Paper Citation Record · LEDGER

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization

As of 11 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2602.10635.

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

pith.paper-citation-record.v1
2602.10635 v3

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T01:06:00.983061Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+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

26 of 26 outbound references displayed

verified exact0
verified fuzzy0
unresolved26
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f12bc8a5-3925-45ee-99b7-148ab2f59cc9 · outbound

This paper cites Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.132667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 479cb759-e01d-4cdb-a087-77f07b5b330d · outbound

This paper cites Constrained dynamical neural ode for time se- ries modelling: A case study on continuous emotion prediction.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Constrained dynamical neural ode for time se- ries modelling: A case study on continuous emotion prediction

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.272249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f912b035-a23f-4a17-a9c6-22bebdab6706 · outbound

This paper cites an unresolved cited work.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.797049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f021cf14-1a22-43d5-a995-c7775c858822 · outbound

This paper cites an unresolved cited work.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.897242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 379506dd-ee90-4580-b518-7e1dde57f2bd · outbound

This paper cites A Closer Look at Deep Policy Gradients.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization A Closer Look at Deep Policy Gradients

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.370976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f0e2477-2c29-4e4e-a905-03477808b965 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Adam: A Method for Stochastic Optimization

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.420234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31738d9a-f240-4e64-a665-29932d082eca · outbound

This paper cites Avec 2016: Depression, mood, and emotion recognition workshop and challenge.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Avec 2016: Depression, mood, and emotion recognition workshop and challenge

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.572376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ea2e88a-9568-4ae7-a1c9-e41749e97fdc · outbound

This paper cites A novel markovian framework for integrating absolute and rela- tive ordinal emotion information.IEEE Transactions on Affective Computing, 14(3):2089–2101,.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization A novel markovian framework for integrating absolute and rela- tive ordinal emotion information.IEEE Transactions on Affective Computing, 14(3):2089–2101,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.598781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60f870d4-7118-468c-b7ab-d2e2b501c9e1 · outbound

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

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.665870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d70d34c-4bea-46ba-a8b1-1b22923ce84b · outbound

This paper cites and Zuo, C.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization and Zuo, C

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.708752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a83e5e2-bfa4-4e72-87d8-42e75a91dc1e · outbound

This paper cites The weighted F1 is then computed as: Weighted-F1= X c∈C nc N ·F1 c, wheren c is the number of true instances in classc,Nis the total number of instances, andCis the set of classes.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization The weighted F1 is then computed as: Weighted-F1= X c∈C nc N ·F1 c, wheren c is the number of true instances in classc,Nis the total number of instances, andCis the set of classes

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.733883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d736e1a9-c1f2-4504-b9da-c8ec1ec6e5de · outbound

This paper cites On the other hand, we implement the reinforcement learning training algorithms in Tab.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization On the other hand, we implement the reinforcement learning training algorithms in Tab

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.769281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26704a28-d3ce-4bd9-9ca5-40ad58f9da15 · outbound

This paper cites Finally, we provide a overlong length penalty, rlen which follows Zhang & Zuo (2025) to prevent excessive length and verbosity of responses.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Finally, we provide a overlong length penalty, rlen which follows Zhang & Zuo (2025) to prevent excessive length and verbosity of responses

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.839355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 606ef4aa-77bc-4e0d-80cf-774c5a9c8095 · outbound

This paper cites Each value is the arithmetic mean over datasets associated with the task.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Each value is the arithmetic mean over datasets associated with the task

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.870555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24f9f5cc-8648-48ac-aadd-3662e953c943 · outbound

This paper cites Additional Training Plots We provide additional training plots to empirically illustrate the training dynamics in our experiments.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Additional Training Plots We provide additional training plots to empirically illustrate the training dynamics in our experiments

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.951038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afc19102-6fec-470d-80dc-ffcaa2801f03 · outbound

This paper cites an unresolved cited work.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.983061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5260150-f11b-4100-836f-9de08d0bad6c · outbound

This paper cites Gemma 3 Technical Report.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Gemma 3 Technical Report

Reference 1999

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.540337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ec840dc-86cf-4f35-a63e-17064f35c7f0 · outbound

This paper cites R., Solar-Lezama, A., and Liang, P.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization R., Solar-Lezama, A., and Liang, P

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.452741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c0b38e1-2239-435a-9567-a92735cf59a5 · outbound

This paper cites Proximal Policy Optimization Algorithms.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Proximal Policy Optimization Algorithms

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.481906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 139aee29-5406-4717-aa0b-f2237a0ee3a3 · outbound

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

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.512187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5403f7c-d68e-468e-b1f9-7e8b52a930e6 · outbound

This paper cites K., Rahman, W., Zadeh, A.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization K., Rahman, W., Zadeh, A

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.315474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da63f133-7b5e-4a82-9817-c685d5efc9f1 · outbound

This paper cites MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.688949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79b87b2c-e996-4802-98ee-8c56dd83ec4b · outbound

This paper cites Qwen2.5-Omni Technical Report.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Qwen2.5-Omni Technical Report

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.643555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e55070f8-c239-4661-bfa7-89f31f9a80a7 · outbound

This paper cites REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.346002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f402657a-3fd1-49cf-839a-7b9207d68587 · outbound

This paper cites Qwen2.5-VL Technical Report.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Qwen2.5-VL Technical Report

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.156526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a07d16f-2563-4631-852d-7fbaf2949c9f · outbound

This paper cites Gpg: A simple and strong reinforcement learning baseline for model reasoning.arXiv preprint arXiv:2504.02546,.

OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization Gpg: A simple and strong reinforcement learning baseline for model reasoning.arXiv preprint arXiv:2504.02546,

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T01:06:00.230808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.