{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LD3QPJPG2LUVVOY3F2ATUIJZV7","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":"4b1b7a3d7a561e6c678612d8d39bc5f7e7b8b74b49a37d3478092797afd71176","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-15T19:00:01Z","title_canon_sha256":"b5f629818a4c5762c1d31f22d090a799300c907ed1af839410db4cc01680260f"},"schema_version":"1.0","source":{"id":"2512.13788","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.13788","created_at":"2026-05-20T00:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2512.13788v2","created_at":"2026-05-20T00:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.13788","created_at":"2026-05-20T00:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"LD3QPJPG2LUV","created_at":"2026-05-20T00:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"LD3QPJPG2LUVVOY3","created_at":"2026-05-20T00:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"LD3QPJPG","created_at":"2026-05-20T00:04:18Z"}],"graph_snapshots":[{"event_id":"sha256:79dcda316e77584905b1ca2ec435fba3b0c612cead738540113ecbd153c87db0","target":"graph","created_at":"2026-05-20T00:04:18Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2512.13788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety-critical learning requires policies that improve performance without leaving the safe operating regime. We study constrained policy learning where model parameters must satisfy rollout-based safety constraints that can be evaluated but not differentiated analytically. We propose SCPO, a sampling-based weight-space projection method that enforces safety directly in parameter space without requiring gradient access to the constraint functions. SCPO constructs a local safe region by combining rollout-based safety evaluations with smoothness bounds relating parameter perturbations to change","authors_text":"Eunhyek Joa, Francesco Borrelli, Shengfan Cao","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-15T19:00:01Z","title":"Constrained Policy Optimization via Sampling-Based Weight-Space Projection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.13788","kind":"arxiv","version":2},"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":"sha256:7bbceca891361820dc1981e5af54c986f9dab789cd9aef3765cf993cf2158da1","target":"record","created_at":"2026-05-20T00:04:18Z","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":"4b1b7a3d7a561e6c678612d8d39bc5f7e7b8b74b49a37d3478092797afd71176","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-15T19:00:01Z","title_canon_sha256":"b5f629818a4c5762c1d31f22d090a799300c907ed1af839410db4cc01680260f"},"schema_version":"1.0","source":{"id":"2512.13788","kind":"arxiv","version":2}},"canonical_sha256":"58f707a5e6d2e95abb1b2e813a2139afc9308d495ab62f93efe314f1fd6701f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58f707a5e6d2e95abb1b2e813a2139afc9308d495ab62f93efe314f1fd6701f9","first_computed_at":"2026-05-20T00:04:18.759972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:18.759972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sGJfmUnnO2tGs029Nkvyz1gHHX9rGaq60Iw6lgU5Q02wmAgKn2pAqXuNjIhjw1V7DVHJaX8+CrFepJj6k+z5BA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:18.760718Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.13788","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bbceca891361820dc1981e5af54c986f9dab789cd9aef3765cf993cf2158da1","sha256:79dcda316e77584905b1ca2ec435fba3b0c612cead738540113ecbd153c87db0"],"state_sha256":"84144aeefd629a275ecb87718a7da9c28e9dc314a83b85f4c9ff0c8b6b4c05bf"}