{"data":{"event":{"id":"92964bd3-5bbc-45fa-b3b5-73316d6aea78","slug":"closing-the-loop-branch-and-bound-for-scalable-verification-of-nonlinear-66a2750fcd","title":"Closing the Loop: Branch-and-Bound for Scalable Verification of Nonlinear Neural Feedback Systems","short_summary":"arXiv:2609.16298v1 Announce Type: new \nAbstract: Despite recent advances in the verification of nonlinear neural feedback systems, scalability remains the central obstacle, as state-of-the-art solvers do not yet handle the network sizes and nonlinear dynamics of autonomy applications. Combinatorial solvers do not scale to large networks, whereas propagative solvers excessively sacrifice precision. This work seeks to improve the scalability of combinatorial solvers by formulating verification as branch-and-bound on an abstraction of the closed-loop system. We introduce \\rail, an interface that ","full_description":"arXiv:2609.16298v1 Announce Type: new \nAbstract: Despite recent advances in the verification of nonlinear neural feedback systems, scalability remains the central obstacle, as state-of-the-art solvers do not yet handle the network sizes and nonlinear dynamics of autonomy applications. Combinatorial solvers do not scale to large networks, whereas propagative solvers excessively sacrifice precision. This work seeks to improve the scalability of combinatorial solvers by formulating verification as branch-and-bound on an abstraction of the closed-loop system. We introduce \\rail, an interface that exposes polyhedral enclosures of the dynamics to LiRPA-style bound propagation, and \\clipper, a branch-and-bound algorithm that jointly refines enclosures and splits controller activations. This framework enables joint reasoning on the computational graph of the closed-loop system, preserving symbolic correlations across time steps. We present our construction and show that it yields significant improvements over the state of the art.","ledger_type":"benefit","primary_domain_id":"fc7d617f-c9df-4b9f-b595-4408915ea380","event_status":"provisional","event_date":"2026-09-16T00:00:00.000Z","discovery_date":"2026-09-16T00:00:00.000Z","first_published_date":"2026-09-16T00:00:00.000Z","last_reviewed_date":"2026-09-16T00:00:00.000Z","geographic_scope":"International","affected_population":null,"base_impact_tier":1,"base_score":"1.00","attribution_multiplier":"0.1000","evidence_multiplier":"0.1000","realization_multiplier":"0.2000","durability_multiplier":"0.5000","current_event_score":"0.001000","confidence_level":"low","score_explanation":"Auto-published from news ingest as a provisional placeholder. Score is conservative until a named release is identified and the record is rescored.","methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","original_methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","published_at":"2026-09-17T03:00:58.991Z","created_at":"2026-09-17T03:00:58.991Z","updated_at":"2026-09-17T03:00:58.991Z","flags":[],"domain_name":"Other","domain_slug":"other","methodology_version":"0.2"},"contributions":[{"id":"cff0883a-ef33-4e6a-9c8b-72d83dee6c20","event_id":"92964bd3-5bbc-45fa-b3b5-73316d6aea78","model_id":"535014f7-c941-4d39-aa9b-8f9c1d3d07b7","role_description":"Unspecified system mentioned or implied by a news item. Remap to a named release when identified.","attribution_multiplier":"0.1000","credit_share":"1.0000","contribution_score":"0.001000","attribution_rationale":"News ingest does not infer a named model from the publisher alone. Attribution stays unspecified until a release is identified.","attribution_confidence":"medium","first_used_date":"2026-09-16T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-17T03:00:59.002Z","model_slug":"unspecified-ai-system","model_name":"Unspecified AI system","identity_class":"unknown","is_internal":false,"family_name":"Unspecified","family_slug":"unknown-unspecified","organization_name":"Unknown","organization_slug":"unknown"}],"sources":[{"id":"63ed9f6e-c03e-497b-b973-62e6540c41c4","event_id":"92964bd3-5bbc-45fa-b3b5-73316d6aea78","url":"https://arxiv.org/abs/2609.16298","canonical_url":"https://arxiv.org/abs/2609.16298","source_type":"preprint","publisher":"arXiv cs.AI","author":null,"publication_date":"2026-09-16T00:00:00.000Z","retrieved_at":"2026-09-17T03:00:59.008Z","title":"Closing the Loop: Branch-and-Bound for Scalable Verification of Nonlinear Neural Feedback Systems","excerpt":"arXiv:2609.16298v1 Announce Type: new \nAbstract: Despite recent advances in the verification of nonlinear neural feedback systems, scalability remains the central obstacle, as state-of-the-art solvers do not yet handle the network sizes and nonlinear dynamics of autonomy applications. Combinatorial solvers do not scale to large networks, whereas propagative solvers excessively sacrifice precision. This work seeks to improve the scalability of combinatorial solvers by formulating verification as ","content_hash":null,"source_reliability_class":"medium","is_primary_source":true,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-17T03:00:59.008Z"}],"claims":[{"id":"c0672236-5b8b-4fce-b717-9b6bb6223413","event_id":"92964bd3-5bbc-45fa-b3b5-73316d6aea78","claim_text":"Closing the Loop: Branch-and-Bound for Scalable Verification of Nonlinear Neural Feedback Systems","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-09-17T03:00:59.013Z","updated_at":"2026-09-17T03:00:59.013Z"}],"revisions":[{"id":"0e0c91d0-c66a-470e-961e-893e45c2a434","event_id":"92964bd3-5bbc-45fa-b3b5-73316d6aea78","model_id":null,"previous_score":"0.000000","new_score":"0.001000","previous_factors":{},"new_factors":{"tier":1,"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Auto-published from news ingest.","trigger_type":"news_ingest","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-17T03:00:59.020Z"}],"secondary":[]},"methodology_version":"0.1"}