Paper Citation Record · LEDGER

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models

As of 6 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 2 inbound Pith citation observations for arXiv:2605.11854.

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

pith.paper-citation-record.v1
2605.11854 v2

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T22:59:53.100421Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-22T09:51:52.886663Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-22T09:54:46.945960Z

Reference resolution

36 of 36 outbound references displayed

verified exact23
verified fuzzy11
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation eab51550-fc8b-44bc-89cd-4a138452283d · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Kimi K2: Open Agentic Intelligence

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.889577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 84d72b43-e721-46fd-a0ff-eba26bd3aaf6 · outbound

This paper cites OpenAI o3 and o4-mini system card.https://openai.com/index/o3-o4-mini-system- card/.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models OpenAI o3 and o4-mini system card.https://openai.com/index/o3-o4-mini-system- card/

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:04:12.924279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 54069b58-8601-4b70-9338-c860688624fd · outbound

This paper cites Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Haowei Zhang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Li, Hui Qu, J.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Zhang, Han Bao, Hanwei Xu, Haocheng Wang, Haowei Zhang, Honghui Ding, Huajian Xin, Huazuo Gao, Hui Li, Hui Qu, J

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:04:12.933461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1cd941f5-e788-481d-8f93-b35b00d2bfac · outbound

This paper cites DeepSeek-V3 Technical Report.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models DeepSeek-V3 Technical Report

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.903170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 220f7acc-172b-4cfc-911f-1c5033b265ad · outbound

This paper cites Attention Is All You Need.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Attention Is All You Need

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.849849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1bec48ee-f3f8-4fb2-8225-73a4bf32216e · outbound

This paper cites Dream 7B: Diffusion Large Language Models.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Dream 7B: Diffusion Large Language Models

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.898916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 528d2412-b4a0-49f9-90a3-42bee9283cdd · outbound

This paper cites Large Language Diffusion Models.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Large Language Diffusion Models

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.868817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 90a1b107-7e57-40cd-8e1b-036f80ad8d5d · outbound

This paper cites Principled rl for diffusion llms emerges from a sequence-level perspective.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Principled rl for diffusion llms emerges from a sequence-level perspective

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:03:50.894412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 025ce3b4-5195-40f3-8679-f8d41590c214 · outbound

This paper cites DARE: Diffusion Large Language Models Alignment and Reinforcement Executor.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models DARE: Diffusion Large Language Models Alignment and Reinforcement Executor

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.923855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bce251f0-304e-4e96-b9a9-740543934d3d · outbound

This paper cites Taming masked diffusion language models via consistency trajectory re- inforcement learning with fewer decoding step.arXiv preprint arXiv:2509.23924.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Taming masked diffusion language models via consistency trajectory re- inforcement learning with fewer decoding step.arXiv preprint arXiv:2509.23924

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:03:50.837131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 68d25a2a-38cd-4774-ae6d-bf2d0af9b260 · outbound

This paper cites dinfer: An efficient inference framework for diffusion language models.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models dinfer: An efficient inference framework for diffusion language models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:03:50.829239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ccaa7908-468b-4207-90d8-4b1f3546b02e · outbound

This paper cites Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.879974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c6cccd3f-973a-46bc-9fd5-88de5161d519 · outbound

This paper cites T3d: Few-step diffusion language models via trajectory self-distillation with direct discriminative optimization.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models T3d: Few-step diffusion language models via trajectory self-distillation with direct discriminative optimization

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:03:50.855239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 228ff3c1-5745-4e3b-8f0b-1b745805f54d · outbound

This paper cites Ling-coder-sft.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Ling-coder-sft

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:04:12.903865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 221cfac3-0b5a-41ea-b2da-0fea17825414 · outbound

This paper cites Mixchain-z-prm12k.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Mixchain-z-prm12k

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:04:12.890590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ccd78b6d-e216-456f-9812-c9443c39087b · outbound

This paper cites A convergence theory for diffusion language models: An information-theoretic perspective.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models A convergence theory for diffusion language models: An information-theoretic perspective

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:03:50.874263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6cb9a7c2-12a6-4e46-b1fc-971feac7b038 · outbound

This paper cites Mercury: Ultra-Fast Language Models Based on Diffusion.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Mercury: Ultra-Fast Language Models Based on Diffusion

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.863996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ad262fdb-6fe1-4080-aaff-d8ee6a0a392b · outbound

This paper cites Large language models are overconfident and amplify human bias.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Large language models are overconfident and amplify human bias

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:03:50.885087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c6d8abe8-e3a9-4aed-86cf-b871d55e1f69 · outbound

This paper cites an unresolved cited work.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-05-20T23:04:12.886271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c30e4d21-cab1-445d-8072-e61f546b1df7 · outbound

This paper cites d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:03:50.842115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5dacf01e-771f-44e7-906c-72b26122b51c · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models LoRA: Low-Rank Adaptation of Large Language Models

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T23:03:50.845934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e1f38095-9724-463b-a0ac-95c84cb71c2b · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Training Verifiers to Solve Math Word Problems

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.937695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3bbd7f1e-61c7-490c-8cfa-e4130ce0c57e · outbound

This paper cites Measuring mathematical problem solving with the math dataset.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Measuring mathematical problem solving with the math dataset

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:04:12.913915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ffc9a83e-2623-4aca-99b9-de401af5b4d5 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Evaluating Large Language Models Trained on Code

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.928511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d98d704d-36c5-4cd4-8eff-4ac9747d2b74 · outbound

This paper cites Johnson, Jonathan Ho, Daniel Tarlow, and Rianne van den Berg.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Johnson, Jonathan Ho, Daniel Tarlow, and Rianne van den Berg

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:04:12.882455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 005af592-4a9b-4082-b40d-622a88a0f4da · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Instruction-Following Evaluation for Large Language Models

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.859568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6d5842dc-1b3f-4931-b6a1-2fd8d5095e13 · outbound

This paper cites Deep unsuper- vised learning using nonequilibrium thermodynamics.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Deep unsuper- vised learning using nonequilibrium thermodynamics

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:04:12.919405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 27033a84-5570-4ffc-a26f-b0b23415dc59 · outbound

This paper cites Argmax flows and multinomial diffusion: Learning categorical distributions.Advances in Neural Information Processing Systems, 34:12454–12465.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Argmax flows and multinomial diffusion: Learning categorical distributions.Advances in Neural Information Processing Systems, 34:12454–12465

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:04:12.909625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 36c49e3d-4787-4c40-802d-61ca4e985016 · outbound

This paper cites A continuous time framework for discrete denoising models.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models A continuous time framework for discrete denoising models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:04:12.928747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 359d6aa5-b94e-4546-81fa-fdabad590be9 · outbound

This paper cites Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.907556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6d275e0e-657d-4911-bac7-a112620648fe · outbound

This paper cites Simplified and Generalized Masked Diffusion for Discrete Data.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Simplified and Generalized Masked Diffusion for Discrete Data

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:03:50.933323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5cb8302c-ea15-43fc-aa91-f573fea36020 · outbound

This paper cites Simple and effective masked diffusion language models.Advances in Neural Information Processing Systems, 37:130136–130184.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Simple and effective masked diffusion language models.Advances in Neural Information Processing Systems, 37:130136–130184

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:04:12.899249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 60f615f6-1767-4438-9d55-d2d0ae05b0a9 · outbound

This paper cites Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:03:50.833241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2f34b73a-a24a-490a-aa54-24b687db2aba · outbound

This paper cites Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.912563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 587413fc-d788-4970-bc37-dccc56b0823a · outbound

This paper cites Gemini-diffusion.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Gemini-diffusion

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:04:12.894907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a4266054-f415-47d1-9fa5-a8cda18e8b0f · outbound

This paper cites Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding.

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:03:50.918875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

Observation 188491d8-c880-4fba-9f05-595ef217f6ae · inbound

A Brief Overview: On-Policy Self-Distillation In Large Language Models cites this paper.

A Brief Overview: On-Policy Self-Distillation In Large Language Models Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-20T09:08:10.046250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 39ca590d-88e3-4b0c-9b0d-9bcd2a7bf22c · inbound

A Brief Overview: On-Policy Self-Distillation In Large Language Models cites this paper.

A Brief Overview: On-Policy Self-Distillation In Large Language Models Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-22T09:54:46.948753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.