Pith. sign in

Paper Citation Record · LEDGER

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization

As of 17 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 0 inbound Pith citation observations for arXiv:2607.22334.

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

pith.paper-citation-record.v1
2607.22334 v1

Coverage vector

measured 60 of 60 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T05:09:59.059091Z

measured 60 of 60 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+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

60 of 60 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved59
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7365310a-3fd2-4c91-8c37-fd463320a0db · outbound

This paper cites DeepSeek-V4: Towards highly efficient million-token context intelligence.arXiv preprint arXiv:2606.19348, 2026.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization DeepSeek-V4: Towards highly efficient million-token context intelligence.arXiv preprint arXiv:2606.19348, 2026

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:53.533128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:53.533128Z digest=sha256:12f0ab1a01dfa421a764a46bdc2ddd21be20a7380be7ad7ed03a61754d9c790b

Observation cd133846-5c22-46e3-81f8-834ca7928f53 · outbound

This paper cites Qwen3 Technical Report.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Qwen3 Technical Report

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:53.635437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:53.635437Z digest=sha256:8b4cb9110db0a4e1e6a6e812efa19c20092b7315b772b22c5d3e498ffb93fe13

Observation d732594f-48e5-4513-b631-3cb6958b0350 · outbound

This paper cites Kimi K2.5: Visual Agentic Intelligence.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Kimi K2.5: Visual Agentic Intelligence

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:53.769900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:53.769900Z digest=sha256:49e45bd7e0e0407a4acdf2a23596f6dbfb6e1dd819e2e9da617a094e046c1626

Observation 81c5069c-e91b-4c36-a4f3-c63f21e7e327 · outbound

This paper cites GLM-5: from Vibe Coding to Agentic Engineering.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization GLM-5: from Vibe Coding to Agentic Engineering

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:53.931917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:53.931917Z digest=sha256:28ceb501f3cd553118b44b8a05ac7dd30ea1faa72f7127b91806793313d96c97

Observation 1a63bafd-7342-4889-abcf-deb3614d4e54 · outbound

This paper cites The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:54.047136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:54.047136Z digest=sha256:35566f91ab582ee4eeb57813be901012d292dbeaa9a32fc70e0ba7a7a58d5e9b

Observation 0adee1f2-c634-4bcc-936b-efa9db5f12d7 · outbound

This paper cites LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:54.163495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:54.163495Z digest=sha256:d78c074b5022b7ae586a2c3124fdf05eca00b4a87a67d9ff3024d4c3e3ca7dbd

Observation b073561a-6b0e-484c-b24f-275b34df8314 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Distilling the Knowledge in a Neural Network

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:54.301356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:54.301356Z digest=sha256:6367f35a74d1108031b625ac089068f9775ac90d884c418a517b02cb935ae263

Observation 527674ce-8624-44b4-8ec2-8cc884a1d5c7 · outbound

This paper cites an unresolved cited work.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Unresolved cited work

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:54.378833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:54.378833Z digest=sha256:21e283005c2babe2a548dc28f0be246fee7fc747af35727525c971e8a96cba7b

Observation cda1910b-de80-4f2f-9f09-97e572c4c9bc · outbound

This paper cites A Survey on Knowledge Distillation of Large Language Models.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization A Survey on Knowledge Distillation of Large Language Models

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:54.527286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:54.527286Z digest=sha256:cffe990a0a5f99d7c7919d5e59791cfbe36dbf1bf79fa513e8bd855309aa5523

Observation f81e3e9e-4a8e-4a08-86bf-c0fb9218fe01 · outbound

This paper cites OpenThoughts: Data Recipes for Reasoning Models.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization OpenThoughts: Data Recipes for Reasoning Models

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:54.664811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:54.664811Z digest=sha256:c93e61ab0a5c134cb00e4a7cbbff775f05d3d837a9749a8b5c971481386219c4

Observation d5a86de0-e4b1-4f4a-ab34-0afde5bdb373 · outbound

This paper cites On-policy distillation of language models: Learning from self-generated mistakes.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization On-policy distillation of language models: Learning from self-generated mistakes

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:54.798840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:54.798840Z digest=sha256:635843a34afea41da1e46377732419a2c83595eaef089d65f9fb9c2d07cfd279

Observation fdaad184-6460-44df-b9c0-ad2ca4e56ba6 · outbound

This paper cites Minillm: Knowledge distillation of large language models.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Minillm: Knowledge distillation of large language models

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:54.890205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:54.890205Z digest=sha256:b3bf835ab53df4153d86aee09a5e8abfd4d7a8a9337f6e881685c6c13126f74d

Observation 8a5326e0-a48e-4338-b044-6408ba749207 · outbound

This paper cites Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.005940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.005940Z digest=sha256:516f2a16f567d1aa541795d31c4c0717e366eaadb829a3f778209181f2b41a23

Observation 272defbe-fce9-4c99-8b44-7479c8f90254 · outbound

This paper cites Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.079840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.079840Z digest=sha256:fceb33326692f84dd32012ff902a7da883a5868d36dad19ed86b9b02cb7ae08c

Observation ad52218a-d094-48cc-952d-aa95dcbbd88e · outbound

This paper cites On-policy distillation.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization On-policy distillation

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.134239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.134239Z digest=sha256:1d17f11635d2e254ba6ebd60dfe2adfd5b358324141c13ab0df16ca6ba062296

Observation f5cdebac-d1de-45e6-9fb7-be2a05d6d840 · outbound

This paper cites BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization BiLD: Bi-directional Logits Difference Loss for Large Language Model Distillation

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.240305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.240305Z digest=sha256:d38e8e19cfee24ac9694ba5dfcf806f26bd07c6de2e92d0f6e1a6ceab5e347f8

Observation 51619f70-3fcf-447a-ad0a-4b3ac0ab41f9 · outbound

This paper cites Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.300776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.300776Z digest=sha256:703992720bea6c35ed391104cbf6246d02e9ff17b49618f6f0d170bfed92581d

Observation ca6ac455-a2cd-4ba8-aa96-7ad343eeced6 · outbound

This paper cites Neural Machine Translation of Rare Words with Subword Units.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Neural Machine Translation of Rare Words with Subword Units

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.353518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.353518Z digest=sha256:b8e26d9b9af05587638d371a7c8eb2cf132dbc269ef888004baef7b1b4dab812

Observation 6fb29719-9e50-4869-8026-579ac0f0fa82 · outbound

This paper cites How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.425532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.425532Z digest=sha256:4d975da8f5a82b4c30c7756aab5a7d2678426be798ce9d48274468cc2d61cfa9

Observation 61d92b1d-ed4a-45c7-bb69-b3e5b8ca639c · outbound

This paper cites Knowledge fusion of large language models.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Knowledge fusion of large language models

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.503962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.503962Z digest=sha256:f28ac00a58a71e93aa84fd77185b5c02c6f4efba14667ce2796fdec1d9b093c2

Observation 8613df07-739b-43dd-b405-1fc16399a90c · outbound

This paper cites Towards cross-tokenizer distillation: the universal logit distillation loss for llms.Transactions on Machine Learning Research (TMLR), 2024.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Towards cross-tokenizer distillation: the universal logit distillation loss for llms.Transactions on Machine Learning Research (TMLR), 2024

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.568202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.568202Z digest=sha256:e05e744ac4b60d8aa96d0688468c99272e8aa453548aa0173223c43bd7b015d5

Observation bf2922a7-ccca-4997-a30b-d8fe8f6cbf35 · outbound

This paper cites Dual-space knowledge distillation for large language models.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Dual-space knowledge distillation for large language models

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.629341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.629341Z digest=sha256:6cb59b4008d216982ca60b6f5a27e5e2e05eabb1ef9b9abeb1e428ac8190df83

Observation 10b8f234-55a3-46d7-b704-aea56a737970 · outbound

This paper cites Multi-level optimal transport for universal cross-tokenizer knowledge distillation on language models.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Multi-level optimal transport for universal cross-tokenizer knowledge distillation on language models

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.708924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.708924Z digest=sha256:91740bf906c30ade65a683d28f8e55177483312f051b537ea5df976ed6a04caa

Observation 0743f326-d772-4821-a0d3-8dc764e0d8e9 · outbound

This paper cites Universal cross-tokenizer distillation via approximate likelihood matching.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Universal cross-tokenizer distillation via approximate likelihood matching

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.713114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.713114Z digest=sha256:b430aaeddca3012080bb4422e53735c7878fd60d78a99a89357f4ec9963bfab1

Observation f13018a2-51e7-4c16-b525-ed7205e2ef1c · outbound

This paper cites Unlocking on-policy distillation for any model family.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Unlocking on-policy distillation for any model family

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.735867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.735867Z digest=sha256:aff67879c689b18d346c18eeb312e7ee2843da083ee71b470d05bd7396e2c1f6

Observation bb2ee1b5-0e33-4e06-b1bf-8d1bf51b2bc3 · outbound

This paper cites SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.790864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.790864Z digest=sha256:58fbe21b0d6ace731ac7cfac8c1d95ac4d0481c851affb5ac24be2dfa42cec33

Observation b0df1043-0977-4429-9a4c-38758d5fdf71 · outbound

This paper cites CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.843624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.843624Z digest=sha256:652418042288bca28270e55c03464d569b0eef3256c49db6ceb083a07ee006ad

Observation 7eb94844-1438-4a36-896f-bf3b19ecfd0a · outbound

This paper cites ByT5: Towards a token-free future with pre-trained byte-to-byte models.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization ByT5: Towards a token-free future with pre-trained byte-to-byte models

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.905970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.905970Z digest=sha256:c22d76e737a21ff9da63fca085405dd4c1f0e96cfd4ce988b68560c635ef5a1c

Observation 88ffc778-30f8-497c-b9b9-12c6a14425af · outbound

This paper cites MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:55.974479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:55.974479Z digest=sha256:2d649fe36e60aa0492a96a1d079617b4b785810d5d7450b7faf3c9ddaa22171d

Observation 0799d3ef-482e-4656-ad44-e5616d0dca69 · outbound

This paper cites Byte Latent Transformer: Patches Scale Better Than Tokens.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Byte Latent Transformer: Patches Scale Better Than Tokens

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:56.046733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:56.046733Z digest=sha256:9de757b4aeaf2873a82fd7ea16d57a02e28198cfdd22adbed74e0c3740d792e3

Observation 5e3a80e7-f55b-4e8f-8fe7-d341e0f8bbeb · outbound

This paper cites FitNets: Hints for thin deep nets.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization FitNets: Hints for thin deep nets

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:56.131433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:56.131433Z digest=sha256:601b67188c3a3ab6476797053c9b0576420bf3024e6faf7123512ba9a49e6daf

Observation e9ed172f-9016-49fd-810c-348419d1b448 · outbound

This paper cites Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:56.235298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:56.235298Z digest=sha256:350e940ee71d48ee8aa984b894b7f08c16dc47b3c174de1557226716785b4f25

Observation fa2c8231-2f81-4080-b0bc-d11294536dc0 · outbound

This paper cites Teaching Small Language Models to Reason.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Teaching Small Language Models to Reason

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:56.295699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:56.295699Z digest=sha256:f1058ef4ff32fe61064810fbbfca7a8b42edddb3fcea97ece7ef1e6805788f30

Observation ab4e288a-da65-491c-bd02-cdaba873ad08 · outbound

This paper cites MiniPLM: Knowledge Distillation for Pre-Training Language Models.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization MiniPLM: Knowledge Distillation for Pre-Training Language Models

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:56.368774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:56.368774Z digest=sha256:66539bf40f3ed56d74dd5de6f7fcce1a0cc5e467bb623885d5350aff17db9c86

Observation c0bcfb11-c700-4e58-b363-fce44f7f7460 · outbound

This paper cites UI-Genie: A self-improving approach for iteratively boosting MLLM-based mobile GUI agents.Advances in Neural Information Processing Systems, 38:150376–150411, 2025.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization UI-Genie: A self-improving approach for iteratively boosting MLLM-based mobile GUI agents.Advances in Neural Information Processing Systems, 38:150376–150411, 2025

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:56.432066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:56.432066Z digest=sha256:c5b7d6f1d870e459dd34825ea8f2896413bd74195c57b48d88715fe2eb1a3da2

Observation f83b293e-534a-4639-9eb0-8e576f0e6f5e · outbound

This paper cites UI-Mem: Self-evolving experience memory for online reinforcement learning in mobile GUI agents.arXiv preprint arXiv:2602.05832, 2026.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization UI-Mem: Self-evolving experience memory for online reinforcement learning in mobile GUI agents.arXiv preprint arXiv:2602.05832, 2026

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:56.510436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:56.510436Z digest=sha256:b6064aa1bcc39c75c8b1a180f6e31ff6843b1258eca6f7b4488c659eab1b70fe

Observation a2658691-8d2b-48c8-8943-49620fac2b62 · outbound

This paper cites Autoregressive Knowledge Distillation through Imitation Learning.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Autoregressive Knowledge Distillation through Imitation Learning

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:56.603324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:56.603324Z digest=sha256:f40825629ec87a827c9009f437e6da8cd486243c108f5ed8061fc8eb08ba9ea4

Observation 30c9e008-8908-450b-ab97-922d712edb80 · outbound

This paper cites Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:56.726567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:56.726567Z digest=sha256:31352363e4db3fdf20268aca567410b012a25019c9d6851e441d591ed1975a06

Observation d44d2cca-4c3d-458d-a8bd-74958138efe8 · outbound

This paper cites f-Divergence Minimization for Sequence-Level Knowledge Distillation.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization f-Divergence Minimization for Sequence-Level Knowledge Distillation

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:56.818777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:56.818777Z digest=sha256:c95832867152077bd51ce0a74c355962bbcbf22216f5b0f08e8ff76acb1acb89

Observation 1488b820-6824-4687-954a-28e0b376173d · outbound

This paper cites DistiLLM: Towards Streamlined Distillation for Large Language Models.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization DistiLLM: Towards Streamlined Distillation for Large Language Models

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:56.913028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:56.913028Z digest=sha256:29b9ef7ca030a32762639e29cb2575ee65d8301b896d4b357cdf825b75d9c49f

Observation 3d6f254f-e089-4adb-9c95-cab409fa0e1f · outbound

This paper cites DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:57.003341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:57.003341Z digest=sha256:c0f4f7eb95ba4855c7432406fd36d25f0f75625020288e75ef7706afb9145eee

Observation 657b184c-c03f-4705-abdc-5f2e6df97b51 · outbound

This paper cites Kat-coder-v2 technical report.arXiv preprint arXiv:2603.27703, 2026.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Kat-coder-v2 technical report.arXiv preprint arXiv:2603.27703, 2026

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:57.089734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:57.089734Z digest=sha256:f52b710a21a27e5621b34eaf1f2937fcb030a22538282d3082d41359f23bb0d0

Observation 8105933d-2a93-4051-9f85-ec9be90217da · outbound

This paper cites KAT-Coder-V2.5 Technical Report.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization KAT-Coder-V2.5 Technical Report

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:57.178180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:57.178180Z digest=sha256:f0734fe43078edd98fc8539bc4be0f8a6ddc54c364ebb6868fca9fc89f1e1a2e

Observation cc0f357e-8c9d-4fec-afe6-be75c3e4bd2d · outbound

This paper cites Zero-shot tokenizer transfer.arXiv preprint arXiv:2405.07883, 2025.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Zero-shot tokenizer transfer.arXiv preprint arXiv:2405.07883, 2025

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:57.271305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:57.271305Z digest=sha256:fa2e1c71b969ff91a389955828d959dfec97f37e8c97b11d9fd868c366d31cce

Observation b9bb61d4-4cc3-4a03-a2d2-35d7922e6dd9 · outbound

This paper cites Breaking the ceiling of the LLM community by treating token generation as a classification for ensembling.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Breaking the ceiling of the LLM community by treating token generation as a classification for ensembling

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:57.340958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:57.340958Z digest=sha256:8df07368b1cc85178abefc71ca0a8b90b56c0617ac2185f97db5e47ca3a3f367

Observation 22109fd3-12b5-4ee2-8a50-58873c3837ea · outbound

This paper cites Bridging the gap between different vocabularies for LLM ensemble.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Bridging the gap between different vocabularies for LLM ensemble

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:57.395365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:57.395365Z digest=sha256:8948ef0dab6f611f02334a4ae1fcc5a3792872f3401eb450157e18a7cea68fbe

Observation f447a65a-a3e8-4bb8-a499-dce8ee665cc4 · outbound

This paper cites Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Determine-Then-Ensemble: Necessity of Top-k Union for Large Language Model Ensembling

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:57.457701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:57.457701Z digest=sha256:bf70824c07c34d85010d89a346263554360195fde11e662b28c953e552e34178

Observation eb76f324-2e42-4a7f-8292-0e5c48251517 · outbound

This paper cites Qwen3.5-2b.https://huggingface.co/Qwen/Qwen3.5-2B, 2026.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Qwen3.5-2b.https://huggingface.co/Qwen/Qwen3.5-2B, 2026

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:57.543632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:57.543632Z digest=sha256:9ab41fc6fe8bcce29b04e634093752fb4608d594cb864cea8f3552c4231da6ba

Observation e901e7a8-151d-4e43-b55e-687384cad144 · outbound

This paper cites ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:57.723805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:57.723805Z digest=sha256:70e5ba1a6514d4e92a6afedaae0d6066d113e4ff12fb19dabf8bd48af7aa4a24

Observation f3e9f124-8704-4427-bcee-340c8f19b253 · outbound

This paper cites GLM-Z1-9B-0414: Model card.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization GLM-Z1-9B-0414: Model card

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:57.871797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:57.871797Z digest=sha256:18e21aa403787f99ea2ceea82e0d4adb5e7ea9feca0a95764b4380aa345a053d

Observation c1398cfc-8931-4562-a8a6-8a2d1b78acd4 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:57.981831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:57.981831Z digest=sha256:cc9e36b2449faaf2cc1b47d5ac623dda1bcd45cf3ef2654fd83071f236446dd4

Observation ce7a54d4-7973-4358-91b8-0cf20ab783bf · outbound

This paper cites TACO: Topics in Algorithmic COde generation dataset.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization TACO: Topics in Algorithmic COde generation dataset

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:58.131045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:58.131045Z digest=sha256:895b8c90376492e1ebddde83aaf2740f93f80ff895cb95ffac19dea904969eed

Observation ec07b375-9a8d-4024-bb0c-4d8cabad7f3f · outbound

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

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Measuring mathematical problem solving with the math dataset

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:58.301172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:58.301172Z digest=sha256:ab5435f5264126657c2708184db916cf837965c76a8718ec8b168778285a8820

Observation 3626d464-d741-4a68-9cec-713a2f01c44d · outbound

This paper cites Let’s verify step by step.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Let’s verify step by step

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:58.442901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:58.442901Z digest=sha256:a7d9c77dbc3704ddf5f35b9ba5b1a3eb71084fbd0c70187299ff04c239cdb122

Observation 0deacad6-a97a-4098-9d60-3100c1b5395f · outbound

This paper cites MathArena: Evaluating LLMs on uncontaminated math competitions.https://matharena.ai/, 2025.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization MathArena: Evaluating LLMs on uncontaminated math competitions.https://matharena.ai/, 2025

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:58.559750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:58.559750Z digest=sha256:83b063cc6e08fdabe675d00b80ca5252cc8d3a454c7ade61887df3c3dbc3f3b8

Observation 31d403b7-e71b-4d42-85c5-8ca99a464a83 · outbound

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

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:58.691795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:58.691795Z digest=sha256:1ea92a73a7b905676f96e7f1e847afa1eb824bb9e8101618f9ca07547f034193

Observation 2df03126-c2c6-4b6f-aab6-5f2f0fc4a179 · outbound

This paper cites Livecodebench: Holistic and contamination free evaluation of large language models for code.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Livecodebench: Holistic and contamination free evaluation of large language models for code

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:58.778304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:58.778304Z digest=sha256:21ed3a02f6a043530d2601a0510260caeb972f5492a052f41030aee94e9a3d22

Observation 2733ff5c-365e-48b8-ae58-246c8ada2964 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization Evaluating Large Language Models Trained on Code

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:58.839779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:58.839779Z digest=sha256:a01f5df40583201cf601c2771e18850bb40161ba76b978310eb65ad70b8031ec

Observation 3b5f5768-87a2-432a-88c7-92682d12d1ef · outbound

This paper cites DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-01T05:09:58.972025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:58.972025Z digest=sha256:ad7ebd7402a4514fdeb96fcd4d88f5c244426f2815d30b0ae7cc1fbdc9d7383e

Observation 24bd331e-ab2e-4fc7-b682-51c81dd77a38 · outbound

This paper cites KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding.

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding

Reference 60

Resolution
malformed identifier
no resolver link, observed 2026-08-01T05:09:59.059091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T05:09:59.059091Z digest=sha256:828e314cb893a9ff883e9589e8843dddd7bf04b49e553ab042a1adcbc36cfaa4

Pith citing papers

No inbound Pith citation observations are available.