{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:65BZRRYSK5TJFE7AEW34JNNBWQ","short_pith_number":"pith:65BZRRYS","canonical_record":{"source":{"id":"2605.19469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T07:21:53Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"4e1cf5561bac1ee21ef8a41a81f794b205950a29134ed0319d896c9fe03e5932","abstract_canon_sha256":"719eb63a44b45126f1e4209af3009825f57aa3b0f403610cd515f3d149f6f971"},"schema_version":"1.0"},"canonical_sha256":"f74398c71257669293e025b7c4b5a1b419c3619690e0f352d0e791dfdd25becd","source":{"kind":"arxiv","id":"2605.19469","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19469","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19469v1","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19469","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"65BZRRYSK5TJ","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"65BZRRYSK5TJFE7A","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"65BZRRYS","created_at":"2026-05-20T01:05:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:65BZRRYSK5TJFE7AEW34JNNBWQ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.19469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T07:21:53Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"4e1cf5561bac1ee21ef8a41a81f794b205950a29134ed0319d896c9fe03e5932","abstract_canon_sha256":"719eb63a44b45126f1e4209af3009825f57aa3b0f403610cd515f3d149f6f971"},"schema_version":"1.0"},"canonical_sha256":"f74398c71257669293e025b7c4b5a1b419c3619690e0f352d0e791dfdd25becd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:47.379837Z","signature_b64":"c+YCy58j+DKt0MYYlRL7/CJx7fa6zkRFMDeJk2dSr2ZUMj5SEeYC5OstQf1wXwJTyWoXNo2gIM9RQrWlB8NvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f74398c71257669293e025b7c4b5a1b419c3619690e0f352d0e791dfdd25becd","last_reissued_at":"2026-05-20T01:05:47.378987Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:47.378987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.19469","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":"2026-05-20T01:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kvn8kFM06qiPey0pMrnks6bSFmW+FKdaZkGc/HssUHQsK+QZWOXroa0xkPTcNJJEd4C6j06rQPiYshxk7cqrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T10:02:19.369480Z"},"content_sha256":"b6a7c308e4a769f4e30c577dc5782ab3410a1c92299c4efdc55a2fc00610af59","schema_version":"1.0","event_id":"sha256:b6a7c308e4a769f4e30c577dc5782ab3410a1c92299c4efdc55a2fc00610af59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:65BZRRYSK5TJFE7AEW34JNNBWQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sampling-Based Safe Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Bruce D. Lee, Luca Vignola, Manish Prajapat, Manuel Wendl, Melanie Zeilinger, Yarden As","submitted_at":"2026-05-19T07:21:53Z","abstract_excerpt":"Safe exploration remains a fundamental challenge in reinforcement learning (RL), limiting the deployment of RL agents in the real world. We propose Sampling-Based Safe Reinforcement Learning (SBSRL), a model-based RL algorithm that maintains safety throughout the learning process by enforcing constraints jointly across a finite set of dynamics samples. This formulation approximates an intractable worst-case optimization over uncertain dynamics and enables practical safety guarantees in continuous domains. We further introduce an exploration strategy based on constraining epistemic uncertainty,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19469","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/2605.19469/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":"2026-05-20T01:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UFO3b0ZCzRXX6KdebDpVOUl0ZzqimVq1f9Vad6kJajk5N5lMPX9UBK322/SzyrC9352b1WAhwnYGu9s/eowzBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T10:02:19.370187Z"},"content_sha256":"02f36ef893e3700e29fb9bdd967b8a8c64c37ee6ef6c78592662274290f9a7a0","schema_version":"1.0","event_id":"sha256:02f36ef893e3700e29fb9bdd967b8a8c64c37ee6ef6c78592662274290f9a7a0"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:65BZRRYSK5TJFE7AEW34JNNBWQ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1017/cbo9780511546921.(citedon) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Nicolò Cesa-Bianchi and Gábor Lugosi.Prediction, Learning, and Games. 2006. doi: 10.1017/CBO9780511546921.(Cited on page 20)","arxiv_id":"2605.19469","detector":"doi_compliance","evidence":{"ref_index":63,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"Nicolò Cesa-Bianchi and Gábor Lugosi.Prediction, Learning, and Games. 2006. doi: 10.1017/CBO9780511546921.(Cited on page 20)","reconstructed_doi":"10.1017/cbo9780511546921.(citedon"},"severity":"advisory","ref_index":63,"audited_at":"2026-05-20T07:10:16.039139Z","event_type":"pith.integrity.v1","detected_doi":"10.1017/cbo9780511546921.(citedon","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"bed4dd9bd5468655c216fae1f058fe9daf53c9a28a7760df27cee2ee6bc305d9","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":4897,"payload_sha256":"862f87811017937d63a7985363b741ccba3e46d4025d1bcee3c8af11f616f3ea","signature_b64":"5mPkxgRCYcCR/vQYBUOmQCjBaAdxAau5GN9nykwlf488NsdUI5YloUYK9CeHnEhiM7Cn2eqnG6JBLMLMEoUtBg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T07:12:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cR8imJFRNp2xwSCIkdVao+KLAEsZ1Z5x90k66XZCK0la4VtmOmIx93r6uuRGzVu3CSxxhGtVW3UgxOUD/+t5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T10:02:19.371512Z"},"content_sha256":"42f31e83114266e0835f0a68b013aa4c8852fb57abb460ef55cebd9a7d8a144a","schema_version":"1.0","event_id":"sha256:42f31e83114266e0835f0a68b013aa4c8852fb57abb460ef55cebd9a7d8a144a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/65BZRRYSK5TJFE7AEW34JNNBWQ/bundle.json","state_url":"https://pith.science/pith/65BZRRYSK5TJFE7AEW34JNNBWQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/65BZRRYSK5TJFE7AEW34JNNBWQ/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":"2026-05-28T10:02:19Z","links":{"resolver":"https://pith.science/pith/65BZRRYSK5TJFE7AEW34JNNBWQ","bundle":"https://pith.science/pith/65BZRRYSK5TJFE7AEW34JNNBWQ/bundle.json","state":"https://pith.science/pith/65BZRRYSK5TJFE7AEW34JNNBWQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/65BZRRYSK5TJFE7AEW34JNNBWQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:65BZRRYSK5TJFE7AEW34JNNBWQ","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"719eb63a44b45126f1e4209af3009825f57aa3b0f403610cd515f3d149f6f971","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T07:21:53Z","title_canon_sha256":"4e1cf5561bac1ee21ef8a41a81f794b205950a29134ed0319d896c9fe03e5932"},"schema_version":"1.0","source":{"id":"2605.19469","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19469","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19469v1","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19469","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"65BZRRYSK5TJ","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"65BZRRYSK5TJFE7A","created_at":"2026-05-20T01:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"65BZRRYS","created_at":"2026-05-20T01:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:02f36ef893e3700e29fb9bdd967b8a8c64c37ee6ef6c78592662274290f9a7a0","target":"graph","created_at":"2026-05-20T01:05:47Z","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/2605.19469/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe exploration remains a fundamental challenge in reinforcement learning (RL), limiting the deployment of RL agents in the real world. We propose Sampling-Based Safe Reinforcement Learning (SBSRL), a model-based RL algorithm that maintains safety throughout the learning process by enforcing constraints jointly across a finite set of dynamics samples. This formulation approximates an intractable worst-case optimization over uncertain dynamics and enables practical safety guarantees in continuous domains. We further introduce an exploration strategy based on constraining epistemic uncertainty,","authors_text":"Andreas Krause, Bruce D. Lee, Luca Vignola, Manish Prajapat, Manuel Wendl, Melanie Zeilinger, Yarden As","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T07:21:53Z","title":"Sampling-Based Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19469","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:b6a7c308e4a769f4e30c577dc5782ab3410a1c92299c4efdc55a2fc00610af59","target":"record","created_at":"2026-05-20T01:05:47Z","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":"719eb63a44b45126f1e4209af3009825f57aa3b0f403610cd515f3d149f6f971","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T07:21:53Z","title_canon_sha256":"4e1cf5561bac1ee21ef8a41a81f794b205950a29134ed0319d896c9fe03e5932"},"schema_version":"1.0","source":{"id":"2605.19469","kind":"arxiv","version":1}},"canonical_sha256":"f74398c71257669293e025b7c4b5a1b419c3619690e0f352d0e791dfdd25becd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f74398c71257669293e025b7c4b5a1b419c3619690e0f352d0e791dfdd25becd","first_computed_at":"2026-05-20T01:05:47.378987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:47.378987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c+YCy58j+DKt0MYYlRL7/CJx7fa6zkRFMDeJk2dSr2ZUMj5SEeYC5OstQf1wXwJTyWoXNo2gIM9RQrWlB8NvDQ==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:47.379837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19469","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6a7c308e4a769f4e30c577dc5782ab3410a1c92299c4efdc55a2fc00610af59","sha256:02f36ef893e3700e29fb9bdd967b8a8c64c37ee6ef6c78592662274290f9a7a0","sha256:42f31e83114266e0835f0a68b013aa4c8852fb57abb460ef55cebd9a7d8a144a"],"state_sha256":"84e2389268491fefc467e799ba97caea87c3873a785a91b67f901850ee5fe168"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ywA3EEeAnG+AnAkwxCn4j5+gr/7hFVZDiJsH+yr6yXDrxEdvz+p+terHipF72cbqOZZXIG3d/M762MEkiaTeBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T10:02:19.374805Z","bundle_sha256":"63b60873c38d58fc7e62a309efd34919cda1a7fade485aeb4e53d599fc05fea3"}}