Paper Citation Record · LEDGER

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections

As of 7 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 3 inbound Pith citation observations for arXiv:2507.00018.

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

pith.paper-citation-record.v1
2507.00018 v2

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:54:49.897621Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-05T02:27:50.369374Z

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

43 of 43 outbound references displayed

verified exact1
verified fuzzy19
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

Observation 155ecc09-68b1-49d9-a69d-74bd2cdbe62a · outbound

This paper cites an unresolved cited work.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:54:50.577843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 63bbd42e-8d4b-418d-b009-286bb6ee8bcb · outbound

This paper cites The Llama 3 Herd of Models.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections The Llama 3 Herd of Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:48.842036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45844eb2-a2b8-44ab-97ff-08b651d4a23b · outbound

This paper cites Qwen2 Technical Report.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Qwen2 Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:48.952808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 740526b3-24a8-467b-8455-7f1896fb89aa · outbound

This paper cites DeepSeek-V3 Technical Report.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections DeepSeek-V3 Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.027509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 299141e7-ae50-4248-b9d6-b70024ebe1a7 · outbound

This paper cites Mistral 7B.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Mistral 7B

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.161443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4d41498-8e2e-4cd1-a861-aabeb3829e17 · outbound

This paper cites LIMO: Less is More for Reasoning.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections LIMO: Less is More for Reasoning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.273212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6f19c3e-faec-4b6a-9a17-ba0818a03dd3 · outbound

This paper cites LIMA: less is more for alignment.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections LIMA: less is more for alignment

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.565495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2527488a-32c2-45bc-af58-26484812d526 · outbound

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

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.466452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 696e9905-ffea-42e7-b833-fc1a31717ae1 · outbound

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

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.570674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e284614f-2074-41cb-8341-709bb668a09d · outbound

This paper cites Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.652357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56f6fa23-9bfa-41a4-abf7-b522dacc86ce · outbound

This paper cites Deep reinforcement learning from human preferences.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Deep reinforcement learning from human preferences

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.759695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ba82bcc-c98a-4bea-91d1-b7bba81c268a · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.763796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9a44f64-bdb9-4b72-ab81-bbc7d787c66e · outbound

This paper cites Self-play fine-tuning converts weak language models to strong language models.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Self-play fine-tuning converts weak language models to strong language models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.551637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1990d6db-a32b-4898-9e51-03d125c24718 · outbound

This paper cites Learning Dynamics of LLM Finetuning.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Learning Dynamics of LLM Finetuning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.770445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 629305d1-60bf-4403-8943-45ff85560ba6 · outbound

This paper cites IQ-Learn: Inverse soft-Q Learning for Imitation.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections IQ-Learn: Inverse soft-Q Learning for Imitation

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:54:50.177850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 07a74808-a6d1-4cb0-b197-fc1a7c6aabf8 · outbound

This paper cites Huang, Artem Sokolov, Matt Barnes, Guillaume Desjardins, Alex Bewley, Sarah Bechtle, Jost Tobias Springenberg, Nikola Momchev, Olivier Bachem, Matthieu Geist, and Martin A.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Huang, Artem Sokolov, Matt Barnes, Guillaume Desjardins, Alex Bewley, Sarah Bechtle, Jost Tobias Springenberg, Nikola Momchev, Olivier Bachem, Matthieu Geist, and Martin A

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.538820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cad91d96-f262-4d7b-abaf-21967381882a · outbound

This paper cites From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.782191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c44ace5-62ea-4b09-95ad-04272b92cf4b · outbound

This paper cites Ng and Stuart Russell.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Ng and Stuart Russell

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.525704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d7489688-7b8b-40ac-a258-ad77e3a60e29 · outbound

This paper cites Preserving Diversity in Supervised Fine-Tuning of Large Language Models.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Preserving Diversity in Supervised Fine-Tuning of Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.789457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c96eb0c2-448a-4c4c-99d0-6d47d8a457e5 · outbound

This paper cites f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.793212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf414451-3f34-4e9e-8547-0d2c55c820d0 · outbound

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

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Sequencematch: Imitation learning for autoregressive sequence modelling with backtracking

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.513128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6a6ec825-10bf-418a-9762-31c5031510ba · outbound

This paper cites Proximal Policy Optimization Algorithms.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Proximal Policy Optimization Algorithms

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.801207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b37f6627-9498-47ce-bc37-d6434e484211 · outbound

This paper cites A general theoretical paradigm to understand learning from human preferences.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections A general theoretical paradigm to understand learning from human preferences

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.501382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 44bf425c-9e56-45d3-aa8c-48e512fbb21c · outbound

This paper cites Model alignment as prospect theoretic optimization.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Model alignment as prospect theoretic optimization

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.489223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1b3bfa17-fbe4-42c6-b82a-29bd522508a8 · outbound

This paper cites Simpo: Simple preference optimization with a reference-free reward.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Simpo: Simple preference optimization with a reference-free reward

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.476399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e98b2b3a-7252-4388-a3a0-77c37cb393d9 · outbound

This paper cites Disentangling length from quality in direct preference optimization.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Disentangling length from quality in direct preference optimization

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.463217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f97dd5a8-7a18-4ff5-b2f4-fbb033ad99b5 · outbound

This paper cites Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.821661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d29a645-ca11-4196-986c-51f102089c7f · outbound

This paper cites Andrew Bagnell.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Andrew Bagnell

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.825840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bd585c5-1ff1-46d0-a33a-e316b98163eb · outbound

This paper cites Ziebart, Andrew L.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Ziebart, Andrew L

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.449803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d5944051-dabb-4ec1-b356-adc6efc21089 · outbound

This paper cites Enhancing chat language models by scaling high-quality instructional conversations.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Enhancing chat language models by scaling high-quality instructional conversations

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.436243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4da6cf93-416a-4c3c-bcfd-37ed4e76961e · outbound

This paper cites UltraFeedback: Boosting Language Models with Scaled AI Feedback.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections UltraFeedback: Boosting Language Models with Scaled AI Feedback

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.838199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cec943e-8c1a-44a2-95f2-7772676d4f1f · outbound

This paper cites OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.842747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ecdcd53-2441-4def-a799-4c63dd45c8d1 · outbound

This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.851308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ac1d6ed-c92c-4bcb-b685-825f7291cc1d · outbound

This paper cites Xing, Hao Zhang, Joseph E.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Xing, Hao Zhang, Joseph E

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.423410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ebdac33f-13bf-48bd-87bb-d78afd04c21d · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Gonzalez, Hao Zhang, and Ion Stoica

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.409199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d4f260b2-1c9f-4368-8840-efb07f890521 · outbound

This paper cites RRHF: rank responses to align language models with human feedback.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections RRHF: rank responses to align language models with human feedback

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.395307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 665991a4-8154-4b0a-a47d-ecd103f3e2eb · outbound

This paper cites SLiC-HF: Sequence Likelihood Calibration with Human Feedback.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections SLiC-HF: Sequence Likelihood Calibration with Human Feedback

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.868787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f00328f4-f5c6-4374-9e20-16d2f547f190 · outbound

This paper cites Contrastive preference optimization: Pushing the bound- aries of LLM performance in machine translation.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Contrastive preference optimization: Pushing the bound- aries of LLM performance in machine translation

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.381363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8b364a22-3f24-487d-bcf7-1c013b6c60f4 · outbound

This paper cites ORPO: monolithic preference optimization without reference model.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections ORPO: monolithic preference optimization without reference model

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.368537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a16ef0d9-cc25-4281-a02f-478cd785d2a9 · outbound

This paper cites Rush, and Thomas Wolf.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Rush, and Thomas Wolf

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.354243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cf15fed3-bf22-4143-b499-94887fc6a6a8 · outbound

This paper cites Let's Verify Step by Step.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Let's Verify Step by Step

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T00:54:49.888136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf6cfa3c-378f-4d8a-a182-8bad4a1293be · outbound

This paper cites Generative adversarial imitation learning.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Generative adversarial imitation learning

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.340230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b227c1bc-9db4-4bdc-bfeb-552bf873ef87 · outbound

This paper cites Zemel, and Shixiang Gu.

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections Zemel, and Shixiang Gu

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:54:50.326969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation 8ba59577-e2d1-4fba-bb7b-b52cc037427d · inbound

Sample-efficient LLM Optimization with Reset Replay cites this paper.

Sample-efficient LLM Optimization with Reset Replay Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:41:54.724211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b63b8c6b-554a-492a-bb64-920db5a6814c · inbound

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning cites this paper.

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-16T22:43:37.903879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8981378c-8c65-4256-96ea-723f954ccbe0 · inbound

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

Compatibility-Aware Dynamic Fine-Tuning for Large Language Models Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-07-05T02:30:40.875988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.