---
type: "post"
id: "the-si-ocp-paper-was-accepted-to-cdc-ecf333"
slug: "the-si-ocp-paper-was-accepted-to-cdc-ecf333"
title: "The SI-OCP paper was accepted to CDC 2026, and the authors released a GitHub repository ."
description: "**Thesis:** SI-OCP turns online prediction errors into an integral uncertainty score for adaptive systems whose state derivatives are not measured."
retrieval_nugget: "**Thesis:** SI-OCP turns online prediction errors into an integral uncertainty score for adaptive systems whose state derivatives are not measured."
published_at: "2026-10-16"
updated_at: "2026-10-16"
record_date: "2026-10-16"
date_kind: "published_at"
topics: ["github"]
source_urls: ["https://arxiv.org/abs/2604.06058"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:the-si-ocp-paper-was-accepted-to-cdc-ecf333"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:8ebbedde5dc70834231c9f85b449e3690895585d23574ea28c69cd2b8b3c4caf","reviewed_at":"2026-10-16T03:00:13.440Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"SI-OCP turns online prediction errors into an integral uncertainty score for adaptive systems whose state derivatives are not measured.","observed_facts":[{"text":"The arXiv abstract says SI-OCP uses an integral score function to quantify the lumped effect of disturbance and learning error.","source_urls":["https://arxiv.org/abs/2604.06058"]},{"text":"The record states the paper was accepted to CDC 2026.","source_urls":["https://arxiv.org/abs/2604.06058"]},{"text":"The authors report a numerical simulation of an all-layer adaptive deep neural network quadcopter using robust tube MPC.","source_urls":["https://arxiv.org/abs/2604.06058"]}],"mechanism":"The integral score aggregates disturbance and learning error into an online uncertainty estimate; authors report long-run coverage guarantees and synthesis with safety-critical controllers such as robust tube MPC.","why_now":"The result addresses a practical gap in safety-critical adaptive control: conventional online conformal prediction is insufficient when systems adapt their dynamics without observations of state derivatives.","implications":["Researchers can evaluate SI-OCP as an uncertainty-estimation component in adaptive control stacks.","The reported quadcopter result is simulation evidence, not validation of physical flight or deployment."],"evidence_boundary":"The supplied arXiv record describes a numerical simulation and reports the authors’ guarantees; it does not establish real-world flight testing, deployment, or performance against other methods. The supplied material does not substantiate repository contents or reproducibility claims.","watch_conditions":["Look for independently inspectable code, benchmark comparisons, or physical flight tests that clarify how the method behaves beyond the reported simulation."],"related_records":[],"new_branch_reason":"Acceptance and a simulation make this a distinct research record; no prior New Runtime record was supplied as a basis for linking it to an existing analytical thread."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/the-si-ocp-paper-was-accepted-to-cdc-ecf333/","markdown":"https://newruntime.com/posts/the-si-ocp-paper-was-accepted-to-cdc-ecf333.md","json":"https://newruntime.com/posts/the-si-ocp-paper-was-accepted-to-cdc-ecf333.json"}
---

# The SI-OCP paper was accepted to CDC 2026, and the authors released a GitHub repository .

## Retrieval answer

**Thesis:** SI-OCP turns online prediction errors into an integral uncertainty score for adaptive systems whose state derivatives are not measured.

**Thesis:** SI-OCP turns online prediction errors into an integral uncertainty score for adaptive systems whose state derivatives are not measured.

The paper describes an algorithm that uses an integral score function to quantify the lumped effect of disturbance and learning error. **Mechanism:** The integral score aggregates disturbance and learning error into an online uncertainty estimate; authors report long-run coverage guarantees and synthesis with safety-critical controllers such as robust tube MPC. The arXiv record says the paper was accepted to CDC 2026.

**Why now:** The result addresses a practical gap in safety-critical adaptive control: conventional online conformal prediction is insufficient when systems adapt their dynamics without observations of state derivatives. The paper’s numerical demonstration uses an all-layer adaptive deep neural network controlling a quadcopter with robust tube MPC. **First implication:** Researchers can evaluate SI-OCP as an uncertainty-estimation component in adaptive control stacks.

**Evidence boundary:** The supplied arXiv record describes a numerical simulation and reports the authors’ guarantees; it does not establish real-world flight testing, deployment, or performance against other methods. The supplied material does not substantiate repository contents or reproducibility claims.

**First watch condition:** Look for independently inspectable code, benchmark comparisons, or physical flight tests that clarify how the method behaves beyond the reported simulation. Acceptance and a simulation make this a distinct research record; no prior New Runtime record was supplied as a basis for linking it to an existing analytical thread.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Github](https://newruntime.com/topics/github.md): Explore the github topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)