Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization | Paper Citation Record

Observation 21676a20-9283-477b-a2c4-7211d9a75ed4 · outbound

This paper cites Chi, Quoc V.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Chi, Quoc V

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.183953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed309b3b-a034-4067-90f9-db226c39a324 · outbound

This paper cites OpenAI o1 System Card.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization OpenAI o1 System Card

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.190811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6c921ba-dcca-43d4-8009-7d992da7ee13 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.203426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a291444f-6f87-48bc-8781-6e36955cb643 · outbound

This paper cites GPT-4 Technical Report.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization GPT-4 Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.215100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72397ade-3810-4307-90cd-c9cad81983b1 · outbound

This paper cites Qwen3 Technical Report.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Qwen3 Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.225174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06fb7be2-73b3-4163-88a7-5ee1a4a8690a · outbound

This paper cites OpenAI GPT-5 System Card.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization OpenAI GPT-5 System Card

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.240012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90497c37-03df-4182-8782-82d699a5d9e7 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.258737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31ffd661-f65f-4df9-93da-410722a3819d · outbound

This paper cites GPT-4o System Card.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization GPT-4o System Card

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.289606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee71e704-b984-476e-b143-a545fc7ae4c4 · outbound

This paper cites s1: Simple test-time scaling.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization s1: Simple test-time scaling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.298091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78ed1afc-ab2b-467f-b8a0-1e5592bb984b · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.306925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4717a97-bdcb-43dd-8d4c-ac26d15e086e · outbound

This paper cites Qwen3.5-Omni Technical Report.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Qwen3.5-Omni Technical Report

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.318300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc126cbb-9a3d-4d15-baf1-b948c1ea7f9c · outbound

This paper cites Deepseek-v4: Towards highly efficient million-token context intelligence, 2026.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Deepseek-v4: Towards highly efficient million-token context intelligence, 2026

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.329923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa7a8b2d-0503-4999-a128-6bc6779a2342 · outbound

This paper cites Q-bert: Hessian based ultra low precision quantization of bert.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Q-bert: Hessian based ultra low precision quantization of bert

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.337491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4575af3-a44a-489f-92c5-5e8e65215a9f · outbound

This paper cites Llm.int8(): 8-bit matrix multiplication for transformers at scale.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Llm.int8(): 8-bit matrix multiplication for transformers at scale

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.354953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59edad68-6a84-4af5-9a83-6d178508af55 · outbound

This paper cites Zeroquant: Efficient and affordable post-training quantization for large-scale transformers.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Zeroquant: Efficient and affordable post-training quantization for large-scale transformers

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.362603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd13c95b-49e1-4a9a-b735-bafb695f6a70 · outbound

This paper cites Gptq: Accurate post-training quantization for generative pre-trained transformers.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Gptq: Accurate post-training quantization for generative pre-trained transformers

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.369697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 412761f0-f5e0-4ea6-a443-1397d0dc45b9 · outbound

This paper cites Smoothquant: Accurate and efficient post-training quantization for large language models.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Smoothquant: Accurate and efficient post-training quantization for large language models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.383847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0317fec1-78a5-44f2-9140-ccecb18e9a80 · outbound

This paper cites Omniquant: Omnidirectionally calibrated quantiza- tion for large language models.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Omniquant: Omnidirectionally calibrated quantiza- tion for large language models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.392855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8f1bed9-22be-4427-9951-f1440cfb93e2 · outbound

This paper cites Awq: Activation-aware weight quantization for llm compression and acceleration.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Awq: Activation-aware weight quantization for llm compression and acceleration

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.401374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caa25158-e0bd-41f1-aa81-1f597c33205a · outbound

This paper cites Quip: 2-bit quantiza- tion of large language models with guarantees.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Quip: 2-bit quantiza- tion of large language models with guarantees

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.411975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75293f45-2314-444c-991f-5c7721e4289c · outbound

This paper cites Quarot: Outlier-free 4-bit inference in rotated llms.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Quarot: Outlier-free 4-bit inference in rotated llms

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:16.010217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 108acd64-eb12-405b-882b-042282208b9f · outbound

This paper cites Spinquant: Llm quantization with learned rotations.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Spinquant: Llm quantization with learned rotations

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.975337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f04a75e9-dfd1-4434-aafd-ae76c51121ef · outbound

This paper cites Flatquant: Flatness matters for llm quantization.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Flatquant: Flatness matters for llm quantization

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.939058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a2831ebe-cb83-4a10-840a-dfac094990f3 · outbound

This paper cites Ostquant: Refining large language model quantization with orthogonal and scaling transformations for better distribution fitting.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Ostquant: Refining large language model quantization with orthogonal and scaling transformations for better distribution fitting

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.892020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 71634be5-9dca-4caa-9b25-496abdb24749 · outbound

This paper cites Sliderquant: Accurate post-training quantization for llms.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Sliderquant: Accurate post-training quantization for llms

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.853609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 63aea83c-2e29-4af9-9c3b-f1242b1c1016 · outbound

This paper cites Quantization hurts reasoning? an empirical study on quantized reasoning models.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Quantization hurts reasoning? an empirical study on quantized reasoning models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.820703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d37ab6b1-9ac9-4f12-b93d-d11c2659212d · outbound

This paper cites Ternary Weight Networks.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Ternary Weight Networks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.483709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24411616-67c3-4d90-b532-ccfdabb1f7df · outbound

This paper cites Ternarybert: Distillation-aware ultra-low bit bert.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Ternarybert: Distillation-aware ultra-low bit bert

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.769404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d9262bda-5acc-4291-af87-074e2b16c608 · outbound

This paper cites Bert: Pre-training of deep bidirectional transformers for language understanding.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Bert: Pre-training of deep bidirectional transformers for language understanding

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.726353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 80512ddb-6172-4c7f-acb6-1230553022f2 · outbound

This paper cites Tinybert: Distilling bert for natural language understanding.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Tinybert: Distilling bert for natural language understanding

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.659674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4bf57a6c-6603-47bf-9d8d-cd9bdfcd3370 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Distilling the Knowledge in a Neural Network

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.546231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5aff7d4-0b57-4414-be60-477900ff977d · outbound

This paper cites Bitnet distillation.arXiv preprint arXiv:2510.13998, 2025.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Bitnet distillation.arXiv preprint arXiv:2510.13998, 2025

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.555901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8e79b38-e36c-4578-a5a0-1952bc3680bb · outbound

This paper cites TernaryLLM: Ternarized Large Language Model.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization TernaryLLM: Ternarized Large Language Model

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.562992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45624723-f89d-4255-943c-82f4217ddb47 · outbound

This paper cites The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.570447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06f49d2c-1f83-443f-9507-f7cf92b85e91 · outbound

This paper cites BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.582287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74ad2f48-c5b4-40e5-bffd-519edd6f580e · outbound

This paper cites Spectra: Surprising effectiveness of pretraining ternary language models at scale.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Spectra: Surprising effectiveness of pretraining ternary language models at scale

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.622281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 711933fb-55d9-4aae-9ef0-67a1bacefcc6 · outbound

This paper cites Tequila: Trapping-free ternary quantization for large language models.arXiv preprint arXiv:2509.23809, 2025.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Tequila: Trapping-free ternary quantization for large language models.arXiv preprint arXiv:2509.23809, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.601102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9862e22c-0c56-4000-889e-d56588bab102 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization LLaMA: Open and Efficient Foundation Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.609486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edb2c59d-2d2a-48e6-8bf9-286791ed57ee · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.620545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26324a60-bcfd-4410-913b-5577b54dc1ac · outbound

This paper cites BitNet b1.58 2B4T Technical Report.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization BitNet b1.58 2B4T Technical Report

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.630582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe32b0c1-bbc2-45d6-912a-4c3b9d3409d2 · outbound

This paper cites Bina- rized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Bina- rized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.585718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 21730db8-70b9-4020-b133-c8f33dbb1aaa · outbound

This paper cites Xnor-net: Imagenet classification using binary convolutional neural networks.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Xnor-net: Imagenet classification using binary convolutional neural networks

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.540497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ff7cba95-c15a-46f7-afe1-fd357de9d8c5 · outbound

This paper cites an unresolved cited work.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:17:15.506663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 97747293-edf7-42c5-91af-bc980a9b3aca · outbound

This paper cites Learned step size quantization.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Learned step size quantization

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.454936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 11c3a8a9-e1e9-49b6-a4b6-33be2bec03f2 · outbound

This paper cites Differentiable soft quantization: Bridging full-precision and low-bit neural networks.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Differentiable soft quantization: Bridging full-precision and low-bit neural networks

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.419528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b71ce7fd-e20d-4652-b330-2836e98f3e49 · outbound

This paper cites Paretoq: Scaling laws in extremely low-bit llm quantization.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Paretoq: Scaling laws in extremely low-bit llm quantization

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.389777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9a0c4c70-effa-43ed-bd5b-6080454bad91 · outbound

This paper cites Cat-q: Cost-efficient and accurate ternary quantization for llms.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Cat-q: Cost-efficient and accurate ternary quantization for llms

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.346964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation facdb3ba-d818-48dd-95c2-ef4149178b39 · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.JMLR, 2020.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Exploring the limits of transfer learning with a unified text-to-text transformer.JMLR, 2020

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.312115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 88690fbc-645e-4c30-b1dc-f1b11b61d5a4 · outbound

This paper cites Pointer sentinel mixture models.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Pointer sentinel mixture models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.756316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2f498b3-e13d-4792-8e56-1a928d3e7795 · outbound

This paper cites Metamath: Bootstrap your own mathematical questions for large language models.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Metamath: Bootstrap your own mathematical questions for large language models

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.237505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4e49feb9-6de7-4f98-8740-dc48214b1a9a · outbound

This paper cites OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.779905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ef35f49-5e72-4ec9-a502-6f4203e28358 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Measuring Mathematical Problem Solving With the MATH Dataset

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.788916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9046b8c-5f21-445e-8cb5-fd521cd8a12e · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Training Verifiers to Solve Math Word Problems

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.801219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca12845c-188d-4dcc-977d-4e86d0f4f885 · outbound

This paper cites Omni-math: A universal olympiad level mathematic benchmark for large language models.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Omni-math: A universal olympiad level mathematic benchmark for large language models

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.207372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 039de2f2-0b0e-4193-a1c3-cfbe50e64e22 · outbound

This paper cites Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.165088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7ba1bb99-5701-4a65-a348-df1c7d2aafa8 · outbound

This paper cites Proofwriter: Generating implications, proofs, and abductive statements over natural language.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Proofwriter: Generating implications, proofs, and abductive statements over natural language

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.125915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 81468bd1-7f2a-4a2b-ab00-83b0feaffa69 · outbound

This paper cites Piqa: Reasoning about physical commonsense in natural language.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Piqa: Reasoning about physical commonsense in natural language

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.842887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fc47c7c-4f37-486f-9241-ca215a30f47d · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.852815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 826a3f62-764c-462b-b602-b575f1f3f489 · outbound

This paper cites Hellaswag: Can a machine really finish your sentence? InACL, 2019.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Hellaswag: Can a machine really finish your sentence? InACL, 2019

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:15.047882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0395ca70-30b9-40cc-a095-30fec1b23d5e · outbound

This paper cites Winogrande: An adversarial winograd schema challenge at scale.Communications of the ACM, 2021.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Winogrande: An adversarial winograd schema challenge at scale.Communications of the ACM, 2021

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.906518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fec127c-e692-4f19-933b-7063199d49e9 · outbound

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

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Llm-pruner: On the structural pruning of large language models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:11.915255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a32af85-746a-4b14-85dd-72e8900ef5af · outbound

This paper cites Slicegpt: Compress large language models by deleting rows and columns.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Slicegpt: Compress large language models by deleting rows and columns

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.957971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9e01b0ad-f3ac-443a-8b7c-56cea0bce803 · outbound

This paper cites Sparsegpt: Massive language models can be accurately pruned in one-shot.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Sparsegpt: Massive language models can be accurately pruned in one-shot

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.914443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e97ff74e-9e0d-4915-8e41-46e549f2188b · outbound

This paper cites Spqr: A sparse-quantized representation for near-lossless llm weight compression.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Spqr: A sparse-quantized representation for near-lossless llm weight compression

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.872558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2811fcc9-7a3b-4437-9946-95465627b1d7 · outbound

This paper cites A simple and effective pruning approach for large language models.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization A simple and effective pruning approach for large language models

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.842056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8c5a90f6-0b4c-4eec-bbd7-f6434ebba71a · outbound

This paper cites On the impact of calibration data in post-training quantization and pruning.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization On the impact of calibration data in post-training quantization and pruning

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.800756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 21c46e7b-6814-48ab-b526-34175a044365 · outbound

This paper cites Self-calibration for language model quantization and pruning.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Self-calibration for language model quantization and pruning

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.738162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 253aab65-78eb-48e2-9764-192a96a9dcb6 · outbound

This paper cites Beyond fixed-length calibration for post-training compression of llms.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Beyond fixed-length calibration for post-training compression of llms

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.697112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 74379738-7ed6-4ee3-b05b-5af639d3a3b2 · outbound

This paper cites Outliers and cal- ibration sets have diminishing effect on quantization of modern llms.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Outliers and cal- ibration sets have diminishing effect on quantization of modern llms

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.661973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7839cd1c-8f6e-4d85-a492-203e83dee2f7 · outbound

This paper cites Enhancing computation efficiency in large language models through weight and activation quantization.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Enhancing computation efficiency in large language models through weight and activation quantization

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.618582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2a564a37-809f-46f1-8253-f05bd72269ca · outbound

This paper cites RSQ: Learning from Important Tokens Leads to Better Quantized LLMs.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization RSQ: Learning from Important Tokens Leads to Better Quantized LLMs

Reference 71

Resolution: verified exact; local_arxiv, observed 2026-08-15T15:17:12.423671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4a8d01f3-cb00-4dfe-abe9-fb2ec125219d · outbound

This paper cites Multilingual brain surgeon: Large language models can be compressed leaving no language behind.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Multilingual brain surgeon: Large language models can be compressed leaving no language behind

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.569928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a5a75b8d-8cb8-4319-863c-b7040320f1ab · outbound

This paper cites Mahoney, Yakun Sophia Shao, Kurt Keutzer, and Amir Gholami.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Mahoney, Yakun Sophia Shao, Kurt Keutzer, and Amir Gholami

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.533488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation aa8dfb83-f2a8-46df-8187-c16491756b4d · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Measuring Massive Multitask Language Understanding

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-15T15:17:12.072828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a47006e4-f30a-4d2b-82bc-b691313e20b2 · outbound

This paper cites So, the GCF is 132.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization So, the GCF is 132

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.494128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f7bc60c6-d83a-45d7-a9b8-64ff92b18e0a · outbound

This paper cites So adding 11 to 132 is 143, but that’s not the GCF.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization So adding 11 to 132 is 143, but that’s not the GCF

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.457338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f1da59ae-0ced-48da-9aa1-639c5b045353 · outbound

This paper cites So the answer is 132.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization So the answer is 132

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.416682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e1bc53fc-fc0b-49ec-8f77-259da74f6118 · outbound

This paper cites an unresolved cited work.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Unresolved cited work

Reference 80

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:17:14.331727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 778d9a2e-9b83-4b21-8ee3-b0b2500142b7 · outbound

This paper cites an unresolved cited work.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Unresolved cited work

Reference 81

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:17:14.282046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 21f9ca41-b0a8-4776-bd94-53c9f6b88790 · outbound

This paper cites an unresolved cited work.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Unresolved cited work

Reference 82

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:17:14.242612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 84691f98-7b2f-47db-ad31-6f08581cea87 · outbound

This paper cites an unresolved cited work.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Unresolved cited work

Reference 83

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:17:14.204029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 9538fd72-f824-4dbe-b5e3-e7dfe4889380 · outbound

This paper cites The mathematics problem involves calculating the greatest common factor.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization The mathematics problem involves calculating the greatest common factor

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.157086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cbcc9b02-23eb-4672-9a39-eddb67a0fbb3 · outbound

This paper cites ""Return the largest prime factor of n. Assume n > 1 and is not a prime. >>> largest_prime_factor(13195) 29 >>> largest_prime_factor(2048) 2.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization ""Return the largest prime factor of n. Assume n > 1 and is not a prime. >>> largest_prime_factor(13195) 29 >>> largest_prime_factor(2048) 2

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:14.118771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a4a5042f-0c7c-4b5c-bf78-ff5c54a805a7 · outbound

This paper cites an unresolved cited work.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Unresolved cited work

Reference 86

Resolution: parse uncertain; raw_fallback, observed 2026-08-15T15:17:14.080337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 911bead9-78f4-42e9-8831-61a836434629 · outbound

This paper cites an unresolved cited work.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Unresolved cited work

Reference 87

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:17:14.032618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1caa9b72-ae44-46c8-ad6b-7a37a1a40b5d · outbound

This paper cites an unresolved cited work.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Unresolved cited work

Reference 88

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:17:13.979118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0efda737-5715-4d9b-93cf-09af97dcd4d8 · outbound

This paper cites "" Given a string s, count the number of uppercase vowels in even indices. count_upper(’aBCdEf’) returns 1 count_upper(’abcdefg’) returns 0 count_upper(’dBBE’) returns 0.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization "" Given a string s, count the number of uppercase vowels in even indices. count_upper(’aBCdEf’) returns 1 count_upper(’abcdefg’) returns 0 count_upper(’dBBE’) returns 0

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:13.942853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1164b771-5584-46c5-9a4c-e8abc581e2ae · outbound

This paper cites an unresolved cited work.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Unresolved cited work

Reference 90

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:17:13.886759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation aaa895b5-761d-4d92-8b47-8fdbcabaa511 · outbound

This paper cites an unresolved cited work.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Unresolved cited work

Reference 91

Resolution: parse uncertain; raw_fallback, observed 2026-08-15T15:17:13.833690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b4c09a85-efb5-4fae-b356-7e88451d04ea · outbound

This paper cites ""Return the longest string. Return the first one in case of ties. Return None if the input list is empty.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization ""Return the longest string. Return the first one in case of ties. Return None if the input list is empty

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T15:17:13.763487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4d45b9d9-0f75-4051-93c0-9dc5a32fac72 · outbound

This paper cites an unresolved cited work.

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization Unresolved cited work

Reference 332

Resolution: unresolved; raw_fallback, observed 2026-08-15T15:17:14.365684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers