Pith. sign in

Paper Citation Record · LEDGER

BTS: Harmonizing Specialized Experts into a Generalist LLM

As of 10 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 2 inbound Pith citation observations for arXiv:2502.00075.

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

pith.paper-citation-record.v1
2502.00075 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T21:59:01.357001Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:42:25.004379Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T18:57:16.659067Z

Reference resolution

30 of 30 outbound references displayed

  • verified exact1
  • verified fuzzy3
  • unresolved25
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3037bb8b-9fb6-48ed-9c7c-362386e41f28 · outbound

This paper cites Better fine-tuning by reducing representational collapse.

BTS: Harmonizing Specialized Experts into a Generalist LLM Better fine-tuning by reducing representational collapse

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T21:59:02.188399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T21:59:00.969814Z digest=sha256:a65414081b6eb169003a263697e4ed1fb4ad8330e3f8604d6993a4c883cf932b

Observation 674b5e80-c4ba-458c-8104-5cef98b289b9 · outbound

This paper cites LLM Augmented LLMs: Expanding Capabilities through Composition.

BTS: Harmonizing Specialized Experts into a Generalist LLM LLM Augmented LLMs: Expanding Capabilities through Composition

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:00.989878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:00.989878Z digest=sha256:48876b2b15a88ab1166dc58e132179c595b135752667d60a29bf837be0e418e5

Observation cc60d525-1618-44c4-8e5f-11b3e61038f5 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

BTS: Harmonizing Specialized Experts into a Generalist LLM Training Verifiers to Solve Math Word Problems

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.013542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.013542Z digest=sha256:7ef6439320a15c99ab77c58d860ef10b82f0718edc696a33bebd4a6a96abbd7d

Observation 7420f786-e965-44e1-b308-4070fca186e9 · outbound

This paper cites The Llama 3 Herd of Models.

BTS: Harmonizing Specialized Experts into a Generalist LLM The Llama 3 Herd of Models

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.021975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.021975Z digest=sha256:13acaad1a20aac205f6bd39548d52a88f2aedc2b97e2471b63710af046c7f0f1

Observation 33878b3e-7740-4bd8-9099-9bfd3fe3d33a · outbound

This paper cites No Need to Talk: Asynchronous Mixture of Language Models.

BTS: Harmonizing Specialized Experts into a Generalist LLM No Need to Talk: Asynchronous Mixture of Language Models

Reference 8

Resolution
verified exact
local_arxiv, observed 2026-08-09T21:59:01.832219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T21:59:01.030368Z digest=sha256:1da53712297b1700e56dea74e723cb77ba53831c622f00cad7befbf206f97981

Observation f1178855-9a9a-4c59-8eb3-5c48cca6aa16 · outbound

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

BTS: Harmonizing Specialized Experts into a Generalist LLM Don't Stop Pretraining: Adapt Language Models to Domains and Tasks

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.038955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.038955Z digest=sha256:888df5616d729bfd119a8bdd400c7dc9da51a915fca9e042b2a49386d622a30c

Observation 5bfd1ccc-4dbe-4e36-8663-d05a0b3951f0 · outbound

This paper cites Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models.

BTS: Harmonizing Specialized Experts into a Generalist LLM Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.070134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.070134Z digest=sha256:676f763ba4ad7b40f44395bad38ab5ab0b23606ec268f4284c4d363d1d22001e

Observation 01a5f7e0-41f5-4739-95f3-4d47af8433bd · outbound

This paper cites Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models.

BTS: Harmonizing Specialized Experts into a Generalist LLM Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.077437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.077437Z digest=sha256:5bf2182dd57e8ac7d9160e4e51d2f653d694d2e36c18eda2ee44d1ca61b80ba2

Observation 0357313c-1fc0-4f1e-8f2e-23d8600ceff4 · outbound

This paper cites RouteLLM: Learning to Route LLMs with Preference Data.

BTS: Harmonizing Specialized Experts into a Generalist LLM RouteLLM: Learning to Route LLMs with Preference Data

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.131976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.131976Z digest=sha256:2391b3bcee1bce22530cedd4850800c2e444653c5f26e5b13410f52134d3d9bc

Observation e0a3da1b-3cb9-4997-86b8-d1f55317918d · outbound

This paper cites OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text.

BTS: Harmonizing Specialized Experts into a Generalist LLM OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.164748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.164748Z digest=sha256:4007b41d5d2fb7e9c3df1404641b6caa4542e7e2c1ea23486d38f61fb4084e17

Observation 020bf8b2-90c5-48e8-8eee-f8c9caa01806 · outbound

This paper cites Code Llama: Open Foundation Models for Code.

BTS: Harmonizing Specialized Experts into a Generalist LLM Code Llama: Open Foundation Models for Code

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.205682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.205682Z digest=sha256:a59755a1f512ae350c620f40e902804d065f1048d94f22e169b38037ef8ba9cc

Observation 32bf083b-88a8-4ae0-afbb-4aa136fe3655 · outbound

This paper cites Code Llama: Open Foundation Models for Code.

BTS: Harmonizing Specialized Experts into a Generalist LLM Code Llama: Open Foundation Models for Code

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.236763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.236763Z digest=sha256:b46307b1c5c002814884c6ca917e801d7defd00e05a9fea919c3192d696e49a5

Observation 55e3db53-ce5b-4002-9bf2-ba3d3ddf69a0 · outbound

This paper cites Language Models are Multilingual Chain-of-Thought Reasoners.

BTS: Harmonizing Specialized Experts into a Generalist LLM Language Models are Multilingual Chain-of-Thought Reasoners

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.271328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.271328Z digest=sha256:01ec2e02aac0ff9118d7a684b96e0550a0ef02793045da9fe725475a625673df

Observation 118b8e59-244c-479c-b46b-1d01b0776e34 · outbound

This paper cites Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM.

BTS: Harmonizing Specialized Experts into a Generalist LLM Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.299244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.299244Z digest=sha256:a59fe080b69ce162206dea342bc709295019f1a7be2ad1a711df482f14b1d21a

Observation 45c70adb-9721-44a4-a224-80e0b12dad0b · outbound

This paper cites Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.

BTS: Harmonizing Specialized Experts into a Generalist LLM Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.305357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.305357Z digest=sha256:2a4233ef69c5ede21daa42be12d114873d30c08c78955b9e84f0118185b0bedc

Observation c26671c3-d0bb-4472-80fb-54803cdc8f51 · outbound

This paper cites Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models.

BTS: Harmonizing Specialized Experts into a Generalist LLM Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.312232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.312232Z digest=sha256:48ce83f18fff9950aee76abaa1bf40fd3a42b86ad59c3b822142e27220339106

Observation c2c03fec-4a9c-415d-adc8-252e17245934 · outbound

This paper cites Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models.

BTS: Harmonizing Specialized Experts into a Generalist LLM Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.317633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.317633Z digest=sha256:50e566268c8950c777cb7217242288aa258dc382c029737b2c108331d71ca62d

Observation 45766439-9f24-42ff-be77-a8a250d14933 · outbound

This paper cites Mitchell Wortsman, Gabriel Ilharco, Samir Ya Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, et al.

BTS: Harmonizing Specialized Experts into a Generalist LLM Mitchell Wortsman, Gabriel Ilharco, Samir Ya Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, et al

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T21:59:02.090254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T21:59:01.323697Z digest=sha256:88ead228b6fa73b8128bfc14079e7b69cb9a5e02040044bca06d6679ec1f29c5

Observation 0232f297-8b07-4137-8f53-26572a8d4f20 · outbound

This paper cites Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance.

BTS: Harmonizing Specialized Experts into a Generalist LLM Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.330804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.330804Z digest=sha256:37cb73e6d1846e0f7162aade1664292b5ce00b1ce0debe63abe4771d449bcae0

Observation 3570ed30-138e-4f50-a5fc-d9d91e723865 · outbound

This paper cites Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance.

BTS: Harmonizing Specialized Experts into a Generalist LLM Data Mixing Laws: Optimizing Data Mixtures by Predicting Language Modeling Performance

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.338060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.338060Z digest=sha256:54c4149f5c39233db44339374a43def1ef063d97d72a895a0e619b83fe04cc6b

Observation 5365c168-cc5a-44a8-be24-673fe2225cc8 · outbound

This paper cites Mixture of Attention Heads: Selecting Attention Heads Per Token.

BTS: Harmonizing Specialized Experts into a Generalist LLM Mixture of Attention Heads: Selecting Attention Heads Per Token

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.344329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.344329Z digest=sha256:e3cdb7a2537a16c71afde38e0f8d9a3949d9abcebc906716154a9a51fc645535

Observation 71a16bef-a5f7-43dc-a220-6ece9adb0772 · outbound

This paper cites Law of the Weakest Link: Cross Capabilities of Large Language Models.

BTS: Harmonizing Specialized Experts into a Generalist LLM Law of the Weakest Link: Cross Capabilities of Large Language Models

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.351042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.351042Z digest=sha256:3d906dd0583d0bd29fbfaf31220bbe724c3f6f2611a2773d810f89beb29e8c7b

Observation eb98c7c0-ef8b-41f3-865e-40254b27134d · outbound

This paper cites The expert training setup follows the same procedure outlined in Section 3.1.

BTS: Harmonizing Specialized Experts into a Generalist LLM The expert training setup follows the same procedure outlined in Section 3.1

Reference 30

Resolution
malformed identifier
raw_fallback, observed 2026-08-09T21:59:01.962611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T21:59:01.357001Z digest=sha256:5ccad8a1e09fbbcee60e229d2e0157065522f0bdb0f9f5ee6feb5588c030b2d7

Observation 802491ba-907d-4a32-8e5e-56693ca642de · outbound

This paper cites Soft Merging of Experts with Adaptive Routing.

BTS: Harmonizing Specialized Experts into a Generalist LLM Soft Merging of Experts with Adaptive Routing

Reference 1989

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.099537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.099537Z digest=sha256:ffe4c12a602e21c8cfb181193d851755ee8914312fe1f36ba5e02106cdb6bd4d

Observation f473eb2e-8517-4541-91d9-c6f27cc26b1f · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

BTS: Harmonizing Specialized Experts into a Generalist LLM TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 2016

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.056284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.056284Z digest=sha256:f14e0efdb1e41a1fda0199b35cfa0d2382900810e0d17667b741407bb2413460

Observation 7e575699-2b4b-4e4d-954a-c640877587d2 · outbound

This paper cites Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints.

BTS: Harmonizing Specialized Experts into a Generalist LLM Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints

Reference 2017

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.063787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.063787Z digest=sha256:587cac6bd10830254787f9bdb38df7c2e97747bdaa3aaa86d775ea3ad4641aeb

Observation c3cc1c4b-7472-440f-aa9a-1362d5044225 · outbound

This paper cites an unresolved cited work.

BTS: Harmonizing Specialized Experts into a Generalist LLM Unresolved cited work

Reference 2021

Resolution
unresolved
raw_fallback, observed 2026-08-09T21:59:02.169295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T21:59:00.976739Z digest=sha256:a9670bf6dba5c0fcfed01bb16e3f4f86e7a1eba1dc46d1a6930f79c2763d32a3

Observation 4240c37a-cfaa-479b-8912-60a846284ce6 · outbound

This paper cites Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, and Charles Sutton.

BTS: Harmonizing Specialized Experts into a Generalist LLM Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, and Charles Sutton

Reference 2022

Resolution
verified fuzzy
raw_fallback, observed 2026-08-09T21:59:02.147711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-09T21:59:00.983148Z digest=sha256:81f595a2d57187b1fda5a3ab729d753cec72b0d34363e113fffd18d1ee09dba8

Observation 926bafb9-f89e-4097-9a96-5fc5069c22f4 · outbound

This paper cites Categorical Reparameterization with Gumbel-Softmax.

BTS: Harmonizing Specialized Experts into a Generalist LLM Categorical Reparameterization with Gumbel-Softmax

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.048635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.048635Z digest=sha256:14d621e79b4c2c0888caa3cf3d3395e2f2966b174b8581dff16b172911757861

Observation 4a25f593-e9d7-4852-aad6-9ebd15c8a398 · outbound

This paper cites Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models.

BTS: Harmonizing Specialized Experts into a Generalist LLM Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-09T21:59:01.000294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-09T21:59:01.000294Z digest=sha256:aaa4a8ead076eb56d8be8b6dff2290f92f470885c7d4ef620d0771e566208c1b

Pith citing papers

Observation 44264d05-83d7-41fc-a250-54f05126a1ae · inbound

Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging cites this paper.

Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging BTS: Harmonizing Specialized Experts into a Generalist LLM

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-07T15:42:25.004379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-07T15:42:25.004379Z digest=sha256:e954c42b64177ec0566effaead5a9eb85e2e45d815971b13310ee7fe4687345f

Observation 5dab02fd-d9b4-4086-bc34-cd3ea123042b · inbound

FlexOlmo: Open Language Models for Flexible Data Use cites this paper.

FlexOlmo: Open Language Models for Flexible Data Use BTS: Harmonizing Specialized Experts into a Generalist LLM

Reference 57

Resolution
verified exact
local_arxiv, observed 2026-08-06T18:57:16.664191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-06T18:57:16.074667Z digest=sha256:f21c6cb1caa41ea75e99897e90c56e05a3e5649ad5982ab10b8eae064fe58134