Paper Citation Record · LEDGER

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders

As of 8 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2604.22504.

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

pith.paper-citation-record.v1
2604.22504 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-08T10:15:03.085089Z

measured 24 of 24 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 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

24 of 24 outbound references displayed

verified exact15
verified fuzzy5
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 964ba8ef-7a0c-4f52-9c34-269467363e33 · outbound

This paper cites Decoding Matters: Addressing Amplification Bias and Homogeneity Issue for LLM-based Recommendation.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Decoding Matters: Addressing Amplification Bias and Homogeneity Issue for LLM-based Recommendation

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:06:13.396003Z

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 ac948618-8742-47c7-84aa-2724d234a1d0 · outbound

This paper cites Learn- ing recommenders for implicit feedback with importance resampling.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Learn- ing recommenders for implicit feedback with importance resampling

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T15:27:35.223486Z

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 522d5109-4e9b-4ab3-b5dd-17c88ea367af · outbound

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

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-11T20:06:13.402702Z

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 bb461742-1d85-4b1e-9285-936e3f509b72 · outbound

This paper cites OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-12T18:30:36.120082Z

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 9bd0f90c-0934-4226-a4e6-a533175dd894 · outbound

This paper cites The Llama 3 Herd of Models.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders The Llama 3 Herd of Models

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T20:06:13.504441Z

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 8e2d1ddc-ede7-432a-a8d5-54d4031012d3 · outbound

This paper cites Session-based Recommendations with Recurrent Neural Networks.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Session-based Recommendations with Recurrent Neural Networks

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:09:40.489683Z

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 51abb986-447f-42e4-987b-528d434bb6d4 · outbound

This paper cites Minionerec: An open-source framework for scaling generative recommendation.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Minionerec: An open-source framework for scaling generative recommendation

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:06:13.413098Z

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 cd8fd457-bb81-4751-9909-017f0893335e · outbound

This paper cites Crafting papers on machine learning.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Crafting papers on machine learning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T15:27:35.226816Z

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 0c855c14-4c4a-4195-8905-e5a1818efe90 · outbound

This paper cites Disco: Re- inforcing large reasoning models with discriminative con- strained optimization.arXiv preprint arXiv:2505.12366.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Disco: Re- inforcing large reasoning models with discriminative con- strained optimization.arXiv preprint arXiv:2505.12366

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:06:13.470502Z

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 014a8510-7410-4c4a-9a57-3c99bed92759 · outbound

This paper cites DeepSeek-V3 Technical Report.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders DeepSeek-V3 Technical Report

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-11T20:06:13.476449Z

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 c8d4ff5a-950a-466b-a6ed-5a02f33984a0 · outbound

This paper cites Is ChatGPT a Good Recommender? A Preliminary Study.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Is ChatGPT a Good Recommender? A Preliminary Study

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:06:13.500120Z

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 505070c2-ccfd-4313-9ae4-7ed31c603822 · outbound

This paper cites Decoupled Weight Decay Regularization.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Decoupled Weight Decay Regularization

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-11T20:06:13.526901Z

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 a16d341f-20f6-405a-be22-9990cb11a941 · outbound

This paper cites Negative Sampling in Recommendation: A Survey and Future Directions.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Negative Sampling in Recommendation: A Survey and Future Directions

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:06:13.464535Z

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 c0483577-56fe-4419-93cc-5ccdf652f6af · outbound

This paper cites Analyzing a portion of the ROC curve.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Analyzing a portion of the ROC curve

Reference 14

Resolution: verified exact; doi, observed 2026-05-08T22:09:17.613970Z

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 71bac23e-a799-44ff-8295-4d41d617aa60 · outbound

This paper cites GPT-4 Technical Report.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders GPT-4 Technical Report

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-11T20:06:13.418533Z

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 30c8e4cf-6dfd-4881-bded-ca2f296b4286 · outbound

This paper cites Qwen2.5 Technical Report.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Qwen2.5 Technical Report

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T20:06:13.454362Z

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 9c05f0da-3174-43e1-88a0-4544fc0824d0 · outbound

This paper cites BPR: Bayesian Personalized Ranking from Implicit Feedback.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders BPR: Bayesian Personalized Ranking from Implicit Feedback

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-13T22:59:04.301080Z

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 f41de597-35e9-44aa-bb8a-9a7a75c5d114 · outbound

This paper cites Lower-left partial auc: An effective and ef- ficient optimization metric for recommendation.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Lower-left partial auc: An effective and ef- ficient optimization metric for recommendation

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T15:27:35.219499Z

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 a02e5170-1516-475b-bb0f-f79c22d65a30 · outbound

This paper cites Tan, J., Chen, Y ., Zhang, A., Jiang, J., Liu, B., Xu, Z., Han, Z., Xu, J., Zheng, B., and Wang, X.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Tan, J., Chen, Y ., Zhang, A., Jiang, J., Liu, B., Xu, Z., Han, Z., Xu, J., Zheng, B., and Wang, X

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:06:13.490788Z

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 8adb6688-a0bd-49c9-ae70-57f88580fb5b · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-11T20:06:13.444264Z

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 662e54bb-ecd9-442c-8833-976145f1c9cf · outbound

This paper cites Group Sequence Policy Optimization.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Group Sequence Policy Optimization

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T20:06:13.531498Z

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 9e4dd9e2-f19f-4f7b-8464-f6c19c3edcd8 · outbound

This paper cites Onerec technical report.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Onerec technical report

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:06:13.482882Z

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 19c29abe-bc25-4e79-87ff-a51d55d7a7b2 · outbound

This paper cites Experimental Settings G.1.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders Experimental Settings G.1

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T15:27:35.212164Z

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 4eb43935-200d-4a19-8506-5acd6c049afb · outbound

This paper cites During fine-tuning, SFT and preference- alignment data are processed with batch size 128, while reinforcement learning uses batch size.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders During fine-tuning, SFT and preference- alignment data are processed with batch size 128, while reinforcement learning uses batch size

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T15:27:35.215993Z

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.

Pith citing papers

No inbound Pith citation observations are available.