Pith. sign in

Paper Citation Record · LEDGER

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD

As of 6 August 2026, this Paper Citation Record lists 100 of 128 outbound references and 0 inbound Pith citation observations for arXiv:2607.20145.

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

pith.paper-citation-record.v1
2607.20145 v2

Coverage vector

measured 100 of 128 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T10:42:47.058369Z

measured 100 of 100 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 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

100 of 128 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved99
  • parse uncertain1
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6eefd2aa-ae09-4e8f-8c9a-17bfcd45177f · outbound

This paper cites YouTube-8M: A Large-Scale Video Classification Benchmark.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD YouTube-8M: A Large-Scale Video Classification Benchmark

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:34.395951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:34.395951Z digest=sha256:40f87ea8075e49737325afb04a53047567a5c2848186d5bcbd0f6f0871cc5079

Observation 8208a9ee-5e0a-436c-b810-72276e1534d7 · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2025 , year =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Findings of the Association for Computational Linguistics: ACL 2025 , year =

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:34.505442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:34.505442Z digest=sha256:734b490a002b65a11c6700b83e4e0148bd1b527bb1f97817b3fda389d5babe20

Observation 79b801c9-061f-4453-8d1b-24affb66e7fd · outbound

This paper cites , institution =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD , institution =

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:34.629095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:34.629095Z digest=sha256:0843f9c7952d22364950ee8773dd4f04245f746e2b08e0bc26bc9458ff1f2180

Observation 154e4279-dc39-44ca-9731-d13c3e66f8ec · outbound

This paper cites an unresolved cited work.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Unresolved cited work

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:34.756027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:34.756027Z digest=sha256:238dad3a23fb3ebbedee9d9b6537db088e7fec4620ac360adcaa491a5d12c31d

Observation 04f19e51-a960-46d7-834f-551da8269f6b · outbound

This paper cites arXiv preprint arXiv:2602.09003 , year =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD arXiv preprint arXiv:2602.09003 , year =

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:34.888041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:34.888041Z digest=sha256:4d5991199ff14fb06fcaff1010dc52b31b0c0b7e1a68b3c3a0f128af940eb076

Observation 69397945-f4b1-4735-a598-37d86ec667d0 · outbound

This paper cites an unresolved cited work.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Unresolved cited work

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:35.007541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:35.007541Z digest=sha256:ca8b1f5b5eeb92f57a5c10b33020b99f0b365cd55f9af69f9e0287d53abde5b1

Observation d2d396f0-29b2-4c9e-a5e9-628f9f8a70c5 · outbound

This paper cites an unresolved cited work.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Unresolved cited work

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:35.169126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:35.169126Z digest=sha256:2b80047459f25f47b701b5c0a01cdb9241d1cb82dc6520b4927e17694faded3d

Observation 3a5054b5-6eef-4019-9bd2-92c19f72735d · outbound

This paper cites an unresolved cited work.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Unresolved cited work

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:35.250421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:35.250421Z digest=sha256:2c9f9632918ab2be28bde0a6f19ad197cd5fe6df9af0359aa8f8a7d66067652a

Observation b8ccaa0f-370c-4dd1-9201-89544f60ff63 · outbound

This paper cites Le and Geoffrey E.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Le and Geoffrey E

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:35.337613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:35.337613Z digest=sha256:5aa4ca5eb66b14f9d1375a578cde18bff4967cd6a8a3daf6d963368b3d2654e7

Observation b9eb0a12-f3b2-430d-a395-10d991ef7626 · outbound

This paper cites 9th International Conference on Learning Representations, ICLR 2021 , publisher =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD 9th International Conference on Learning Representations, ICLR 2021 , publisher =

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:35.452315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:35.452315Z digest=sha256:a20891fc9f4d114ae94a38ffb156402e186b455665103ce87eeb795656ce0a31

Observation 52745584-23ac-4c7b-bb3c-a426d845b93b · outbound

This paper cites Journal of Machine Learning Research , volume =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Journal of Machine Learning Research , volume =

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:35.574131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:35.574131Z digest=sha256:bb5ed9ded77c9375d0559ef41cc22d8d2ffc0378ceeb9f5ef0b0ddde3504c49c

Observation db183193-2bae-4f75-90c0-dea1d9eb7d75 · outbound

This paper cites Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2020 , pages =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2020 , pages =

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:35.833233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:35.833233Z digest=sha256:c8332deb437268f352931ba57482555cff1c8a51545b6de3239a109ba873eb8f

Observation e8d259df-08ea-40fd-a384-ac3c16a94b73 · outbound

This paper cites DeepSeek-V3 Technical Report.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD DeepSeek-V3 Technical Report

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:35.990033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:35.990033Z digest=sha256:ea6592a7bd81ed89aebd79958c86879e7e5c779bd436142848ad1049839a0489

Observation 20d5b6b3-ce37-4082-b824-c756f25ef0a8 · outbound

This paper cites Operations Research , volume =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Operations Research , volume =

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:36.162156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:36.162156Z digest=sha256:693f0d4647c2519b23ef04ba0213ae96ce028f5b8a6095d8dd10b44772a7a1b7

Observation a033cb60-25fa-4c53-8662-0b4b7f3c80c3 · outbound

This paper cites Thirty-Ninth AAAI Conference on Artificial Intelligence, AAAI 2025 , pages =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Thirty-Ninth AAAI Conference on Artificial Intelligence, AAAI 2025 , pages =

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:36.267678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:36.267678Z digest=sha256:bb81f0becd2c8615ec5e83c020d8827969299407b2c05160dc9845c637132b74

Observation aa58dfc8-99dd-4924-9822-936c109b5ebe · outbound

This paper cites Proceedings of the NeurIPS 2022 Competitions Track , pages =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the NeurIPS 2022 Competitions Track , pages =

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:36.399044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:36.399044Z digest=sha256:694fc84d9e94c649bd7cb73cdc4bff93f4344c3a80d6d195119a4eba6a67243f

Observation 4bf77e72-c30b-4597-ba83-15c495a34d12 · outbound

This paper cites CoRR , volume =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD CoRR , volume =

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:36.516159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:36.516159Z digest=sha256:b819fbeff70d36234b24ff1c55df77848ff01d2c3f211519e4ec7f7d1f377ce5

Observation d5bb94f7-9dad-4d91-b8a7-dab5011bb25a · outbound

This paper cites 2606.19348 , archivePrefix=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD 2606.19348 , archivePrefix=

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:36.636257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:36.636257Z digest=sha256:f13dc54934de03db385b894f36788675da88275605ffe7e6d6848921ca6cf84a

Observation 9a5d2e95-95a4-4c9d-85f2-00f7c5b57e3f · outbound

This paper cites Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence , articleno =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence , articleno =

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:36.713124Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:36.713124Z digest=sha256:90e7401a0649447266e7c5843a6f2438080f8df4c17945b07c2c0aa4fb26198f

Observation b498da15-0299-4c1c-964e-52520059d5c8 · outbound

This paper cites CoRR , volume =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD CoRR , volume =

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:36.815873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:36.815873Z digest=sha256:2555905f135a6d58532b61ef5785b94b5b52f825de800dfe597c63a95063dc77

Observation 2911d236-a25f-4d04-b852-0b579b7ad06b · outbound

This paper cites French , title =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD French , title =

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:36.902236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:36.902236Z digest=sha256:30875a44b539213c4bace7f957ec3b0fbd036b9259741189ea0fdbe568402ce3

Observation 0b9fc82f-75c8-4a3a-ad94-bc6bd2bf6f85 · outbound

This paper cites Don't Stop Pretraining: Adapt Language Models to Domains and Tasks , booktitle =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Don't Stop Pretraining: Adapt Language Models to Domains and Tasks , booktitle =

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:36.976169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:36.976169Z digest=sha256:1a6eecf32b3ff51c22d214f1d9ecd9ffb0bf49263f5ac5573c593ced1e498844

Observation 99f93e6a-c6c4-410d-9d37-7a1d6681e838 · outbound

This paper cites D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:37.077298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:37.077298Z digest=sha256:6e95a743f460c1037c1a94f122009d3510f1fe676b626d82f312f75073687693

Observation d8bb39ec-05e0-4511-99db-d98c06b3f4f5 · outbound

This paper cites Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages =

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:37.155902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:37.155902Z digest=sha256:59a30fad9e7a3d7a8aa67dddc98560adecaf7ebe81bafb2d7daa641b216f9e3c

Observation 416b8a08-a33f-4710-a2db-18ba5e2dd20b · outbound

This paper cites A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:37.269767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:37.269767Z digest=sha256:ac78b3902c1fe20fddd8cd33f1c641d61ff648428584b45c0fd0337933e18618

Observation b222587a-b2cc-4fb1-809c-de46f66724da · outbound

This paper cites International Conference on Learning Representations , volume=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD International Conference on Learning Representations , volume=

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:37.436480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:37.436480Z digest=sha256:b8e5cd4f500ac788b488d89f509a0157c2118cfb6734e5ad8f32de40c96cfa63

Observation e71e7fcf-2e47-40de-8eae-506038b2a3ba · outbound

This paper cites Proceedings of the 42nd International Conference on Machine Learning , series =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the 42nd International Conference on Machine Learning , series =

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:37.629309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:37.629309Z digest=sha256:9907b7fcb9a23efbf30c260df965c983596eec36640b206067f2c8ff6b058f9f

Observation 380a2f7e-98a9-431c-a51f-648c7fe4dc6c · outbound

This paper cites Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Models Can Model, But Can't Bind: Structured Grounding in Text-to-Optimization

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:37.752074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:37.752074Z digest=sha256:85f1fee6827af99cef4c60ffab2a589ccf268bd3fe59dccd3f77106fae2a7ead

Observation e242bd29-f583-43fa-81d5-72eedc20f9f5 · outbound

This paper cites FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:37.861003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:37.861003Z digest=sha256:82fd26c51057fc8d490ebbcd81fa2ad059e7ee12296f8f1de368625da0321abe

Observation 23df44b5-0d74-4fe3-968a-94a6eff89c5c · outbound

This paper cites Proceedings of the 41st International Conference on Machine Learning , series =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the 41st International Conference on Machine Learning , series =

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:37.963864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:37.963864Z digest=sha256:faa44818d0c760c08be38d55050196f0ee541908ea64c087faf00bd36237e51b

Observation f8940e7f-112c-4a7e-882b-7aa58bea7bd4 · outbound

This paper cites 2025 , howpublished =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD 2025 , howpublished =

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:38.057431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:38.057431Z digest=sha256:6f22824f21d7be738aadfb13734536efb3c00bfeb23e6338d3255eb34f6c851f

Observation 385e47be-37ba-4c22-ae8d-6d6c5f3ea384 · outbound

This paper cites LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:38.162881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:38.162881Z digest=sha256:6e538a826b7f8e2624003b8850042c4c1aef09aa632e964795dfd46183ca3593

Observation cf9773a1-cc42-423c-bd10-39213bc92e38 · outbound

This paper cites 2026 , note =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD 2026 , note =

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:38.275491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:38.275491Z digest=sha256:b0a14961d03ff42441c4fcb678b3b722a8d259630551910c7ed390cd5f682138

Observation 9a0b9cba-3d46-40ff-b8ef-69143f4f2f5f · outbound

This paper cites 2024 , howpublished =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD 2024 , howpublished =

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:38.428107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:38.428107Z digest=sha256:e134b17d702e4b6a6bc123933b2833080679c7cd9d8836cd93b4451667fcb240

Observation 8c536f30-fb4f-44f0-9160-81503247bc6b · outbound

This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:38.539823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:38.539823Z digest=sha256:fedc52220f3c7da9658671c32e63c431380c6a34d2a5bde3a8dff7ada6215bd0

Observation 7f1059b7-b842-469e-bd39-0481fada8adb · outbound

This paper cites FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:38.706619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:38.706619Z digest=sha256:4723a78eb9160ce207c40653ee1754c4a48cf4730a6ea415a2cbe3b9a0ab4f2a

Observation ad47effb-6913-4034-9b36-084bf8e83cc7 · outbound

This paper cites FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:38.861814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:38.861814Z digest=sha256:8a5dbabd5cd0eca70833c654a6919c125e0d82bc168f7be206c6ad1f15d2ba6d

Observation 44ab689c-0f5a-4fd3-9dbb-5236b8176c5f · outbound

This paper cites FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:38.990693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:38.990693Z digest=sha256:cca5755eb8bde887a3515d72ee6ad5cbe6292ebfdaaaed58b136d170541098c4

Observation 9f9ef4d6-2709-4bc6-b948-23ba6defbbbd · outbound

This paper cites an unresolved cited work.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Unresolved cited work

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:39.156942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:39.156942Z digest=sha256:1b5a1a1a83311614db2c0cd045c1256c105ac80b3c297b1fbc360218c746daf7

Observation ac74de85-89ad-49d8-82c2-2622d1e69176 · outbound

This paper cites Liger Kernel: Efficient Triton Kernels for LLM Training.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Liger Kernel: Efficient Triton Kernels for LLM Training

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:39.291065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:39.291065Z digest=sha256:ac39c061d1b7f7f32279e7a418d48b814526c0eddaca1ae9f9de344296be701e

Observation 63e72ea7-bfb6-4f7e-927c-625aa377e615 · outbound

This paper cites FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:39.443501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:39.443501Z digest=sha256:2e2b52fb2e2833c059294056c83471dc33cd5baf643ab6e4d787349b344b0c52

Observation fc494aab-5587-4a4e-bc24-02bb551dc123 · outbound

This paper cites CoRR , volume =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD CoRR , volume =

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:39.608074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:39.608074Z digest=sha256:27618a8bd01b2a3ac16cc7cb0333f3af965c8612531dfd2597c077d5b4ebe094

Observation 099871ff-4128-4c28-9e05-6b5b26590d0b · outbound

This paper cites CoRR , volume =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD CoRR , volume =

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:39.749155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:39.749155Z digest=sha256:3dfbb322da75eae06c576a81037e969505ca3bcf903538350e931c5d5415301e

Observation 00da7b69-8be1-4464-ae4f-fdaf423434fb · outbound

This paper cites FullStack Bench: Evaluating LLMs as Full Stack Coders.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD FullStack Bench: Evaluating LLMs as Full Stack Coders

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:39.936078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:39.936078Z digest=sha256:a6d35cc15b2cfdd7c2f0620b6b984b01ca187b9a06909b906645a1fc9882f3a1

Observation 8f70b291-131c-4bcb-af34-b4b1ede46179 · outbound

This paper cites AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:40.072916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:40.072916Z digest=sha256:c15c23c86f44a235cd29e8d8ce7d33d3c8fcd626eb0cfec7e15b4881ccf18ed7

Observation 30c95f43-8e8d-4f2c-9a16-6f9a634db1b9 · outbound

This paper cites AscendKernelGen: A Systematic Study of LLM-Based Kernel Generation for Neural Processing Units.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD AscendKernelGen: A Systematic Study of LLM-Based Kernel Generation for Neural Processing Units

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:40.202768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:40.202768Z digest=sha256:ecf1306a38362bb9b126186163463b6b9fc40db9690c349bf716c96a91f0076a

Observation 3e6e1acb-a462-42c0-bf8b-c6f28c6cd6a1 · outbound

This paper cites 2601.22760 , archivePrefix=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD 2601.22760 , archivePrefix=

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:40.328346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:40.328346Z digest=sha256:0ecdf58cb1331353695c696afa055e78fa4585b9b4a03960c77429188c7367c0

Observation 43d178ee-cc4e-497d-b8a4-f68008f42d0e · outbound

This paper cites Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence , pages =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence , pages =

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:40.451257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:40.451257Z digest=sha256:381f2a05df113214208dfe005837d55d0f706f4542660711d265289d71975571

Observation 9f1727a9-d708-476f-b026-8f3a487ae30c · outbound

This paper cites CoRR , volume =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD CoRR , volume =

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:40.613279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:40.613279Z digest=sha256:05619469cccf2fc152f85039886166127effc8a5495eac5f66c604fcfa62c7f3

Observation dab65f1b-0784-4b09-b9fd-f8ea70212a38 · outbound

This paper cites Assured autonomy: How operations research powers and orchestrates generative AI systems.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Assured autonomy: How operations research powers and orchestrates generative AI systems

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:40.769321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:40.769321Z digest=sha256:19620d725bb3ab99bd8e647945443174b2de89cab5189487ab90889ff768365f

Observation 5a7c6e1c-cff2-41d6-8c11-e59427dd4536 · outbound

This paper cites Chain-of-Experts: When.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Chain-of-Experts: When

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:40.933327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:40.933327Z digest=sha256:4951505c11bcd5c33debc6ce49498e89cb88baeaf29edf83347f5448b91c6293

Observation 9a8deb74-f374-46f6-a84a-19af9fcb5fc3 · outbound

This paper cites an unresolved cited work.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Unresolved cited work

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:41.061243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:41.061243Z digest=sha256:0c0fb61b4cdd77b33eb911434adb6e91f9753c80c24355610945eaf3ae60e920

Observation d4dd7da5-8ba9-4bd6-b4c0-830aaa0bed47 · outbound

This paper cites 2026 , url =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD 2026 , url =

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:41.166854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:41.166854Z digest=sha256:ef36407330c3b5aadbd1d6bb9a423b789eb63e4e44b316e72d5a8d2bc5769022

Observation 2b463597-5de0-43e7-9562-384e0d5bc831 · outbound

This paper cites an unresolved cited work.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Unresolved cited work

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:41.294341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:41.294341Z digest=sha256:ecb1ab3b0a55bd014a80b33ed563e7cf3fc05930fc400eb8b371d8cef108039a

Observation b7cbb21b-0bbc-453e-9235-562f0b29ee0c · outbound

This paper cites RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:41.407957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:41.407957Z digest=sha256:8eaabc9c01c433dd2a9dd67effdec6bfcb2f6c282c5147002507d463b86b01b7

Observation 4d3d733f-3125-44cb-85c9-e1b6c0bdc1c9 · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:41.553486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:41.553486Z digest=sha256:632fe7ff7da81c2ddc475ca30bbab8947a86fd274960e5ef2a04cd9c441bfb3c

Observation e20b470a-1b56-46e8-be0d-e40b7a3a415f · outbound

This paper cites Proceedings of the AAAI Conference on Artificial Intelligence , volume=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the AAAI Conference on Artificial Intelligence , volume=

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:41.659929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:41.659929Z digest=sha256:01b7bde27b817a4abe69f497b179d2f69e988a94636fce5941742e3da77cb686

Observation a3ca89dd-67e0-4436-8f0c-67f71f67dd6e · outbound

This paper cites Findings of the Association for Computational Linguistics: EMNLP 2025 , pages=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Findings of the Association for Computational Linguistics: EMNLP 2025 , pages=

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:41.763344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:41.763344Z digest=sha256:400a8cd7f16bba92cb9f1381e47c36f3f1f2075ae6ace8e571d160b1e170be9c

Observation dc1d0779-6de3-4648-a384-1f85d88e5cc3 · outbound

This paper cites Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:41.859432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:41.859432Z digest=sha256:98432e7bf75067579fee4b8e6fd87899d289cb6869a70daa544ee32e9de92dbd

Observation abdf7e4e-c888-4ede-8e7c-d2db27fb109c · outbound

This paper cites Findings of the Association for Computational Linguistics: EMNLP 2025 , pages=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Findings of the Association for Computational Linguistics: EMNLP 2025 , pages=

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:41.973882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:41.973882Z digest=sha256:b275a5666cef9183dfb22d1a4f2880fa49d7a18490d7421d54657c5445713d1c

Observation 081183ca-e9d8-4ee0-ab2c-bb958653f164 · outbound

This paper cites Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:42.084760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:42.084760Z digest=sha256:13503d7d358c28ec5a658231eae1b0b274ccfb706c82e5633be619baf8421747

Observation 9fa4c218-5ace-4029-a7dc-c89356643ed4 · outbound

This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:42.216041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:42.216041Z digest=sha256:dcf9c3f59d05938bec95f79854c31fe8575d73594dfbba63cd74835ccab7cfa5

Observation ef98c0ad-fcd7-4e87-932d-1480ab1027d9 · outbound

This paper cites Demystifying Long Chain-of-Thought Reasoning in LLMs.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Demystifying Long Chain-of-Thought Reasoning in LLMs

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:42.355955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:42.355955Z digest=sha256:e9183f9cd10f1bcc5532f3abcefb555ff7c0825186d44c759211e32d967a22ae

Observation 2e37fe7c-c8a6-4ea2-a4b5-d614faa5b3c6 · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2024 , pages=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Findings of the Association for Computational Linguistics: ACL 2024 , pages=

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:42.469044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:42.469044Z digest=sha256:d935a272637a9f55208c07ff03959031dd730da303d6b8d55f9d8b73c9714a9e

Observation f440cc73-8ee8-4458-8d52-2f187547da0a · outbound

This paper cites arXiv preprint arXiv:2510.10071 , year=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD arXiv preprint arXiv:2510.10071 , year=

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:42.566298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:42.566298Z digest=sha256:70fce3ac7fb4bf99666c75084ab5ef05835d05642ecced99ded34f6afe041148

Observation fc374ee4-8db5-4941-94ef-28f47914c581 · outbound

This paper cites Investigating Continual Pretraining in Large Language Models: Insights and Implications.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Investigating Continual Pretraining in Large Language Models: Insights and Implications

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:42.659428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:42.659428Z digest=sha256:e22f50c4a7aa021ca33d4f904559a423b4aaf3247a07c5e77f7c9ac812be46e5

Observation 215f0dd9-9288-46a3-b800-061f4952be67 · outbound

This paper cites From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:42.797506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:42.797506Z digest=sha256:66bee53a9e48f013773b6821ecbfff78c2965601cbfde521fd3bea2a4114a442

Observation b49d8a0b-7902-4577-b39e-fea2e11d5355 · outbound

This paper cites Lane , booktitle=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Lane , booktitle=

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:42.937048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:42.937048Z digest=sha256:7d971b613dc74ea902103b0de818b6b39d1e8804a8ae8f38a2a0e67cff159f67

Observation 49fd6153-1497-439b-b2a4-022511519601 · outbound

This paper cites Forty-second International Conference on Machine Learning , year=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Forty-second International Conference on Machine Learning , year=

Reference 70

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:43.068810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:43.068810Z digest=sha256:a59c0c60ddac9791e42a9646a94512f50190ac7af285bd301eadf9e459532f0e

Observation 2a7033c5-e85e-4fc8-b70d-0421cbb52b88 · outbound

This paper cites Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations) , pages=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations) , pages=

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:43.124903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:43.124903Z digest=sha256:d770805ea24f09e3c97f8175c76ec05c60a510e329829185ae80cccfe2b688ef

Observation ef5071dd-bc34-4973-b261-7779dca9f623 · outbound

This paper cites ICML 2025 Workshop on Computer Use Agents , year=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD ICML 2025 Workshop on Computer Use Agents , year=

Reference 72

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:43.194774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:43.194774Z digest=sha256:41a12756db60271dd8f02b08dc9ef39612af47239073cd1f071f3e8450d00f59

Observation 831bc3c3-c25d-43c1-9916-595f77b77de7 · outbound

This paper cites an unresolved cited work.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Unresolved cited work

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:43.255095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:43.255095Z digest=sha256:bd0b45898b990dcfd04ec42d9d62bd19aa4cdfe0db8294e12565bef4fbb6a842

Observation a39531f3-d382-473b-9d7e-9436a9160120 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Advances in Neural Information Processing Systems , volume=

Reference 74

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:43.332072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:43.332072Z digest=sha256:e2850342b21acbcd88fe99593a839f9384e3d69d67e13a31b03e16b4db95f17c

Observation be1ca4bd-3208-4026-be9f-395e38733f56 · outbound

This paper cites Xing and Sham M.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Xing and Sham M

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:43.476271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:43.476271Z digest=sha256:1b35f45fa45b1498107cbc42b942d0377afa849137b94dd08287b8fa0dc9d4f9

Observation 5eb6b9ee-2964-4e3d-bf0b-36dbd861058a · outbound

This paper cites Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V

Reference 76

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:43.601381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:43.601381Z digest=sha256:359480eb320b50a8f3b07cb90f88ee6146dc90076db52dc872f50d88eaad9fa2

Observation c9bc9770-30b3-4df5-83ce-cfc5e46e8b78 · outbound

This paper cites 2025 , eprint=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD 2025 , eprint=

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:43.715467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:43.715467Z digest=sha256:b2d2a50b137f25000ee7dbf77bb8c64d32a144ab24863edfc10a6ee3d847db51

Observation c4a85417-e82e-485d-8cbe-500e90f32ffa · outbound

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

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD GLM-5: from Vibe Coding to Agentic Engineering

Reference 78

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:43.806846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:43.806846Z digest=sha256:b01b24d4b3eb5706e69071b7b3dcb8f71aa0db107c140ac57a83af7ed1bcf767

Observation eee5d0c8-66c9-4e4e-8fe6-68b2f258f44f · outbound

This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 79

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:43.937634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:43.937634Z digest=sha256:68568df8192fd4038da968700285641515df799d6d7ffbbd83688dc35e46357e

Observation ede0abb8-06ae-41fe-9950-9982a24e22f9 · outbound

This paper cites Domain Adaptation of Llama3-70B-Instruct through Continual Pre-Training and Model Merging: A Comprehensive Evaluation.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Domain Adaptation of Llama3-70B-Instruct through Continual Pre-Training and Model Merging: A Comprehensive Evaluation

Reference 80

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:44.093552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:44.093552Z digest=sha256:a804494c18c94088bd042e83dd274919ad71157758391e44719f063145512272

Observation 12b2fd59-b2b6-41a1-bd79-30176f71cf93 · outbound

This paper cites International Conference on Learning Representations , year=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD International Conference on Learning Representations , year=

Reference 81

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:44.133315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:44.133315Z digest=sha256:922dcb0fb624b204850f5c0dbcd69b30fe00638243c290cb57638c3acc4f4635

Observation 526d2e1e-e3f0-4863-b979-54a6f212851b · outbound

This paper cites Multitask Prompted Training Enables Zero-Shot Task Generalization.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Multitask Prompted Training Enables Zero-Shot Task Generalization

Reference 82

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:44.204080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:44.204080Z digest=sha256:323446e259dce91629e0a55814e7c63cff35e3d4d08f5c05913e3863cd30e563

Observation 35fdd07e-9b13-431a-8797-12a7a3ed843e · outbound

This paper cites Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs

Reference 83

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:44.262269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:44.262269Z digest=sha256:d3cfd27e2cdfb7594da8e69a08db4dbc21528fc50e1bbfef2a971b8d73f60c85

Observation c630c723-5371-471b-8def-cabeead4b7a2 · outbound

This paper cites 2024 , month =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD 2024 , month =

Reference 84

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:44.321204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:44.321204Z digest=sha256:48e4284e069fa89d87f6b3f48900512da506da0d75aaaaf11f522f0c87829bfc

Observation 674980c7-15b6-4354-9227-b7b401164277 · outbound

This paper cites 2021 , eprint=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD 2021 , eprint=

Reference 85

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:44.348961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:44.348961Z digest=sha256:7fbdc46a3a20a8dcc96cc5fe9a66583f70e2d7b4229edac6127f794602cad619

Observation 9733e3d0-9b34-44c7-9442-a90667f5f927 · outbound

This paper cites 2024 , journal =.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD 2024 , journal =

Reference 86

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:44.479396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:44.479396Z digest=sha256:b5825e69c0c58594d533999b042e2ec2c6faec4aed840e6555c746da26543fe6

Observation 9b1d7e50-d6ea-42da-a779-d3d2020757fd · outbound

This paper cites Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Injecting New Knowledge into Large Language Models via Supervised Fine-Tuning

Reference 87

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:44.601346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:44.601346Z digest=sha256:9e5ec4ad93caafb49815258aa8eeb203d7821f6684a2b80c2bf0be4646b7e231

Observation ba80b6e8-93d5-4d1c-9416-0a83bc9468e8 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 88

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:44.841286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:44.841286Z digest=sha256:01cebf72d90551d5a1c3b66e8104fbe523bf68d9f498e05b326f5399706f511b

Observation 2243f076-7255-4a67-b447-f5bd22ef75cf · outbound

This paper cites Proximal Policy Optimization Algorithms.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proximal Policy Optimization Algorithms

Reference 89

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:45.054508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:45.054508Z digest=sha256:8f4677637aa17b2e9c9d7594f8f19fa0cee0a85ee59975a4632ac366f3b22896

Observation f3356456-8aeb-45cc-9ad7-ebb5c79df6df · outbound

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

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Reference 90

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:45.279835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:45.279835Z digest=sha256:f164dbb6f0c04bd0857a5e8a77552e1a5847a34ba1c11f0e45b295fb8b83344a

Observation eab94ea7-2f03-4a6d-9aad-5f69086fd2cb · outbound

This paper cites an unresolved cited work.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Unresolved cited work

Reference 91

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:45.439960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:45.439960Z digest=sha256:d594f2431e8eb22fca6afd7f8ff90f0027dd9ebe2c893f969eacdcf23f444407

Observation f6633865-6df6-43b4-933d-93d8433465ff · outbound

This paper cites Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence

Reference 92

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:45.592909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:45.592909Z digest=sha256:8b4f9eab427e7c3172f543f4baca6be8f2871695420faa6467c655e844c0335b

Observation 81003c2e-060c-46ab-a2fc-515efcc9848e · outbound

This paper cites International Conference on Learning Representations , volume=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD International Conference on Learning Representations , volume=

Reference 93

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:45.744353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:45.744353Z digest=sha256:da4d14e0dd655d268f3e6d06ef26615ed29e22e477ac72a3b3f41e5c49fe6c5e

Observation e3addb22-6af7-47c0-8aa4-da72e40bf2aa · outbound

This paper cites International Conference on Learning Representations , volume=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD International Conference on Learning Representations , volume=

Reference 94

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:45.952338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:45.952338Z digest=sha256:11f375eb22216da41ef54c9fa5227d173595488e0756cfb7d74e8e016cf1080e

Observation af92d206-c799-4da7-9524-5552aff8346c · outbound

This paper cites arXiv e-prints , pages=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD arXiv e-prints , pages=

Reference 95

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:46.143917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:46.143917Z digest=sha256:da5a7ba6210878de8f212b2d67de300b1ca05434e63f497739f0e6dfd8061b75

Observation 1fa4eb63-ea05-4dad-81e5-2ffa56454117 · outbound

This paper cites Proceedings of the International Conference on Learning Representations (ICLR) , year=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Proceedings of the International Conference on Learning Representations (ICLR) , year=

Reference 96

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:46.334512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:46.334512Z digest=sha256:5e811416c40805a60f21332b4a17a26057c13556fc0358aa1d7b385e87054451

Observation 98c645b8-5d39-4ee5-bc5a-29126cc293e7 · outbound

This paper cites an unresolved cited work.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Unresolved cited work

Reference 97

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:46.503777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:46.503777Z digest=sha256:305f0c811677885f199b801671b5f4777d07ab838561e0ec9914ffdbdaec8444

Observation 8e600000-dad5-44ec-94a1-90b2dd47866e · outbound

This paper cites CMMLU : Measuring massive multitask language understanding in C hinese.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD CMMLU : Measuring massive multitask language understanding in C hinese

Reference 98

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:46.724457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:46.724457Z digest=sha256:a3f69413beeb0c4cc3df1c904193cd8adab8ac044f74eaede4283fb727df0ced

Observation 462999da-7234-4ce3-baf2-cb147238f77f · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Training Verifiers to Solve Math Word Problems

Reference 99

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:46.854625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:46.854625Z digest=sha256:e73da5e20b33ad37f35131a2cf119ce3b6624235482a9d1de1eec32419dfe70c

Observation d9ae0598-52fa-4e3f-89e3-7e26bc30dbaf · outbound

This paper cites 2021 , eprint=.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD 2021 , eprint=

Reference 100

Resolution
unresolved
no resolver link, observed 2026-08-01T10:42:46.984968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:46.984968Z digest=sha256:bfab26508e794862af32a83958d8e76bf6aaf3a27334bcea9d98d805c2319444

Observation 10fc9f2f-4c12-42de-a634-3b4f1154a4aa · outbound

This paper cites an unresolved cited work.

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD Unresolved cited work

Reference 101

Resolution
parse uncertain
no resolver link, observed 2026-08-01T10:42:47.058369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-01T10:42:47.058369Z digest=sha256:8c0b18f268e98b0913f2fb42c605dfa9676acea3f0a60906cc17c36963b2d123

Pith citing papers

No inbound Pith citation observations are available.