{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GSOOJ6KYF2EWX53HYIAK3QMY6V","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":"6f8fee3a773ebbcbc3e9442b1b803cce5b76551abd65533d0a4c7ea08b5a2dfe","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-02T15:34:36Z","title_canon_sha256":"656ff9fd2d74977ebb07fb49f10a8e47ce916d7140f1ed65ccbfaa6adaa2b08a"},"schema_version":"1.0","source":{"id":"2505.01348","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01348","created_at":"2026-07-05T10:59:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01348v1","created_at":"2026-07-05T10:59:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01348","created_at":"2026-07-05T10:59:09Z"},{"alias_kind":"pith_short_12","alias_value":"GSOOJ6KYF2EW","created_at":"2026-07-05T10:59:09Z"},{"alias_kind":"pith_short_16","alias_value":"GSOOJ6KYF2EWX53H","created_at":"2026-07-05T10:59:09Z"},{"alias_kind":"pith_short_8","alias_value":"GSOOJ6KY","created_at":"2026-07-05T10:59:09Z"}],"graph_snapshots":[{"event_id":"sha256:e1fa2f9e7b0c1fd8ae6335443e7eedf16b579e5cc39ae2d47ec6c1ac3ac228c4","target":"graph","created_at":"2026-07-05T10:59:09Z","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/2505.01348/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of learning to stabilize (LTS) a linear time-invariant (LTI) system. Policy gradient (PG) methods for control assume access to an initial stabilizing policy. However, designing such a policy for an unknown system is one of the most fundamental problems in control, and it may be as hard as learning the optimal policy itself. Existing work on the LTS problem requires large data as it scales quadratically with the ambient dimension. We propose a two-phase approach that first learns the left unstable subspace of the system and then solves a series of discounted linear quadrati","authors_text":"James Anderson, Leonardo F. Toso, Lintao Ye","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-02T15:34:36Z","title":"Learning Stabilizing Policies via an Unstable Subspace Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01348","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:c2429d50c8e9f19b8ae5bf249b3b43061707d60eb52130d6806bc082e36da3dc","target":"record","created_at":"2026-07-05T10:59:09Z","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":"6f8fee3a773ebbcbc3e9442b1b803cce5b76551abd65533d0a4c7ea08b5a2dfe","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-02T15:34:36Z","title_canon_sha256":"656ff9fd2d74977ebb07fb49f10a8e47ce916d7140f1ed65ccbfaa6adaa2b08a"},"schema_version":"1.0","source":{"id":"2505.01348","kind":"arxiv","version":1}},"canonical_sha256":"349ce4f9582e896bf767c200adc198f55c140cae6deca65fbf1a86a705979561","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"349ce4f9582e896bf767c200adc198f55c140cae6deca65fbf1a86a705979561","first_computed_at":"2026-07-05T10:59:09.972917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:09.972917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vvdenHGjqwnYaJgHCFcrzL63Ok7UAIspP2Vn4LPiWWnkNCmRvOF6qGKunbXiSnU7y8lnszI5iEmINHk/PPtVCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:09.973341Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.01348","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2429d50c8e9f19b8ae5bf249b3b43061707d60eb52130d6806bc082e36da3dc","sha256:e1fa2f9e7b0c1fd8ae6335443e7eedf16b579e5cc39ae2d47ec6c1ac3ac228c4"],"state_sha256":"8bb5be0440887f1c69199c64a53966f263730a7c1667cab3d3d34d33443e646c"}