{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TSTO6BRDXBDB4ZAAJS64QMQ6W5","short_pith_number":"pith:TSTO6BRD","canonical_record":{"source":{"id":"2510.20152","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2025-10-23T03:00:04Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"811d80d5b8fb49a54c074874e3f926b4e8a09c9dcfbe6a20c640af3a83d0ed5d","abstract_canon_sha256":"b27d02767b8257f5fe6e3837762718f35a2a0ca162c80f43dfa53ddcb2077b7b"},"schema_version":"1.0"},"canonical_sha256":"9ca6ef0623b8461e64004cbdc8321eb74584d0eeff8bebf2cc4792d145d304be","source":{"kind":"arxiv","id":"2510.20152","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.20152","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2510.20152v4","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.20152","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"TSTO6BRDXBDB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TSTO6BRDXBDB4ZAA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TSTO6BRD","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TSTO6BRDXBDB4ZAAJS64QMQ6W5","target":"record","payload":{"canonical_record":{"source":{"id":"2510.20152","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2025-10-23T03:00:04Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"811d80d5b8fb49a54c074874e3f926b4e8a09c9dcfbe6a20c640af3a83d0ed5d","abstract_canon_sha256":"b27d02767b8257f5fe6e3837762718f35a2a0ca162c80f43dfa53ddcb2077b7b"},"schema_version":"1.0"},"canonical_sha256":"9ca6ef0623b8461e64004cbdc8321eb74584d0eeff8bebf2cc4792d145d304be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:33.739817Z","signature_b64":"KNYqZbuwGDwXW3RtTZxmORQfObcp2CZn5e1fXn1vnoSRFjUYh5o9/yuKD8tAwaXL6jJS8baZHe8CdjzG9fWXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ca6ef0623b8461e64004cbdc8321eb74584d0eeff8bebf2cc4792d145d304be","last_reissued_at":"2026-05-18T03:09:33.739378Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:33.739378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.20152","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3uGhSZ6n1J4PtB35HadFnFW9RG3GHHt1Ctb0ErFO4P7PRJ4qjhFVJ55PWWFNYsIiOmBqBzAwH5BAKxo0WqqECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T11:59:12.972620Z"},"content_sha256":"87c31e6471f74d7dfe42f099dcfdfed051e3f94c0150b461599157d3d1f7d3ce","schema_version":"1.0","event_id":"sha256:87c31e6471f74d7dfe42f099dcfdfed051e3f94c0150b461599157d3d1f7d3ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TSTO6BRDXBDB4ZAAJS64QMQ6W5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Soft Switching Expert Policies for Controlling Systems with Uncertain Parameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Junya Ikemoto","submitted_at":"2025-10-23T03:00:04Z","abstract_excerpt":"This paper proposes a simulation-based reinforcement learning algorithm for controlling systems with uncertain and varying system parameters. While simulators are useful for safely learning control policies, the reality gap remains a major challenge. To alleviate this challenge, we propose a two-stage algorithm. First, multiple control policies are learned for systems with different system parameters in a simulator. Second, for a real system, the control policies are adaptively switched using an online convex optimization algorithm based on observations. This approach is expected to reduce lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.20152","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T03:09:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FABN3K2KRSDpYk001IeQs3XhZSZmL5ldhM33u79qk3f0fcbwFpxyCy7yC/efGy2f1nPVdxYAsscQ1kiAX0s+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T11:59:12.972973Z"},"content_sha256":"b9e39e1a326b67796be2946cb6b5b8efed22a828abd8d923a5f8b3594bde21d8","schema_version":"1.0","event_id":"sha256:b9e39e1a326b67796be2946cb6b5b8efed22a828abd8d923a5f8b3594bde21d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5/bundle.json","state_url":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5/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":"2026-05-21T11:59:12Z","links":{"resolver":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5","bundle":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5/bundle.json","state":"https://pith.science/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TSTO6BRDXBDB4ZAAJS64QMQ6W5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TSTO6BRDXBDB4ZAAJS64QMQ6W5","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":"b27d02767b8257f5fe6e3837762718f35a2a0ca162c80f43dfa53ddcb2077b7b","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2025-10-23T03:00:04Z","title_canon_sha256":"811d80d5b8fb49a54c074874e3f926b4e8a09c9dcfbe6a20c640af3a83d0ed5d"},"schema_version":"1.0","source":{"id":"2510.20152","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.20152","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"arxiv_version","alias_value":"2510.20152v4","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.20152","created_at":"2026-05-18T03:09:33Z"},{"alias_kind":"pith_short_12","alias_value":"TSTO6BRDXBDB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TSTO6BRDXBDB4ZAA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TSTO6BRD","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:b9e39e1a326b67796be2946cb6b5b8efed22a828abd8d923a5f8b3594bde21d8","target":"graph","created_at":"2026-05-18T03:09:33Z","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"},"paper":{"abstract_excerpt":"This paper proposes a simulation-based reinforcement learning algorithm for controlling systems with uncertain and varying system parameters. While simulators are useful for safely learning control policies, the reality gap remains a major challenge. To alleviate this challenge, we propose a two-stage algorithm. First, multiple control policies are learned for systems with different system parameters in a simulator. Second, for a real system, the control policies are adaptively switched using an online convex optimization algorithm based on observations. This approach is expected to reduce lea","authors_text":"Junya Ikemoto","cross_cats":["cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2025-10-23T03:00:04Z","title":"Soft Switching Expert Policies for Controlling Systems with Uncertain Parameters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.20152","kind":"arxiv","version":4},"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":"sha256:87c31e6471f74d7dfe42f099dcfdfed051e3f94c0150b461599157d3d1f7d3ce","target":"record","created_at":"2026-05-18T03:09:33Z","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":"b27d02767b8257f5fe6e3837762718f35a2a0ca162c80f43dfa53ddcb2077b7b","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2025-10-23T03:00:04Z","title_canon_sha256":"811d80d5b8fb49a54c074874e3f926b4e8a09c9dcfbe6a20c640af3a83d0ed5d"},"schema_version":"1.0","source":{"id":"2510.20152","kind":"arxiv","version":4}},"canonical_sha256":"9ca6ef0623b8461e64004cbdc8321eb74584d0eeff8bebf2cc4792d145d304be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ca6ef0623b8461e64004cbdc8321eb74584d0eeff8bebf2cc4792d145d304be","first_computed_at":"2026-05-18T03:09:33.739378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:33.739378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KNYqZbuwGDwXW3RtTZxmORQfObcp2CZn5e1fXn1vnoSRFjUYh5o9/yuKD8tAwaXL6jJS8baZHe8CdjzG9fWXAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:33.739817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.20152","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87c31e6471f74d7dfe42f099dcfdfed051e3f94c0150b461599157d3d1f7d3ce","sha256:b9e39e1a326b67796be2946cb6b5b8efed22a828abd8d923a5f8b3594bde21d8"],"state_sha256":"6d5dded588764c0c94253967975626c3a73d0ac57d8b48bffeb17d2efdf06d2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Y67V9RFGV55/TzIHBLpGEs0FCsAzCwgSMUG1cOeCylPQg8LBed6OGK3ujUHgqYzQQkTUGrsBMebn1oXGJ9PCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T11:59:12.975032Z","bundle_sha256":"e6dfda7473264ce746583b419aea595c2e947980e671b047b3f168a13f91ec53"}}