{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NLDP5CEBW7XDTAZVUH563LFZFX","short_pith_number":"pith:NLDP5CEB","canonical_record":{"source":{"id":"2606.22145","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-20T16:54:36Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"bff43a001440ab492ad394030d626b8c1f391c7a689ce0cddb18138942df22c8","abstract_canon_sha256":"a33ffa94a1b5daf9798bceb7568360a654265259fc3a7fa525bbcb406c2cebb2"},"schema_version":"1.0"},"canonical_sha256":"6ac6fe8881b7ee398335a1fbedacb92dd5d90f9c83e59d4e2fe38edcd9726a16","source":{"kind":"arxiv","id":"2606.22145","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22145","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22145v1","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22145","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"NLDP5CEBW7XD","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"NLDP5CEBW7XDTAZV","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"NLDP5CEB","created_at":"2026-06-23T02:13:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NLDP5CEBW7XDTAZVUH563LFZFX","target":"record","payload":{"canonical_record":{"source":{"id":"2606.22145","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-20T16:54:36Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"bff43a001440ab492ad394030d626b8c1f391c7a689ce0cddb18138942df22c8","abstract_canon_sha256":"a33ffa94a1b5daf9798bceb7568360a654265259fc3a7fa525bbcb406c2cebb2"},"schema_version":"1.0"},"canonical_sha256":"6ac6fe8881b7ee398335a1fbedacb92dd5d90f9c83e59d4e2fe38edcd9726a16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:29.554144Z","signature_b64":"keYHpMjCGoIpIAtjPk1q0sWAChFNFXrPzKjRuEzlee+7/NboTyC1EIpkKzUNAfKDDM41a+B638qC9YQSU5GhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ac6fe8881b7ee398335a1fbedacb92dd5d90f9c83e59d4e2fe38edcd9726a16","last_reissued_at":"2026-06-23T02:13:29.553731Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:29.553731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.22145","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jDlGgQMxpgGxzdeExlQ+GGrFqRJXrEambERB9Rd/zmBFcDlN+5DiQgsqS9r2k4BZAsjjz8mYBjhCTvWbKMVyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T00:22:23.093712Z"},"content_sha256":"2d60cf9558e7861d907f9d4dd34f67739692d8cdb7ea1511825e49805423ec06","schema_version":"1.0","event_id":"sha256:2d60cf9558e7861d907f9d4dd34f67739692d8cdb7ea1511825e49805423ec06"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NLDP5CEBW7XDTAZVUH563LFZFX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Hien Tran, Nikki Xu","submitted_at":"2026-06-20T16:54:36Z","abstract_excerpt":"Reinforcement learning (RL) is a powerful and convenient tool to modernize controller design. In this work, we study the zero-shot transfer of RL-based control policies from simulation to hardware for cart-pole swing-up and stabilization. The two policies are trained independently, and the handoff is implemented in Simulink via switching logic. We apply a first-order action smoothing filter to prevent hardware damage from high-frequency oscillatory actuation. Pairing this bandwidth-aware filtering with sensitivity-guided domain randomization (DR) and a simple linear curriculum learning (CL) sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22145","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.22145/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T02:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4UZY3Znxy8DwcU+PXrt8QK8jO6CP+zgmXdJJX1NiEHzyfoocJrQhaW5y8OryjktpaASBsSbKURNx3u/iXX2hDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T00:22:23.094113Z"},"content_sha256":"4576714ab0e4ee5b93a6da9940653936164960ca61ec42804b261a54e3c71c06","schema_version":"1.0","event_id":"sha256:4576714ab0e4ee5b93a6da9940653936164960ca61ec42804b261a54e3c71c06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NLDP5CEBW7XDTAZVUH563LFZFX/bundle.json","state_url":"https://pith.science/pith/NLDP5CEBW7XDTAZVUH563LFZFX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NLDP5CEBW7XDTAZVUH563LFZFX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-28T00:22:23Z","links":{"resolver":"https://pith.science/pith/NLDP5CEBW7XDTAZVUH563LFZFX","bundle":"https://pith.science/pith/NLDP5CEBW7XDTAZVUH563LFZFX/bundle.json","state":"https://pith.science/pith/NLDP5CEBW7XDTAZVUH563LFZFX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NLDP5CEBW7XDTAZVUH563LFZFX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NLDP5CEBW7XDTAZVUH563LFZFX","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":"a33ffa94a1b5daf9798bceb7568360a654265259fc3a7fa525bbcb406c2cebb2","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-20T16:54:36Z","title_canon_sha256":"bff43a001440ab492ad394030d626b8c1f391c7a689ce0cddb18138942df22c8"},"schema_version":"1.0","source":{"id":"2606.22145","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22145","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22145v1","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22145","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"NLDP5CEBW7XD","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"NLDP5CEBW7XDTAZV","created_at":"2026-06-23T02:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"NLDP5CEB","created_at":"2026-06-23T02:13:29Z"}],"graph_snapshots":[{"event_id":"sha256:4576714ab0e4ee5b93a6da9940653936164960ca61ec42804b261a54e3c71c06","target":"graph","created_at":"2026-06-23T02:13:29Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.22145/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is a powerful and convenient tool to modernize controller design. In this work, we study the zero-shot transfer of RL-based control policies from simulation to hardware for cart-pole swing-up and stabilization. The two policies are trained independently, and the handoff is implemented in Simulink via switching logic. We apply a first-order action smoothing filter to prevent hardware damage from high-frequency oscillatory actuation. Pairing this bandwidth-aware filtering with sensitivity-guided domain randomization (DR) and a simple linear curriculum learning (CL) sc","authors_text":"Hien Tran, Nikki Xu","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-20T16:54:36Z","title":"Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22145","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2d60cf9558e7861d907f9d4dd34f67739692d8cdb7ea1511825e49805423ec06","target":"record","created_at":"2026-06-23T02:13:29Z","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":"a33ffa94a1b5daf9798bceb7568360a654265259fc3a7fa525bbcb406c2cebb2","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-20T16:54:36Z","title_canon_sha256":"bff43a001440ab492ad394030d626b8c1f391c7a689ce0cddb18138942df22c8"},"schema_version":"1.0","source":{"id":"2606.22145","kind":"arxiv","version":1}},"canonical_sha256":"6ac6fe8881b7ee398335a1fbedacb92dd5d90f9c83e59d4e2fe38edcd9726a16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ac6fe8881b7ee398335a1fbedacb92dd5d90f9c83e59d4e2fe38edcd9726a16","first_computed_at":"2026-06-23T02:13:29.553731Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:29.553731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"keYHpMjCGoIpIAtjPk1q0sWAChFNFXrPzKjRuEzlee+7/NboTyC1EIpkKzUNAfKDDM41a+B638qC9YQSU5GhCw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:29.554144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22145","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d60cf9558e7861d907f9d4dd34f67739692d8cdb7ea1511825e49805423ec06","sha256:4576714ab0e4ee5b93a6da9940653936164960ca61ec42804b261a54e3c71c06"],"state_sha256":"bcf6dd2cbe0a4686f517ab5cc8eb83d588d414ff0657b88e8ff8765b3e29295a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gXLHFml+wfM42Kh5VPJ6M1RVkjp7EW/OceDwM8Q8KN5zVWMhQtuEQaIESRiZO80srJAUE9QfPwuh3f2gqBKtCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T00:22:23.096141Z","bundle_sha256":"4266184a3066b64fc19f7fe3bd4ac0a6ea1959c55106ffbc0d50baa4e1ee5c35"}}