresolved cited work.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:48.986359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24826879-a826-4232-ac42-41c68bffba9d · outbound

This paper cites QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:48.989424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64712087-cf19-434a-944f-6b54be25b027 · outbound

This paper cites T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:48.992743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efb24032-453f-4e50-b803-dcbde8280db8 · outbound

This paper cites HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:48.996072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4df02f49-60a3-4792-a149-0619fbb829f0 · outbound

This paper cites Hashimoto.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Hashimoto

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:49.535576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e42a08e0-60bc-4220-8ce5-63878fc71b79 · outbound

This paper cites an unresolved cited work.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:25:49.525821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 400c254e-eddc-4625-af79-9feb5ad17ef1 · outbound

This paper cites Statistically-Lossless Quantization of Large Language Models.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Statistically-Lossless Quantization of Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:49.005401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4f0decb-1f5b-4760-a527-879880c9725c · outbound

This paper cites Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-08-14T04:25:49.179484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 04af1690-1950-426b-b9e4-c373f32a19a5 · outbound

This paper cites DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:49.012259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e06e6e43-2985-45e2-87c8-0465531bd89e · outbound

This paper cites vLLM-Moet (repository; descriptive: DeepSeek-V4-class MoE serving on SM120 GPUs with persistent 2-bit expert packs over NVMe and pinned RAM).

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving vLLM-Moet (repository; descriptive: DeepSeek-V4-class MoE serving on SM120 GPUs with persistent 2-bit expert packs over NVMe and pinned RAM)

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:49.515894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2bec8d92-52e5-466b-a12a-61210d4697e7 · outbound

This paper cites Accuracy is Not All You Need.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Accuracy is Not All You Need

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:49.019427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 804963bd-cf91-4382-8eaa-ec7a315292c3 · outbound

This paper cites Divergent Token Metrics: Measuring degradation to prune away LLM components -- and optimize quantization.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Divergent Token Metrics: Measuring degradation to prune away LLM components -- and optimize quantization

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-14T04:25:49.121973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4ccde3f4-8214-4e4a-9ff3-15c671c33880 · outbound

This paper cites CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-14T04:25:49.107408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c383af49-5a7c-433b-ad3e-68aeaa969f7b · outbound

This paper cites Sanfilippo.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Sanfilippo

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:49.505582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e1a069c8-dc89-4dff-9c2e-9281931bdb86 · outbound

This paper cites DeepSeek-V4-Flash-0731 (revision 7872f01b).

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving DeepSeek-V4-Flash-0731 (revision 7872f01b)

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:49.495101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9e5143d5-5eee-4315-abad-5e4cb81cdb52 · outbound

This paper cites Gerganov and contributors.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Gerganov and contributors

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:49.484200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2fd73d22-1828-4cb6-aa1e-dc1da885cc9b · outbound

This paper cites Pointer Sentinel Mixture Models.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Pointer Sentinel Mixture Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:49.040161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6190100d-dd0b-403a-966e-33b0e79c7934 · outbound

This paper cites Janardhan.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Janardhan

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:49.471784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3a112894-877b-42a1-bb6e-12d166e8fc0d · outbound

This paper cites an unresolved cited work.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-14T04:25:49.459791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7603b4ec-8696-460f-82f0-b21852a23531 · outbound

This paper cites OCP Microscaling Formats (MX) Specification, Version 1.0.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving OCP Microscaling Formats (MX) Specification, Version 1.0

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T04:25:49.449732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fed1e404-8828-43a5-ac11-1c4a312ddeb4 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving Measuring Massive Multitask Language Understanding

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-14T04:25:49.053461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.