{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I5NLUQMKEOIRU5QFGMQNKT5AZM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e42ff80effcd12cf3ec2c971535605e85c299c658a8d58ed5a2a212454ff789d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-16T09:17:51Z","title_canon_sha256":"d639c6f0d46a0e9d6d17ab963bb7b9172a3c6fb14622b41d94b97b6e92c4930f"},"schema_version":"1.0","source":{"id":"2603.15013","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.15013","created_at":"2026-06-26T01:15:18Z"},{"alias_kind":"arxiv_version","alias_value":"2603.15013v3","created_at":"2026-06-26T01:15:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.15013","created_at":"2026-06-26T01:15:18Z"},{"alias_kind":"pith_short_12","alias_value":"I5NLUQMKEOIR","created_at":"2026-06-26T01:15:18Z"},{"alias_kind":"pith_short_16","alias_value":"I5NLUQMKEOIRU5QF","created_at":"2026-06-26T01:15:18Z"},{"alias_kind":"pith_short_8","alias_value":"I5NLUQMK","created_at":"2026-06-26T01:15:18Z"}],"graph_snapshots":[{"event_id":"sha256:dff820c2b655a838e27ac44dc3786b50d22340e172bcf10834d7ab27337472c6","target":"graph","created_at":"2026-06-26T01:15:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"CycleRL achieves a 99.90% balance success rate, 1.15° heading tracking error, and 0.18 m/s velocity tracking error in simulation, with successful hardware deployment that validates DRL as offering superior adaptability over traditional methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That systematic domain randomization over a limited set of simulation parameters is sufficient to cover all real-world uncertainties and enable zero-shot transfer to physical hardware without additional adaptation or fine-tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CycleRL trains a PPO policy in Isaac Sim with domain randomization to achieve 99.9% balance success and direct hardware transfer for autonomous bicycle control."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CycleRL trains a PPO policy in simulation that transfers directly to physical bicycle hardware for balance and tracking."}],"snapshot_sha256":"a970ae49f726748f34243f01a428fefa1650167ea5d9ee3a7ae23cff98d93ace"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5f9cd9c3fd499629b3a9f3042127cedd64ceac46f0af372e23ad2d9aa594d7cc"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.15013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous bicycles offer a promising agile solution for urban mobility and last-mile logistics. However, conventional control strategies often struggle with underactuated nonlinear dynamics, suffering from sensitivity to model mismatches and limited adaptability to real-world uncertainties. To address this, we develop CycleRL, a comprehensive sim-to-real framework for robust autonomous bicycle control. Our approach establishes a direct perception-to-action mapping within the high-fidelity NVIDIA Isaac Sim environment, leveraging Proximal Policy Optimization (PPO) to optimize the control polic","authors_text":"Gelu Liu, Junliang Wu, Songyuan Li, Teng Wang, Xiangwei Zhu, Zhijie Wu","cross_cats":[],"headline":"CycleRL trains a PPO policy in simulation that transfers directly to physical bicycle hardware for balance and tracking.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-16T09:17:51Z","title":"CycleRL: Sim-to-Real Deep Reinforcement Learning for Robust Autonomous Bicycle Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.15013","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T10:41:17.457744Z","id":"ec36a41f-82c1-4726-b4a6-caf623a7545f","model_set":{"reader":"grok-4.3"},"one_line_summary":"CycleRL trains a PPO policy in Isaac Sim with domain randomization to achieve 99.9% balance success and direct hardware transfer for autonomous bicycle control.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CycleRL trains a PPO policy in simulation that transfers directly to physical bicycle hardware for balance and tracking.","strongest_claim":"CycleRL achieves a 99.90% balance success rate, 1.15° heading tracking error, and 0.18 m/s velocity tracking error in simulation, with successful hardware deployment that validates DRL as offering superior adaptability over traditional methods.","weakest_assumption":"That systematic domain randomization over a limited set of simulation parameters is sufficient to cover all real-world uncertainties and enable zero-shot transfer to physical hardware without additional adaptation or fine-tuning."}},"verdict_id":"ec36a41f-82c1-4726-b4a6-caf623a7545f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:767a51c0bed5db0b319dc812c578784484d9d96588e318e020149dd7bca06b27","target":"record","created_at":"2026-06-26T01:15:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e42ff80effcd12cf3ec2c971535605e85c299c658a8d58ed5a2a212454ff789d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-16T09:17:51Z","title_canon_sha256":"d639c6f0d46a0e9d6d17ab963bb7b9172a3c6fb14622b41d94b97b6e92c4930f"},"schema_version":"1.0","source":{"id":"2603.15013","kind":"arxiv","version":3}},"canonical_sha256":"475aba418a23911a76053320d54fa0cb1d1ed26faf618aad5b87f8905d81cbb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"475aba418a23911a76053320d54fa0cb1d1ed26faf618aad5b87f8905d81cbb7","first_computed_at":"2026-06-26T01:15:18.361625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:18.361625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pcxVjfjAWYO9Wwod0AXU6i6N13IToI3EZiVbcXS3Ue8WzzIPvR1EvcMnqDVZcJw7fvZQzUtWbpLeQ45O+GFCCw==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:18.362163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.15013","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:767a51c0bed5db0b319dc812c578784484d9d96588e318e020149dd7bca06b27","sha256:dff820c2b655a838e27ac44dc3786b50d22340e172bcf10834d7ab27337472c6"],"state_sha256":"3e08eb5aa6e7750dd55c6adfa8aa123bdc3395faf903bb619c6f8d5498bafc3c"}