Pith. sign in

Paper Citation Record · LEDGER

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation

As of 23 August 2026, this Paper Citation Record lists 76 of 76 outbound references and 3 inbound Pith citation observations for arXiv:2605.07711.

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

pith.paper-citation-record.v1
2605.07711 v2

Coverage vector

measured 76 of 76 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-22T10:30:11.309910Z

measured 79 of 79 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T03:23:28.881458Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

76 of 76 outbound references displayed

  • verified exact41
  • verified fuzzy34
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8549e758-dce9-4f57-bc5f-0fad715e6ca8 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Distilling the Knowledge in a Neural Network

Reference 1

Resolution
metadata mismatch
local_arxiv, observed 2026-05-22T10:31:25.066081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:47aa95993bd42fe260665141092a5cc8f2db5bc5d41425432204f967cafff0e4

Observation af48e5ab-6bb9-4fc0-ae8b-2ebaac8f7aee · outbound

This paper cites A survey on model compression for large language models.Transactions of the Association for Computational Linguistics (TACL).

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation A survey on model compression for large language models.Transactions of the Association for Computational Linguistics (TACL)

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.310696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:0d20ff15615ffb818d499910986fea0de3282eb5454e3c1ef4230182aca785d9

Observation 0a88ed71-00d5-4aa9-bc3d-ce2e04eaeb21 · outbound

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

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation A Survey on Knowledge Distillation of Large Language Models

Reference 3

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:25.075162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:28691d4c165e7be4b36be01bde944899d935fd227fe0edf0b5c03c933d714131

Observation 36443ef4-a44b-4948-93c6-41048c5118c6 · outbound

This paper cites Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application

Reference 4

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:25.070537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:dcb6be35385e29fe209813bc474a04411957512983118ce73e6cf39b74a947c6

Observation 8d6d6954-e355-4cda-b9c2-fba48f35ae0e · outbound

This paper cites DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.325482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:a21f74ab7e4dcba8d277ec5addf24532f1f7a3721fcd3b43de2e60e78a7e44a1

Observation 96220fd9-8c58-419a-ba16-86ffb73350be · outbound

This paper cites TinyBERT: Distilling BERT for natural language understanding.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation TinyBERT: Distilling BERT for natural language understanding

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.313982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:fd9daaaeeac311553d39079c5bab413dcf8e6a5a7038071c30e2ae2dd9bc2908

Observation f238e125-5aab-468c-8b8b-1073e1edee93 · outbound

This paper cites Compact language models via pruning and knowledge distillation.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Compact language models via pruning and knowledge distillation

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.316756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:93d3e43d61cacf6f2b56ecd44cb70e4a5330d2fb004605ea6d99c36ce61017e9

Observation 2314dd3a-64a8-4d25-9d39-2756b23a5c98 · outbound

This paper cites Scheduled sampling for sequence prediction with recurrent neural networks.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Scheduled sampling for sequence prediction with recurrent neural networks

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.319207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:c22abe6e46cb273d59608621d2474338e8a9bf8bc9bfc73692e0ef5318fbff94

Observation 10dd729b-74db-4cbb-9179-c1428f0b05e2 · outbound

This paper cites Bridging the gap between training and inference for neural machine translation.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Bridging the gap between training and inference for neural machine translation

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.321999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:b6a451873692256555d723c239a61d8257068ad86fb620b2bb3a633bec7075ae

Observation 1fa5dbc5-0c5f-4964-85fc-90c2f18fc486 · outbound

This paper cites Autoregressive knowledge distillation through imitation learning.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Autoregressive knowledge distillation through imitation learning

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.328760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:8e8ebfb1e3bb9e2ed06c86f9d47c8f72229bd0db299c0f0234e567908ca0b01c

Observation 686634e9-2fba-44ba-af95-44e892d9e807 · outbound

This paper cites SequenceMatch: Imitation learning for autoregressive sequence modelling with backtracking.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation SequenceMatch: Imitation learning for autoregressive sequence modelling with backtracking

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.331373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:6a95e2bdb4a481d7913a325e71e1216794d354ace7e50c99d2b22eb09967bcbe

Observation 466b4737-e24c-4c56-8072-b387906be992 · outbound

This paper cites Gordon, and J.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Gordon, and J

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.267046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:525905fc960dfc65db59d30c14bf6bf160e22e9196fae129e077ba42ac8edf75

Observation 125aecf9-17ee-45ff-a818-6971c3c490b7 · outbound

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

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation On-policy distillation of language models: Learning from self-generated mistakes

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.256206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:51a3bcc6f1015b008ec84b61a338418f9d9854f6205787173a6b8c95d40874cb

Observation 7cc398f4-1d2b-43f7-b469-24d5072b363f · outbound

This paper cites MiniLLM: On-policy distillation of large language models.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation MiniLLM: On-policy distillation of large language models

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.248703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:6e3011c80fb2a1b2e6f23758f78cebbf5b08523d8f59f20b3dbbb41faa20ef55

Observation 47ba3cce-fc5e-4be3-97ef-85f27579f7eb · outbound

This paper cites DistiLLM: Towards streamlined distillation for large language models.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation DistiLLM: Towards streamlined distillation for large language models

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.251123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:63a32e25fa3a0442536d21d02c395960242f16c45d2bc46ad6ec0fa8a929de51

Observation c7830ddc-a084-40e0-87af-b06b006357e3 · outbound

This paper cites DistiLLM-2: A contrastive approach boosts the distillation of LLMs.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation DistiLLM-2: A contrastive approach boosts the distillation of LLMs

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.245803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:84bace8da4e36344eeeb59ee45d46e64f30c15c3f0044098902df6cfa581151e

Observation 66ad1212-8fe8-4e5e-95ec-2c95a7f4b1e1 · outbound

This paper cites Black-box on-policy distillation of large language models.arXiv preprint.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Black-box on-policy distillation of large language models.arXiv preprint

Reference 17

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:25.014689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:ea15138b11397ce7df5adea5dc8fc02b84c6b39c297b931370ad29fb6268468d

Observation e142e345-4795-4a0c-a9f6-4bb9dfe67535 · outbound

This paper cites Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation

Reference 18

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.948934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:b487cd84314909368d15c39b3386cce87519016e6e9ea52cef9d415cf78a95c0

Observation 399b0f2b-b924-40bf-8f0f-8ded6107bf2c · outbound

This paper cites Stable On-Policy Distillation through Adaptive Target Reformulation.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Stable On-Policy Distillation through Adaptive Target Reformulation

Reference 19

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.924363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:bd0621d26afeb9e9475b785d9e5d2f07d61597bcc7d8e3e12e7066c8f3f5d4d1

Observation be246533-0e02-4166-bdcd-5519e6123a12 · outbound

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

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Reference 20

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:25.057400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:281f806ab406ed60fbf8d923cb2215c1271dd7de5c9817ce142a9efa3493d253

Observation a61bab5c-f4ff-4566-b708-8686eafd9bd0 · outbound

This paper cites On-Policy Context Distillation for Language Models.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation On-Policy Context Distillation for Language Models

Reference 21

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.929036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:b0ba40780054987d7b62aababba04eba6ca89685b713647b684496d2fb880a3d

Observation 7ebbc276-9519-486a-9d20-32380de130de · outbound

This paper cites A Survey of On-Policy Distillation for Large Language Models.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation A Survey of On-Policy Distillation for Large Language Models

Reference 22

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.872717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:a5b126bc58f36033a297a14e1343a0b5af60cdf049689b02f43f5ad6d2793c3b

Observation 9ca60856-3bb1-4c96-8b45-efb57e7efff0 · outbound

This paper cites Towards cross- tokenizer distillation: The universal logit distillation loss for LLMs.Transactions on Machine Learning Research (TMLR).

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Towards cross- tokenizer distillation: The universal logit distillation loss for LLMs.Transactions on Machine Learning Research (TMLR)

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.259435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:24009da3d12b35ecb96f7e943ce93c0e762ebd99613bf362268a5a3dc46e3ef2

Observation 453ac5c3-d231-4f8f-a546-7560bdfbf53d · outbound

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

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Dual-space knowledge distillation for large language models

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.261848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:556edad73773d805b21c616abb75bc97144c9eae1ab91130c295138f723d0245

Observation 6c81ce92-bf38-46be-ad61-5e71250817ee · outbound

This paper cites CTPD: Cross-tokenizer preference distillation.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation CTPD: Cross-tokenizer preference distillation

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.240170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:b85d35048b5d8681acc893c59c6af8ae5ae0a61b03ee07909cd98cd4a9153797

Observation e94aa396-9efa-4454-87c9-3771530ca835 · outbound

This paper cites Cross-Tokenizer LLM Distillation through a Byte-Level Interface.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Cross-Tokenizer LLM Distillation through a Byte-Level Interface

Reference 26

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.919240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:7daba19caa7e20ae79c172877127def9e1a0abaf337f048ef9a0fac12b8d307a

Observation bcf99f3e-8369-4d2d-a207-14dbf0dc20a6 · outbound

This paper cites Cross-tokenizer likelihood scoring algorithms for language model distillation.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Cross-tokenizer likelihood scoring algorithms for language model distillation

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.243307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:47f6734d532e75142a071aaf5586139fafeb580467a8fbca4efa220976b0c343

Observation 8d700067-9a2e-4645-b2e8-2446ec94167b · outbound

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

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Multi-level optimal transport for universal cross-tokenizer knowledge distillation on language models

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.253850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:f4751e5d3622b06078f1bb1b61becf64b073ea6e7cad2c88e3006c21fac95e33

Observation b21ac0a3-de0e-4dee-a910-61c60f6f448f · outbound

This paper cites Unlocking on-policy distillation for any model family.Hugging Face Tech- nical Report.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Unlocking on-policy distillation for any model family.Hugging Face Tech- nical Report

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.264691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:13c3639433bec3c29f23edb2b087e24eebc259d0ba466997c95605dc25bfdec1

Observation 553e9527-da29-4659-bb92-b03a68df5dfa · outbound

This paper cites A Dual-Space Framework for General Knowledge Distillation of Large Language Models.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation A Dual-Space Framework for General Knowledge Distillation of Large Language Models

Reference 30

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:25.009565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:5b7ec01d1bc3c81a3f40ec74bb012795bbe94666cc7d1fb228d66a6fc2b5845f

Observation cfd8a466-b732-4546-8613-9e547430cc5d · outbound

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

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Universal cross-tokenizer distil- lation via approximate likelihood matching

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.307634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:f5a419199ed73d4cb2d7226b1e542fda29d53ea63e732b3a8c5a964de36b64bb

Observation 0bd8cbca-a72e-478b-983c-c6eaee16a292 · outbound

This paper cites Enhancing cross-tokenizer knowledge distillation with contextual dynamical mapping.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Enhancing cross-tokenizer knowledge distillation with contextual dynamical mapping

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.300933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:c506ff3d70d1a2821556756850257bfb8cbc503a89544f9784a080dfa4c1c8cd

Observation 7acfc3b5-85fc-4361-915b-dd915433c23f · outbound

This paper cites Entropy-Aware On-Policy Distillation of Language Models.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Entropy-Aware On-Policy Distillation of Language Models

Reference 33

Resolution
verified exact
arxiv_id, observed 2026-05-25T03:02:00.585154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:d7b606b4e584a28335d5b705c378083a22659c230071cf53a77d837dda24a227

Observation 404e92e6-9f3e-482d-b176-9694138df48a · outbound

This paper cites On-policy distillation.Thinking Machines Lab: Con- nectionism.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation On-policy distillation.Thinking Machines Lab: Con- nectionism

Reference 34

Resolution
verified exact
doi, observed 2026-05-22T10:31:24.604857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:d03c7b80a016b5875832f954781a7e236f2413bf3dbade41d86f7d783936a842

Observation 8a737bd3-4106-44c6-8487-7e92377b2f4c · outbound

This paper cites Rethinking kullback- leibler divergence in knowledge distillation for large language models.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Rethinking kullback- leibler divergence in knowledge distillation for large language models

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.298080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:28dedf0b272e5595bcb4b40d25ba1c3fb39389508640e4c2db3a2eb6d32c3604

Observation 31d52e4e-afdd-4575-92af-cbb3d1bd6ff1 · outbound

This paper cites Diversity-aware reverse kullback-leibler divergence for large language model distillation.arXiv preprint.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Diversity-aware reverse kullback-leibler divergence for large language model distillation.arXiv preprint

Reference 36

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:24.893425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:d26161f744ba2bef262ff2c4d3bc83a38d970e3f845bc27077ed778253998e35

Observation 249ffbe9-e50b-4394-af92-6af5f9c48a57 · outbound

This paper cites Distillation of Large Language Models via Concrete Score Matching.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Distillation of Large Language Models via Concrete Score Matching

Reference 37

Resolution
verified exact
arxiv_id, observed 2026-06-02T02:03:33.414151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:715135017a5c7de4751b0795a22a9396957a14c2cf907b1ec3044f060c79032c

Observation 73bf2b2b-824b-4401-91ff-ae91195b2d85 · outbound

This paper cites Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes

Reference 38

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.909338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:bf472c11a8fa66fa066090a84ff4a18bc27a4ca2014278c112e8825b73ff81b5

Observation 7fe0deee-7897-42be-933b-99cc0d00aab8 · outbound

This paper cites SelecTKD: Selective token- weighted knowledge distillation for LLMs.arXiv preprint arXiv:2510.24021.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation SelecTKD: Selective token- weighted knowledge distillation for LLMs.arXiv preprint arXiv:2510.24021

Reference 39

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:24.968412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:10c0225971436f4466d246fb0aa93d59ef66baa342435a55c99c36d6a68ba69a

Observation 6c11ab24-9855-4558-ad37-27925e088f1f · outbound

This paper cites TIP: Token Importance in On-Policy Distillation.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation TIP: Token Importance in On-Policy Distillation

Reference 40

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.987784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:ce5561e621e2bfc615690e0bd8cbc1e3b9de6b1607134c962b320528076de3ea

Observation 4d8127ea-ec13-4f58-8c68-be3479703d51 · outbound

This paper cites CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation CoT2Align: Cross-Chain of Thought Distillation via Optimal Transport Alignment for Language Models with Different Tokenizers

Reference 41

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:24.953607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:a07d52efb0f823c4afd4773931a28f75fda94a85a45d8358c5aa3967acc75044

Observation 710f1158-0682-4a8c-9830-017415089391 · outbound

This paper cites Dual-space knowledge distillation with key-query matching for large language models with vocabulary mismatch.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Dual-space knowledge distillation with key-query matching for large language models with vocabulary mismatch

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.304143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:c727b08a9635e2827a0665f876a8a541daccd3538c9bc6528635aa30bed06a1a

Observation 23f87d62-9081-46dd-b412-15cfef0d1ca4 · outbound

This paper cites Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling

Reference 43

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:24.898822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:e5cb1dbd79408a0bca1273fba89dd54b6f25eb337d2df5eb598c1e1bc065dbc2

Observation bbed16a3-cd01-45b9-a0d2-27690b131f26 · outbound

This paper cites MoL: Mixture of layers in cross- tokenizer embedding model distillation.Knowledge-Based Systems.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation MoL: Mixture of layers in cross- tokenizer embedding model distillation.Knowledge-Based Systems

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.295854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:db1d8c56468fa5c6bd0ea840693d36f08a743922fa3d55f4faad098bcf1f758b

Observation c9de98d9-5b9b-45c6-ac79-8859f7241f82 · outbound

This paper cites Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

Reference 45

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.903973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:e693b6fc0c2dd2447e48027630b2728a242ebf5de953508acf6c98548fefb7b3

Observation d84de946-a0d9-48d2-9f41-cafef7bdfe26 · outbound

This paper cites Qwen2.5 Technical Report.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Qwen2.5 Technical Report

Reference 46

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:25.003761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:a8402ffa668b8c187096fcf0ca58ce60b56a2c684f159f0a8e7d062601ab4004

Observation 18d09668-4518-4b80-b812-32da377dc361 · outbound

This paper cites Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs

Reference 47

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.938742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:7d917af8a8773badf7c363d42065d250a543645401f874399ddec94b549a7bc9

Observation aa28bac4-94bc-4b2e-bc94-7efe0f204666 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Gemma 2: Improving Open Language Models at a Practical Size

Reference 48

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.957775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:add959ee8058907536570a5f8eaddfc3e4806a2c898911ce23883d43b38b7426

Observation f143c7d4-8b97-4eec-8fae-7f2f904de02a · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Training Verifiers to Solve Math Word Problems

Reference 49

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.882819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:d79dff29349deccae88f1772b355182c68b75df1af01c4b3a31033e3eb133399

Observation 89d3c712-0683-41c9-bb0d-164eb1299a2e · outbound

This paper cites Orca-Math: Unlocking the potential of SLMs in Grade School Math.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Orca-Math: Unlocking the potential of SLMs in Grade School Math

Reference 50

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:24.877899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:7e4246c0cc1c0a65c59d16a001d8bf8451c490746fb883d2b480a7c57043b489

Observation 00fa99fc-893c-4635-b27f-721c2ea0447d · outbound

This paper cites OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset

Reference 51

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:24.888136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:5c1ef72ee917c5c74b69cc94ed90953dc2e9608f5cbf970084905ccbc18b4e04

Observation f3187a92-4d82-49da-a911-3613ea196931 · outbound

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

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Measuring mathematical problem solving with the MATH dataset

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.288577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:3d5757e34c8131a4fbbb406364b651fe1287a18e2b6183c5d6be98d4a66eb318

Observation 50a37ed7-eed9-421c-861d-4b004b9c2bc6 · outbound

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

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs

Reference 53

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:25.025236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:20f9b2ea37d554c1349d1cc2550e98dee71220ec7b04c9efac45d4fe1cb47432

Observation 953d47c2-8f7f-47d5-9625-98c6e36cf3d1 · outbound

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

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding

Reference 54

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:24.914644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:f543675d97f5afce47a5ff5fec87d62c340fd4e36c02e32fcff8c5d98109fd5d

Observation 3fa173a6-78a0-4f7f-8aa9-77a3cff314a4 · outbound

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

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation TACO: Topics in Algorithmic COde generation dataset

Reference 55

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:25.030496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:44750c479d9adfbf949aad00ef1e248187b078cab64d1309d56e908a0e973617

Observation 8da825b1-4fc9-4cc4-be84-207ae85616cb · outbound

This paper cites Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando de Freitas, Koray Kavukcuoglu, and Oriol Vinyals.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando de Freitas, Koray Kavukcuoglu, and Oriol Vinyals

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.282958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:f4c15b5313e6fd11cff9d0ff9ea16385744e56e26ebe2123d72158bcc40e9a7c

Observation 42deac3c-0e99-458e-9a09-15aa2528a8b4 · outbound

This paper cites Let’s verify step by step.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Let’s verify step by step

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.285657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:0187ce5f472f9fc52876e9576b31e13f8b83f26ff3185c06ed78db9b444b5f92

Observation effc5120-8fa5-49d7-8ab0-8e9d51a4f24d · outbound

This paper cites Program Synthesis with Large Language Models.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Program Synthesis with Large Language Models

Reference 58

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.983076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:58db257ede3c0e600cdf44fa7b3799d27852fd3eeefc7ca1eb9e32262e5ae493

Observation f24958e5-e8bd-4dc4-8df7-7ee6e6f045e3 · outbound

This paper cites LiveCodeBench: Holistic and contamina- tion free evaluation of large language models for code.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation LiveCodeBench: Holistic and contamina- tion free evaluation of large language models for code

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.291058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:6b1cb23b7bd03d136503267b5b64af12aa1a08abaf66bae332bfc8a92dc53d9d

Observation f9313a53-396e-47b7-99a6-774415001a3b · outbound

This paper cites KDFlow: A User-Friendly and Efficient Knowledge Distillation Framework for Large Language Models.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation KDFlow: A User-Friendly and Efficient Knowledge Distillation Framework for Large Language Models

Reference 60

Resolution
verified exact
arxiv_id, observed 2026-07-20T02:18:26.584736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:566b21cbeb265064c5ccf26119ee5591111cbc7fa84b5fa3fec7794046ce921e

Observation 566ae296-2c72-45bf-ad53-687a1f995064 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Evaluating Large Language Models Trained on Code

Reference 61

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.978298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:29ca57ff7228d4885b336d585034a984f65c439ea4ac13a39ea22a90a9f8422b

Observation 11d440ab-8c10-4105-bf2a-f8cc43dba56a · outbound

This paper cites AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts

Reference 62

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.963224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:969fc51a256b24e54e70565f4cf6dc054c97b05b45fe91ca5e23f2074a7595a3

Observation dafe7bab-2136-41e1-b0ba-bce6a75f03dd · outbound

This paper cites Limi: Less is more for agency.arXiv preprint.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Limi: Less is more for agency.arXiv preprint

Reference 63

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:25.046731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:7433d19bddb052f98ccaabd947c17223e4134a8d326c0ec184a12380690d939d

Observation e398d7d2-159e-4e13-810a-92297cf278d1 · outbound

This paper cites Innovatorbench: Evaluating agents’ ability to conduct innovative LLM research.arXiv preprint.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Innovatorbench: Evaluating agents’ ability to conduct innovative LLM research.arXiv preprint

Reference 64

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:24.998718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:d4fc8c310277382bc77472f72ce2ea3119935deff731559652eca6f9f0f92451

Observation 3193cbd0-6254-4478-b465-c5d9c275ed49 · outbound

This paper cites davinci-dev: Agent-native mid-training for software engineering.arXiv preprint.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation davinci-dev: Agent-native mid-training for software engineering.arXiv preprint

Reference 65

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:24.933866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:f4e6c50450478577ae3caa981f94f2b24b01d604fcdb0d081c3cf38af8331ab3

Observation d67ebaee-5165-4ad2-9b6e-1a49cc54c929 · outbound

This paper cites Longcli-bench: A preliminary benchmark and study for long-horizon agentic programming in command-line interfaces.arXiv preprint.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Longcli-bench: A preliminary benchmark and study for long-horizon agentic programming in command-line interfaces.arXiv preprint

Reference 66

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:25.052265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:ea3f3419089772f2013b895462394207a12fb72d7f7d530622f5d7b7fe4ed9b3

Observation b111961e-db7b-43c3-baa5-c1943ecac06b · outbound

This paper cites davinci-env: Open swe environment synthesis at scale.arXiv preprint.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation davinci-env: Open swe environment synthesis at scale.arXiv preprint

Reference 67

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:25.041586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:f54d538bf9816b86d33d200a03be84ca5c996d82d96122d2e654ac4c1f121afd

Observation ccd73136-28dc-482d-bd3f-33d78582db62 · outbound

This paper cites Argo: Asynchronous rollout with human guidance for research agent optimization.OpenReview preprint.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Argo: Asynchronous rollout with human guidance for research agent optimization.OpenReview preprint

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.277689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:f4120dc04096b868a844d6e957c383d8538f12e5aef3a0279e8afe0e7154ceec

Observation 2d033aab-3719-44d3-b4af-1b427e359efe · outbound

This paper cites SOD: Step-wise On-policy Distillation for Small Language Model Agents.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation SOD: Step-wise On-policy Distillation for Small Language Model Agents

Reference 69

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:25.020076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:e837828affe803c9415df6353b7dbdb81d53d04fa4984d627735b77f0e56973f

Observation 098fdcfe-07fe-4f87-90ca-4883bd96ca9d · outbound

This paper cites Unifying group-relative and self-distillation policy optimization via sample routing.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Unifying group-relative and self-distillation policy optimization via sample routing

Reference 70

Resolution
verified exact
arxiv_id, observed 2026-05-22T10:31:24.973244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:d8b04f1723b352d0281bbd814720c5522b4a6436b7d2a4c0b401700c83b33f0a

Observation 1f973ef5-b0b6-4ec9-8a57-4e492e5060ca · outbound

This paper cites Robust preference optimization via dynamic target margins.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Robust preference optimization via dynamic target margins

Reference 71

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.274799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:e13de4834c9cf2ace51e0ec363ccae052468acf8f246f003276661111353d61e

Observation 1afe7701-4a14-4083-9a73-96b7b3367942 · outbound

This paper cites Lamp- val: Large language models empower personalized valuation in auction.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Lamp- val: Large language models empower personalized valuation in auction

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.280279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:fab76bb1ad6d8a87fae9897d5e8cb61d38c612dac3131ad527247701d32139e2

Observation 0b05ab3e-22db-4a9e-b75c-79f437d8cdff · outbound

This paper cites SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs

Reference 73

Resolution
verified exact
local_arxiv, observed 2026-05-22T10:31:24.993262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:8f4f27df70c8d9d6ac8619c8ff7a201ed70deb33cf496f8ebe33dedc4655d0b2

Observation 2dfe962b-fa5a-40f9-bdf0-421e1a7f2f69 · outbound

This paper cites A simple data augmentation for graph classification: A perspective of equivariance and invariance.ACM Transactions on Knowledge Discovery from Data, 19(2): 1–24.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation A simple data augmentation for graph classification: A perspective of equivariance and invariance.ACM Transactions on Knowledge Discovery from Data, 19(2): 1–24

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.293405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:c7c447d7cfbcd995544844ab13597c9b93f17c5204697c63870bc32c7681b484

Observation 3dbca49b-d9fa-4874-9a8e-367e36a9a103 · outbound

This paper cites A unified invariant learning framework for graph classification.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation A unified invariant learning framework for graph classification

Reference 75

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.269695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:20d389063bc0d6e105a9aa8628af7a373f5fec9d4775e4d1146f9b6f75c8485d

Observation 2b1d17f7-05eb-493b-bbe3-f90c5c401079 · outbound

This paper cites Since 10000 = 7×1428 + 4 , the remainder is 4.

SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation Since 10000 = 7×1428 + 4 , the remainder is 4

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-05-22T10:31:26.272187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

source=pdf_text observed=2026-05-22T10:30:11.309910Z digest=sha256:0e72401e7f5630ddcc0b05f1b2d9c3dc67e374edf790f6309c69974ea522961e

Pith citing papers

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

Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization cites this paper.

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 dca3f7a3-3a99-4865-9d75-5e546c4d2051 · inbound

Group-Reflective Self-Distillation for Agentic Reinforcement Learning cites this paper.

Group-Reflective Self-Distillation for Agentic Reinforcement Learning SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation

Reference 6

Resolution
unresolved
no resolver link, observed 2026-07-31T18:36:16.782544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-31T18:36:16.782544Z digest=sha256:d884976e4b1afae646a34f5397733486a39fc4a33e4778a1258ada276558a55a

Observation b6733b28-0330-44a9-a61d-f415abe92211 · inbound

Group-Reflective Self-Distillation for Agentic Reinforcement Learning cites this paper.

Group-Reflective Self-Distillation for Agentic Reinforcement Learning SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-04T03:23:28.881458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T03:23:28.881458Z digest=sha256:3666e31f0b05f3183670f62a7f3855ee8334ca349a162fe3949c02d3f36f321d