Paper Citation Record · LEDGER

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding

As of 20 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2506.07434.

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

pith.paper-citation-record.v1
2506.07434 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:41:59.898754Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+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

37 of 37 outbound references displayed

verified exact1
verified fuzzy0
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f42454d5-f4d2-4ceb-ad89-ed16655ecc5b · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.723254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2d04461-63eb-4683-b39b-d4ff39bc5ba2 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Evaluating Large Language Models Trained on Code

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.728663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2454226-aa40-439d-94cf-58f199d91b95 · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.733623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6eab885f-f233-43d4-8214-d026879de2c8 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Training Verifiers to Solve Math Word Problems

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.738804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c126313-59e3-46f2-898b-59f623c5335b · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:42:00.429903Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e263492c-a53e-4a19-8da9-d8a058e9ebe8 · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.748520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69929be8-2c5d-4f29-a7f4-a1d5c50a16da · outbound

This paper cites The Llama 3 Herd of Models.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding The Llama 3 Herd of Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.754141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c48dca-cb8a-40da-979e-57de75e1eca0 · outbound

This paper cites Towards a Unified View of Preference Learning for Large Language Models: A Survey.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Towards a Unified View of Preference Learning for Large Language Models: A Survey

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.758542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4aa96fc-ea8e-414f-b248-0a220dd2f454 · outbound

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

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Gemma 2: Improving Open Language Models at a Practical Size

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.763408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf14a360-c7d7-4ca5-8200-7361abb00d9a · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.768395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcf37842-a86b-4865-9d2e-62087eda24fa · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:42:00.414961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 728195e0-4188-42a7-836a-cbd81a21e6c0 · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:42:00.399434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ae38a833-d89b-4e7b-966f-acd3521c1e16 · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.783935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26d64d00-ed8d-4e16-a975-c5d840efa41c · outbound

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

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Gonzalez, Hao Zhang, and Ion Stoica

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.788661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea847371-9676-4b68-b5cc-1bb76b531e33 · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.793457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0ca6ada-dfb6-47b6-8910-fc9d13ec4de4 · outbound

This paper cites Cascade Reward Sampling for Efficient Decoding-Time Alignment.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Cascade Reward Sampling for Efficient Decoding-Time Alignment

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.798320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddb1f633-567c-4dda-b123-7a64809bc191 · outbound

This paper cites From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.803056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f06e1fb-6d84-4874-9fae-94f8a8f16659 · outbound

This paper cites Hashimoto.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Hashimoto

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.807985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04d88e52-dcd1-4a23-a4db-dbe687d393af · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:42:00.343664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3c235bbf-c136-439c-8880-3a62de372171 · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:42:00.327360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b619c84c-ea22-4f36-88f2-510e374b9de2 · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.822198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00cfa11b-6d35-4e7e-b128-ccc94a2bde9c · outbound

This paper cites Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.826898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da3a15be-3b24-40f3-b24f-ff7ad75c4025 · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.831536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10244946-515c-4eac-8887-dbf5191fb7c2 · outbound

This paper cites MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:42:00.035197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6afa6bf8-e9d3-4407-b26d-c19045ce25ef · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.841106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70609451-2c99-4a11-ada2-fca543dd2f80 · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:42:00.291938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5375d0f2-0ab7-45de-a8a9-108c59f968fc · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.850453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98d78969-e2bd-4620-bd8a-ea940cc3af37 · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.855461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a32203e1-f232-4ca3-9054-d26c33800a0b · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:42:00.256598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 50457d42-c2c4-4bdf-9aec-af5d02db6c69 · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:42:00.240191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 875c2e27-052c-4e7f-bbbd-d4b8646455d2 · outbound

This paper cites Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.868635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38ed5144-7e39-40df-b130-03924ff07c98 · outbound

This paper cites HelpSteer2-Preference: Complementing Ratings with Preferences.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding HelpSteer2-Preference: Complementing Ratings with Preferences

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.874401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b1f624a-b78e-40e0-92a9-ae8961a70220 · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.879020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25a722e3-a79e-495b-b7cf-4b0ae3582c2b · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.883540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 022ed38c-2672-427e-b021-93c840d06276 · outbound

This paper cites an unresolved cited work.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.888508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 770a7858-670d-4cbb-ba78-232a78c0282e · outbound

This paper cites online" 'onlinestring :=.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding online" 'onlinestring :=

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.893439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 002ea223-2ba5-45dc-8dfe-98b998b3b746 · outbound

This paper cites write newline.

Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding write newline

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:59.898754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.