Paper Citation Record · LEDGER

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training

As of 23 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 1 inbound Pith citation observation for arXiv:2510.15859.

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

pith.paper-citation-record.v1
2510.15859 v5

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T09:22:46.580769Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T23:18:59.283834Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-06-29T23:24:01.706149Z

Reference resolution

40 of 40 outbound references displayed

verified exact0
verified fuzzy0
unresolved38
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a34295d0-34fb-43cc-be62-9b00871745fe · outbound

This paper cites GPT-4 Technical Report.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:40.110994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51d06983-6196-491a-a143-7cccab947567 · outbound

This paper cites Language models that think, chat better.arXiv preprint arXiv:2509.20357,.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Language models that think, chat better.arXiv preprint arXiv:2509.20357,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:40.930592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5276c8a0-776e-41c3-b934-af35ee4e937e · outbound

This paper cites Ace-rl: Adaptive constraint-enhanced reward for long-form generation re- inforcement learning.arXiv preprint arXiv:2509.04903,.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Ace-rl: Adaptive constraint-enhanced reward for long-form generation re- inforcement learning.arXiv preprint arXiv:2509.04903,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:41.760730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63376715-0001-4f25-9e4d-3cea55bbc407 · outbound

This paper cites HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:41.903752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a388ea47-140f-42eb-bebb-9b2e25ba3a5f · outbound

This paper cites SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:42.012260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71bb4fec-3170-44f5-859f-ac3bc0284b3a · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:42.136987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60b940e9-440d-40ff-9dc9-27b582546b88 · outbound

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

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training UltraFeedback: Boosting Language Models with Scaled AI Feedback

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:42.290521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd3fcd13-dbfe-47c0-a4ad-eea3a1adb75f · outbound

This paper cites Multichallenge: A realistic multi-turn con- versation evaluation benchmark challenging to frontier llms.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Multichallenge: A realistic multi-turn con- versation evaluation benchmark challenging to frontier llms

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:42.370031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c49ab613-422c-446f-ae97-617e899e3be1 · outbound

This paper cites Qa-lign: Aligning llms through constitution- ally decomposed qa.arXiv preprint arXiv:2506.08123,.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Qa-lign: Aligning llms through constitution- ally decomposed qa.arXiv preprint arXiv:2506.08123,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:42.457913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 294d778f-1817-420d-8322-4c8adf78cb60 · outbound

This paper cites Baichuan-M2: Scaling Medical Capability with Large Verifier System.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Baichuan-M2: Scaling Medical Capability with Large Verifier System

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:42.521571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b9a9b21-0407-4aae-9415-86805e856077 · outbound

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

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:42.681512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5406e69-7612-4621-ac78-c534ba31f751 · outbound

This paper cites m1: Unleash the potential of test-time scaling for medical reasoning with large language models.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training m1: Unleash the potential of test-time scaling for medical reasoning with large language models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:42.737007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 793ac8f9-4666-4d31-bcaf-393bc9335441 · outbound

This paper cites Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:42.829865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 587ece49-1ab1-4654-ac28-0f2667bb4dd4 · outbound

This paper cites Reward Design with Language Models.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Reward Design with Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:42.928860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f751fc81-a66f-4fa7-8f16-a766a6380e8e · outbound

This paper cites Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:42.993723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fca7aa40-b80c-4670-830c-3d39af3f28e3 · outbound

This paper cites WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:43.139966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4744b8c1-bbb1-4855-a935-21941b67f116 · outbound

This paper cites Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:43.249504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff6b3a35-f140-4610-ab3a-9d208e1706cc · outbound

This paper cites Large Language Models: A Survey.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Large Language Models: A Survey

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:43.509662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1af21bce-07ba-4364-b4ea-b1fbbe0452e2 · outbound

This paper cites InFoBench: Evaluating Instruction Following Ability in Large Language Models.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training InFoBench: Evaluating Instruction Following Ability in Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:43.631107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38d1f916-1045-44e5-8421-baec885ace3b · outbound

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

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:43.796312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2ac91dd-c48d-493a-82c6-34ae2609fbbf · outbound

This paper cites RL's Razor: Why Online Reinforcement Learning Forgets Less.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training RL's Razor: Why Online Reinforcement Learning Forgets Less

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:43.958435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96fb2987-9169-495a-9dff-6ae253a63d3b · outbound

This paper cites PaperBench: Evaluating AI's Ability to Replicate AI Research.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training PaperBench: Evaluating AI's Ability to Replicate AI Research

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:44.150906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eb2586a-26f0-400b-9932-9c66dff9cdbf · outbound

This paper cites Reasonmed: A 370k multi-agent gen- erated dataset for advancing medical reasoning.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Reasonmed: A 370k multi-agent gen- erated dataset for advancing medical reasoning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:44.258716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa0317e5-b0e1-45ca-ace3-98938490fd10 · outbound

This paper cites Medagents: Large language models as collab- orators for zero-shot medical reasoning.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Medagents: Large language models as collab- orators for zero-shot medical reasoning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:44.414968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80bf72b1-c7a5-4bf5-98d8-26b69633403a · outbound

This paper cites Large language models in medicine.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Large language models in medicine

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:44.556266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 741df60c-8317-4065-983d-3d5ed13632cc · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:44.781689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 678fc548-cf3e-4a30-9635-aa752f0a62c4 · outbound

This paper cites Check- lists are better than reward models for aligning language models.arXiv preprint arXiv:2507.18624,.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Check- lists are better than reward models for aligning language models.arXiv preprint arXiv:2507.18624,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:44.929913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1870351-44ba-4f14-a312-fa747656f6df · outbound

This paper cites MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:45.109601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 802c15a0-7022-4caa-a725-9cef68be0c0c · outbound

This paper cites Qwen3 Technical Report.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Qwen3 Technical Report

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:45.350657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26268332-ed02-44b4-a5b1-ce3c2620eeac · outbound

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

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:45.579042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 836e7d2c-8598-4d25-af18-27d1615279d0 · outbound

This paper cites Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:45.779908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20a10f86-11cb-404d-a60b-1361d6a94a3e · outbound

This paper cites Group Sequence Policy Optimization.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Group Sequence Policy Optimization

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:45.967654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc648d4f-9614-4142-a76f-279483902ed3 · outbound

This paper cites Ask patients with patience: Enabling llms for human-centric medical dialogue with grounded reasoning.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Ask patients with patience: Enabling llms for human-centric medical dialogue with grounded reasoning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:46.126866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2802811a-1746-40bb-a8e7-eff22721f8c9 · outbound

This paper cites an unresolved cited work.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Unresolved cited work

Reference 38

Resolution: malformed identifier; no resolver link, observed 2026-08-04T09:22:46.265245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e897e7e-7f88-4ebb-a878-fa4b0e154b2e · outbound

This paper cites This subplot measures the proportion of rubrics that are satisfied (or penalties avoided) at least once within 40 rollouts for each query.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training This subplot measures the proportion of rubrics that are satisfied (or penalties avoided) at least once within 40 rollouts for each query

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:46.416690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e83c4e79-9d64-455c-945c-dd0649c27e0b · outbound

This paper cites For all other models, the generation parameters were set to align with those specified in the official HealthBench protocol.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training For all other models, the generation parameters were set to align with those specified in the official HealthBench protocol

Reference 40

Resolution: malformed identifier; no resolver link, observed 2026-08-04T09:22:46.580769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4c0393d-1008-4caa-8887-5e2d3577686c · outbound

This paper cites A generalist medical language model for disease diagnosis assistance.Nature medicine, 31(3):932–942, 2025e.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training A generalist medical language model for disease diagnosis assistance.Nature medicine, 31(3):932–942, 2025e

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:43.377717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 569f998a-5475-4431-8715-ae8ea0b8a4b4 · outbound

This paper cites gpt-oss-120b & gpt-oss-20b Model Card.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training gpt-oss-120b & gpt-oss-20b Model Card

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:40.275971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 283ec89e-9879-4524-8c41-9972e0ec7745 · outbound

This paper cites Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning.

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learning

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:42.597472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 453fc6cf-e046-4366-a789-5159e2506e8c · outbound

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

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training HealthBench: Evaluating Large Language Models Towards Improved Human Health

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T09:22:40.462108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 372bc0a3-133d-40e8-a4f9-58acde27eaf9 · inbound

LLM-as-a-Judge in Healthcare: A Scoping Analysis of Applications, Methods, and Human Alignment cites this paper.

LLM-as-a-Judge in Healthcare: A Scoping Analysis of Applications, Methods, and Human Alignment InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training

Reference 152

Resolution: verified exact; local_arxiv, observed 2026-06-29T23:24:01.707495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.