Paper Citation Record · LEDGER

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

As of 9 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 12 inbound Pith citation observations for arXiv:2507.12856.

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

pith.paper-citation-record.v1
2507.12856 v2

Coverage vector

measured 63 of 63 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:44:51.047658Z

measured 75 of 75 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 12 of 12 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-11T17:03:13.686066Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

63 of 63 outbound references displayed

verified exact4
verified fuzzy25
unresolved33
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation afb97173-c846-4dd5-aa11-24107e077d56 · outbound

This paper cites Training language models to follow instructions with human feedback.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Training language models to follow instructions with human feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:45.401136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ae96b4f-752c-4734-b189-ad82e388fa32 · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Fine-Tuning Language Models from Human Preferences

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:45.500663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dd8d10b-7d19-4cf4-837d-47a1138126a0 · outbound

This paper cites RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:45.719179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e196e2bc-700e-4987-ab05-180d411725d2 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Constitutional AI: Harmlessness from AI Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:45.773825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fde1362d-60b9-4d0e-8d05-604669c47cd2 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:45.860300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8300ce0c-2d2a-4072-8b57-4d8ea246b60a · outbound

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

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:45.911559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c232c5e-c530-4ae6-92d8-14ba6956428d · outbound

This paper cites Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:46.002490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62ef0cf6-7c98-4fcd-90de-0686f7a6e8d3 · outbound

This paper cites ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:46.084746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b86cc15b-f822-4864-ae8e-5ebee5ffefb5 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Direct preference optimization: Your language model is secretly a reward model

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:46.142290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfb073a7-0f9e-4f28-a85d-514a64fbb332 · outbound

This paper cites Learning from negative feedback, or positive feedback or both.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Learning from negative feedback, or positive feedback or both

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T16:44:52.510853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5640087d-64d5-4b35-ab97-d304c031a795 · outbound

This paper cites s1: Simple test-time scaling.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) s1: Simple test-time scaling

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:46.335618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f91e8dd-5014-4aa0-afd3-33baf1614ff9 · outbound

This paper cites Reinforcement Learning for Reasoning in Large Language Models with One Training Example.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:46.435921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efee556c-471a-43b1-a52e-e3c1a6e1fe78 · outbound

This paper cites Peters and S.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Peters and S

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:56.861232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b741377d-402c-46d2-8377-8ae21207358e · outbound

This paper cites Policy search for motor primitives in robotics.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Policy search for motor primitives in robotics

Reference 14

Resolution: verified exact; raw_fallback, observed 2026-08-06T16:44:52.290791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 57f29dac-888b-4f4d-9cd4-52053917f724 · outbound

This paper cites Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:46.752711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c0d0215-1793-4c1c-b3cc-6c7d45288ae8 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Measuring Mathematical Problem Solving With the MATH Dataset

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:46.837944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16728588-cee1-4bd4-a0ea-133600395631 · outbound

This paper cites D4rl: Datasets for deep data-driven reinforcement learning, 2020.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) D4rl: Datasets for deep data-driven reinforcement learning, 2020

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:56.734986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8e88bc7c-02fd-4134-8a20-025d8f5fa7ca · outbound

This paper cites an unresolved cited work.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Unresolved cited work

Reference 18

Resolution: verified exact; doi, observed 2026-08-06T16:44:51.237564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7ab64d06-7140-4cfd-99d0-38a5b645dc80 · outbound

This paper cites Learning math reasoning from self-sampled correct and partially-correct solutions.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Learning math reasoning from self-sampled correct and partially-correct solutions

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:56.594199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 83d709d3-e8cb-4135-8314-b8b5f1ab78a7 · outbound

This paper cites Learning to generalize from sparse and underspecified rewards.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Learning to generalize from sparse and underspecified rewards

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:56.440699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d419a748-668a-4a22-8bd7-aaa10210dcb6 · outbound

This paper cites Reward augmented maximum likelihood for neural structured prediction.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Reward augmented maximum likelihood for neural structured prediction

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:56.339577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c2cdac58-84db-41e2-ad62-c8f93657213c · outbound

This paper cites Scaling relationship on learning mathematical reasoning with large language models, 2024.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Scaling relationship on learning mathematical reasoning with large language models, 2024

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:56.228534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4a3e8de1-e1a8-473a-9616-c3df12e2d901 · outbound

This paper cites Simplify rlhf as reward-weighted sft: A variational method, 2025.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Simplify rlhf as reward-weighted sft: A variational method, 2025

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:47.432332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 257f81c1-d435-4a4a-875b-84f7e81c6f2d · outbound

This paper cites Reinforced Self-Training (ReST) for Language Modeling.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Reinforced Self-Training (ReST) for Language Modeling

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:47.542530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 771076c3-756d-4b82-bf86-b02498f3c9c5 · outbound

This paper cites Beyond human data: Scaling self-training for problem-solving with language models.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Beyond human data: Scaling self-training for problem-solving with language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:56.075852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fa584de8-e969-4035-84af-959a13e2f10c · outbound

This paper cites Peters, K.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Peters, K

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:55.960423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0c3b15e6-3dbd-407f-982c-21099dd00054 · outbound

This paper cites Efficient iterative policy optimization.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Efficient iterative policy optimization

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-06T16:44:51.818563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4c08c25d-820a-4ef7-9dae-a1be44beee82 · outbound

This paper cites Tighter bounds lead to improved classifiers.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Tighter bounds lead to improved classifiers

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-06T16:44:51.678790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7997a69a-b90a-4623-8aca-0ab0520792b4 · outbound

This paper cites Process for adapting language models to society (palms) with values-targeted datasets.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Process for adapting language models to society (palms) with values-targeted datasets

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:55.847173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c11d96f1-3267-4067-9e90-17b4b8c3e13d · outbound

This paper cites Self-consuming generative models with curated data provably optimize human preferences.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Self-consuming generative models with curated data provably optimize human preferences

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:55.709899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a97c8070-9390-4a67-b0ff-4be30d82d30a · outbound

This paper cites Maximum a posteriori policy optimisation.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Maximum a posteriori policy optimisation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:55.501691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 45f416fc-0333-48e9-97be-f7b45475e876 · outbound

This paper cites On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:48.223183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29d5868e-4a55-4112-ad0a-c0eea351d23a · outbound

This paper cites Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:48.304660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4f35b25-c428-4649-b9d0-a82cccd0435b · outbound

This paper cites Proximal Policy Optimization Algorithms.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Proximal Policy Optimization Algorithms

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:48.492080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d4a7ba3-4f64-4919-8e9d-09a6ea8441d3 · outbound

This paper cites Offline Reinforcement Learning with Implicit Q-Learning.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Offline Reinforcement Learning with Implicit Q-Learning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:48.588072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b54d76e-aa16-4dc0-9478-4302dc1c0d4b · outbound

This paper cites When does return-conditioned supervised learning work for offline reinforcement learning? In S.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) When does return-conditioned supervised learning work for offline reinforcement learning? In S

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:55.354255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 57d6da3f-8e75-4292-9d15-21a48fb37d5f · outbound

This paper cites Decision transformer: Reinforcement learning via sequence modeling.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Decision transformer: Reinforcement learning via sequence modeling

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:55.137459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fdd94b3f-bdf5-4ec4-a8a4-7e990cac77b1 · outbound

This paper cites Kahn and Andrew W.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Kahn and Andrew W

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:54.952638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a0d9b5b8-8fbb-4d1f-baef-1e95294083a1 · outbound

This paper cites Rubinstein and Dirk P.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Rubinstein and Dirk P

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:54.740440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 88f4b4b9-f99e-4300-aeea-dd32ec107cd3 · outbound

This paper cites Stochastic simulation.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Stochastic simulation

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:54.569844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d1290aa6-45e6-4f4f-bdb3-f7946219a033 · outbound

This paper cites Doubly robust off-policy value evaluation for reinforcement learning.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Doubly robust off-policy value evaluation for reinforcement learning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:49.093487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a26b3599-c974-47b4-808f-22057a1eaf14 · outbound

This paper cites Policy optimization via importance sampling.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Policy optimization via importance sampling

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:54.382252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f2d7eba5-97db-40d1-8f10-b4034d166bbe · outbound

This paper cites Andrad\'ottir, D.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Andrad\'ottir, D

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:54.218210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cced70b8-1f35-4901-b3c6-883f2bf2c9db · outbound

This paper cites Qwen2.5 Technical Report.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Qwen2.5 Technical Report

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:49.354945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d50992c-f704-45d8-853f-9a1058b752be · outbound

This paper cites Numinamath, 2024.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Numinamath, 2024

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:54.057836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a673c9d4-9d75-4660-8609-a19683a7ce93 · outbound

This paper cites Aime, February 2024.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Aime, February 2024

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:53.913396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0c4b594e-f0a2-43cc-8651-0f6f4b6a0a1d · outbound

This paper cites Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:49.647176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 336f7a07-a1a9-4885-9ce8-204c9c234a51 · outbound

This paper cites AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:49.735291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae6dc2d4-66ed-44d4-9409-536ced3b8c14 · outbound

This paper cites Gemini 2.0 flash thinking mode (gemini-2.0-flash-thinking-exp-1219), December 2024.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Gemini 2.0 flash thinking mode (gemini-2.0-flash-thinking-exp-1219), December 2024

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:53.691885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4ee868a3-7f94-42d6-b3e0-f291b78a9a62 · outbound

This paper cites Qwq: Reflect deeply on the boundaries of the unknown, November 2024.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Qwq: Reflect deeply on the boundaries of the unknown, November 2024

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:49.880551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4d49f26-0a3f-4942-8c82-e2dd23e1a758 · outbound

This paper cites Learning to reason with llms, September 2024.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Learning to reason with llms, September 2024

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:53.487524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7470890e-5934-4df4-85ca-ca63db0f7f60 · outbound

This paper cites Bespoke-stratos: The unreasonable effectiveness of reasoning distillation, 2025.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Bespoke-stratos: The unreasonable effectiveness of reasoning distillation, 2025

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:53.298736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 668ec223-1aa3-4844-b3d9-059bb8fb9e58 · outbound

This paper cites Sky-t1: Fully open-source reasoning model with o1-preview performance in \ 450 budget, 2025.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Sky-t1: Fully open-source reasoning model with o1-preview performance in \ 450 budget, 2025

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:53.146540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a47ffc63-3e48-4a2b-a199-8c7edfecea5b · outbound

This paper cites Gemini 2.5: Our most intelligent ai model, March 2025.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Gemini 2.5: Our most intelligent ai model, March 2025

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:44:52.995163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d4722487-92ec-4734-942d-1a862edfe79b · outbound

This paper cites Decoupled Weight Decay Regularization.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Decoupled Weight Decay Regularization

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:50.258889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ee6a2d9-e86e-4377-8003-f89dea17118c · outbound

This paper cites Continuous control with deep reinforcement learning.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Continuous control with deep reinforcement learning

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:50.353512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 151b4ce6-8c6f-4147-9149-2611c709b90f · outbound

This paper cites A minimalist approach to offline reinforcement learning.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) A minimalist approach to offline reinforcement learning

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:50.436962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f45d04a-2659-4dcf-a7de-a64126f29578 · outbound

This paper cites AWAC: Accelerating Online Reinforcement Learning with Offline Datasets.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) AWAC: Accelerating Online Reinforcement Learning with Offline Datasets

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:50.531632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9adab734-26de-496a-b29b-9eb92f25db63 · outbound

This paper cites Conservative q-learning for offline reinforcement learning.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Conservative q-learning for offline reinforcement learning

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:50.671535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eb94329-e8c1-470b-b550-a4b008815cab · outbound

This paper cites PyTorch: An Imperative Style, High-Performance Deep Learning Library.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) PyTorch: An Imperative Style, High-Performance Deep Learning Library

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:50.738027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f70e476b-efaf-42b7-a1db-205748ae26fa · outbound

This paper cites Accelerate: Training and inference at scale made simple, efficient and adaptable.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Accelerate: Training and inference at scale made simple, efficient and adaptable

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:50.830477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5d0cf3f-3ad7-4711-a8e4-f2ea0bb0b5a9 · outbound

This paper cites SGDR : Stochastic gradient descent with warm restarts.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) SGDR : Stochastic gradient descent with warm restarts

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:50.909102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c37973e0-39b8-43df-a3d4-68712b60c06e · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved) Adam: A Method for Stochastic Optimization

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T16:44:51.047658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 54a57a42-7d6b-497a-b993-a839ecc1914d · inbound

Proximal Supervised Fine-Tuning cites this paper.

Proximal Supervised Fine-Tuning Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-18T20:42:50.932782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3f61dc23-2063-46c8-8d16-a499a3e67153 · inbound

Multi-LLM Orchestration for High-Quality Code Generation: Exploiting Complementary Model Strengths cites this paper.

Multi-LLM Orchestration for High-Quality Code Generation: Exploiting Complementary Model Strengths Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:22:33.306633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1c44e9b4-86b8-4c9d-9515-fd5da3410e5d · inbound

Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors cites this paper.

Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T15:51:44.181536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5a99cba9-220f-481b-9f34-85429aad88fb · inbound

Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent cites this paper.

Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Reference 37

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T05:45:23.212875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c53f467c-925c-4fd4-b0f5-bd44f83690f3 · inbound

Rotation-Preserving Supervised Fine-Tuning cites this paper.

Rotation-Preserving Supervised Fine-Tuning Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T06:27:24.422736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b6439b38-6462-46eb-b7c8-88e767908f8d · inbound

Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models cites this paper.

Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-06-29T08:03:13.954844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 353feea3-2ed2-4330-92c0-23c886e339e7 · inbound

DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization cites this paper.

DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-06-28T23:22:47.435668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4d8fce38-062b-45f3-8b32-d81b7b5715d8 · inbound

PriFT: Prior-Support Guided Supervised Fine-Tuning cites this paper.

PriFT: Prior-Support Guided Supervised Fine-Tuning Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T00:57:29.908830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 197441d6-2553-4e83-98c0-184d73a79727 · inbound

When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff cites this paper.

When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T22:27:26.355797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4e3531e1-fe33-4e57-97ba-b04f0faf917c · inbound

Compatibility-Aware Dynamic Fine-Tuning for Large Language Models cites this paper.

Compatibility-Aware Dynamic Fine-Tuning for Large Language Models Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-05T02:30:40.844795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 01422f85-b83c-4c76-ab8e-e3f2056d0f89 · inbound

Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning cites this paper.

Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T16:29:57.043899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6f56a063-4987-42b8-8411-20189f8b2049 · inbound

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training cites this paper.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.