Paper Citation Record · LEDGER

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy

As of 3 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 2 inbound Pith citation observations for arXiv:2603.15646.

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

pith.paper-citation-record.v1
2603.15646 v2

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-15T17:08:23.269275Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-02T06:30:47.504484+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T15:03:42.266254Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-12T07:51:38.881425Z

Reference resolution

28 of 28 outbound references displayed

verified exact17
verified fuzzy6
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f7ed8e7f-0c5a-4c00-9a81-8acffdac8a78 · outbound

This paper cites H., Gendler, A., Baruch, E.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy H., Gendler, A., Baruch, E

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:10:11.210472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation bf8328d8-4c95-4557-a204-05683fd2b2ec · outbound

This paper cites HealthBench: Evaluating Large Language Models Towards Improved Human Health.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy HealthBench: Evaluating Large Language Models Towards Improved Human Health

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T17:10:10.350720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 02e6903c-9be5-42d8-bf6e-aef97cd6cd38 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Constitutional AI: Harmlessness from AI Feedback

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:10:10.332916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 1bacc138-fa68-4527-b4fe-2a77ad2b0d19 · outbound

This paper cites XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:06.160463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 67c5f086-2392-481f-9936-c73202b9170d · outbound

This paper cites Language models that think, chat better.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Language models that think, chat better

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:10:10.403000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 5d59b23f-9125-4152-91fd-b49ca58de998 · outbound

This paper cites Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:10:10.378588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation babd34df-a8b7-480c-8daf-1b43780aa7f0 · outbound

This paper cites arXiv preprint arXiv:2511.10507 , year=.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy arXiv preprint arXiv:2511.10507 , year=

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:10:10.357083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation e85495b3-c760-4a36-93ab-334b15bc8a38 · outbound

This paper cites Reinforcement Learning with Rubric Anchors.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Reinforcement Learning with Rubric Anchors

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:10:10.378397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 926a2f97-4b4c-4901-b841-6f6c88568dad · outbound

This paper cites MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T17:10:10.383743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 743c52f8-3add-4133-91d6-b5d6be436fbe · outbound

This paper cites Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:10:10.403325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation b8c6df27-566c-470d-9452-5dd60f4f12a1 · outbound

This paper cites Learning to optimize multi-objective alignment through dynamic reward weighting.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Learning to optimize multi-objective alignment through dynamic reward weighting

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:10:10.396976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 64ad7a06-22b8-4fe7-8cd6-be8316a5cda4 · outbound

This paper cites Online rubrics elicitation from pairwise comparisons.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Online rubrics elicitation from pairwise comparisons

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:10:10.372183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 230ddb86-54b7-48d0-85af-f7e6af4abd7e · outbound

This paper cites Proximal Policy Optimization Algorithms.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Proximal Policy Optimization Algorithms

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:10:10.339593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 4d72c8f2-1d8b-486d-aed7-81956b721a65 · outbound

This paper cites DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T00:00:28.487879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation b353b112-8ab4-4c92-b29c-0352a7f7fd9f · outbound

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

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:10:10.373798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 98fc3c8c-3610-4314-9f0a-407b49f7958d · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy HybridFlow: A Flexible and Efficient RLHF Framework

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:10:10.390724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 1544c5fe-57fb-47d7-8d66-bcc4ca1ba7ba · outbound

This paper cites Nemotron-cascade: Scaling cascaded reinforcement learning for general-purpose reasoning models.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Nemotron-cascade: Scaling cascaded reinforcement learning for general-purpose reasoning models

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:10:10.384722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 58184558-409e-4387-8175-a31b123cae3c · outbound

This paper cites arXiv preprint arXiv:2602.01511 , year=.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy arXiv preprint arXiv:2602.01511 , year=

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:10:10.351260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 03f65816-e7db-4a58-b780-04d4effd86f9 · outbound

This paper cites Qwen3 Technical Report.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Qwen3 Technical Report

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:10:10.389425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation df6a2493-f2bf-462a-84cb-ac6ed9e751ae · outbound

This paper cites Does this image satisfy this rule?.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Does this image satisfy this rule?

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T17:10:10.409449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation a8683238-ad7e-4b0a-aac5-b3bfd90353d4 · outbound

This paper cites Group Sequence Policy Optimization.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Group Sequence Policy Optimization

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:10:10.360727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation f49e56ad-0276-47f8-ac17-be9fbaa1550f · outbound

This paper cites Breaking the exploration bottleneck: Rubric-scaffolded reinforcement learning for general llm reasoning.arXiv preprint arXiv:2508.16949.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Breaking the exploration bottleneck: Rubric-scaffolded reinforcement learning for general llm reasoning.arXiv preprint arXiv:2508.16949

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:10:10.314742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation d3a505f3-a108-4713-8047-b886cb783476 · outbound

This paper cites I’m an emergency medicine physician.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy I’m an emergency medicine physician

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:10:11.215521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 86af8d85-5403-4cc1-8bdd-d5597f3e90b2 · outbound

This paper cites accuracy.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy accuracy

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:10:11.209097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation c880ebe9-ddf9-44eb-a386-db0d3aaeffc7 · outbound

This paper cites ‘list [ { “criterion.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy ‘list [ { “criterion

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:10:11.208091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 858c46ae-06b5-4637-ae2b-1cad7bfae204 · outbound

This paper cites Llama-3.1-8B-Instruct starts at 0.34 and achieves 0.70, while Qwen3-8B starts at a higher score0.58and achieves0.76.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy Llama-3.1-8B-Instruct starts at 0.34 and achieves 0.70, while Qwen3-8B starts at a higher score0.58and achieves0.76

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:10:11.213055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 58b581e5-cd56-4160-a5e6-b9b8e55bdbfe · outbound

This paper cites In ARL, we use the fixed meta-class Order 0: [completeness, accuracy, instruction following, context awareness, communication quality].

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy In ARL, we use the fixed meta-class Order 0: [completeness, accuracy, instruction following, context awareness, communication quality]

Reference 27

Resolution: malformed identifier; raw_fallback, observed 2026-05-15T17:10:11.204202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 28e83434-7346-41a8-b8c9-87c6ed66c940 · outbound

This paper cites The maximum response length is set to 2048, and the temperature in LLM sampling is set to 1.0 in the training process.

Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy The maximum response length is set to 2048, and the temperature in LLM sampling is set to 1.0 in the training process

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:10:11.211669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Pith citing papers

Observation 01682382-2014-48d5-872e-b6959ccacae6 · inbound

Reinforcement Learning for Scalable and Trustworthy Intelligent Systems cites this paper.

Reinforcement Learning for Scalable and Trustworthy Intelligent Systems Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy

Reference 164

Resolution: verified exact; local_arxiv, observed 2026-05-12T07:51:38.936160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-02T06:30:47.504484+00:00.

Observation 623215f7-1583-430c-8a30-443982b723de · inbound

Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions cites this paper.

Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T15:03:42.266254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.