{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GH5YRNZFW5NSXSXUBCAWLLACXZ","short_pith_number":"pith:GH5YRNZF","canonical_record":{"source":{"id":"2606.31320","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T08:26:50Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"707c028e3ebc6a268d1dbe31c8ccc2a17258350d3b461781e99fa7b082c95640","abstract_canon_sha256":"ac499164d658074b678d40d306d6b2a6ff95f845c55b1591f3e5dfdee85c7d00"},"schema_version":"1.0"},"canonical_sha256":"31fb88b725b75b2bcaf4088165ac02be44d3fd1432a5347f7c265008000737ef","source":{"kind":"arxiv","id":"2606.31320","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31320","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31320v1","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31320","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"GH5YRNZFW5NS","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"pith_short_16","alias_value":"GH5YRNZFW5NSXSXU","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"pith_short_8","alias_value":"GH5YRNZF","created_at":"2026-07-01T01:17:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GH5YRNZFW5NSXSXUBCAWLLACXZ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.31320","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T08:26:50Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"707c028e3ebc6a268d1dbe31c8ccc2a17258350d3b461781e99fa7b082c95640","abstract_canon_sha256":"ac499164d658074b678d40d306d6b2a6ff95f845c55b1591f3e5dfdee85c7d00"},"schema_version":"1.0"},"canonical_sha256":"31fb88b725b75b2bcaf4088165ac02be44d3fd1432a5347f7c265008000737ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:59.103785Z","signature_b64":"YB5L5F9IbqqhLQm7z3NbAE03zVAohyrztBCPgn/7/tMQ0vzd5BRtFM3yh/cMTKXIEPljoop2OXNSWQ4HzGWQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31fb88b725b75b2bcaf4088165ac02be44d3fd1432a5347f7c265008000737ef","last_reissued_at":"2026-07-01T01:17:59.103331Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:59.103331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.31320","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":"2026-07-01T01:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a4H8lf95rtPAK2BI+00jTqgH8+e3NoK2Nu1BMRLXAjCYarLZpXq9gHISIgNEb/GIRDQ2SDebflGly6UZf1yDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:11:02.809211Z"},"content_sha256":"303170d1c78a82541fe77ea225dc5ebb774783ef04994061e52364583091848c","schema_version":"1.0","event_id":"sha256:303170d1c78a82541fe77ea225dc5ebb774783ef04994061e52364583091848c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GH5YRNZFW5NSXSXUBCAWLLACXZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safe Online Learning via Smooth Safety-Structured Policy Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Hongpeng Cao, Liqun Zhao, Lui Sha, Marco Caccamo, Naira Hovakimyan, Yuliang Gu","submitted_at":"2026-06-30T08:26:50Z","abstract_excerpt":"Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics. Existing approaches typically rely on either strict safety enforcement via action interventions, which introduce discontinuities in system interaction and learning, or soft safety constraint formulations, which preserve smooth learning but provide limited safety assurance. We propose AutoSafe, a safety-aware policy architecture that integrates structured safety monitoring and intervention directly into the action generation process. This design enables smooth, risk"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31320","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/2606.31320/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":"2026-07-01T01:17:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IUpzxDuxrmgq+KpsfJq74kfJvpjhSnMslIapfmzknqwHsby5NEdjaYSY7gmzNZ4b74yRmLYN2jCJsFBgtxydBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:11:02.809754Z"},"content_sha256":"e9149ceeffe263075495d459a6795d763b00631083c1987916a98d87641c73fa","schema_version":"1.0","event_id":"sha256:e9149ceeffe263075495d459a6795d763b00631083c1987916a98d87641c73fa"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:GH5YRNZFW5NSXSXUBCAWLLACXZ","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/MS.2001.936213.Wesley) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"doi: 10.1109/MS.2001. 936213. Wesley Suttle, Vipul Kumar Sharma, Krishna Chaitanya Kosaraju, Sivaranjani Seetharaman, Ji Liu, Vijay Gupta, and Brian M. Sadler. Sampling-based safe reinforcement learning for nonlinear dynamical systems. InIn","arxiv_id":"2606.31320","detector":"doi_compliance","evidence":{"ref_index":14,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"doi: 10.1109/MS.2001. 936213. Wesley Suttle, Vipul Kumar Sharma, Krishna Chaitanya Kosaraju, Sivaranjani Seetharaman, Ji Liu, Vijay Gupta, and Brian M. Sadler. Sampling-based safe reinforcement learning for nonlinear dynamical systems. InIn","reconstructed_doi":"10.1109/MS.2001.936213.Wesley"},"severity":"advisory","ref_index":14,"audited_at":"2026-07-09T11:01:47.919960Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/MS.2001.936213.Wesley","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"2a83f7807f942cc5286e387acb33731cc2262a193938393fb7f630831ad149c9","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":8497,"payload_sha256":"52ced11e4704a3a927f797616534e0c20c07e6ef691d73df23081b40de0c891c","signature_b64":"m1HCBL0eRzfo23RhpbeYK/e94awdTcOHi8wjm4HcauUoFmB7vLhF8BNs68+RyE1qgPqhTtfAyTGXZRRtZQG7Ag==","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":"2026-07-09T11:02:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mHcZcP0gya8rOuMLhZOBZejvofmE7AifiJZ7UCE4VcOP4jBjCQBgYy1dCsnEfQ+sd7GjddDhtVIlCGRE/4RcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:11:02.814518Z"},"content_sha256":"ea26d7edfed4ebc4bbd615c2f760d54dc72faa0ad308b6cea14dc0a79717607d","schema_version":"1.0","event_id":"sha256:ea26d7edfed4ebc4bbd615c2f760d54dc72faa0ad308b6cea14dc0a79717607d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GH5YRNZFW5NSXSXUBCAWLLACXZ/bundle.json","state_url":"https://pith.science/pith/GH5YRNZFW5NSXSXUBCAWLLACXZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GH5YRNZFW5NSXSXUBCAWLLACXZ/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":"2026-08-09T23:11:02Z","links":{"resolver":"https://pith.science/pith/GH5YRNZFW5NSXSXUBCAWLLACXZ","bundle":"https://pith.science/pith/GH5YRNZFW5NSXSXUBCAWLLACXZ/bundle.json","state":"https://pith.science/pith/GH5YRNZFW5NSXSXUBCAWLLACXZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GH5YRNZFW5NSXSXUBCAWLLACXZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GH5YRNZFW5NSXSXUBCAWLLACXZ","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":"ac499164d658074b678d40d306d6b2a6ff95f845c55b1591f3e5dfdee85c7d00","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T08:26:50Z","title_canon_sha256":"707c028e3ebc6a268d1dbe31c8ccc2a17258350d3b461781e99fa7b082c95640"},"schema_version":"1.0","source":{"id":"2606.31320","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31320","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31320v1","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31320","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"GH5YRNZFW5NS","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"pith_short_16","alias_value":"GH5YRNZFW5NSXSXU","created_at":"2026-07-01T01:17:59Z"},{"alias_kind":"pith_short_8","alias_value":"GH5YRNZF","created_at":"2026-07-01T01:17:59Z"}],"graph_snapshots":[{"event_id":"sha256:e9149ceeffe263075495d459a6795d763b00631083c1987916a98d87641c73fa","target":"graph","created_at":"2026-07-01T01:17:59Z","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/2606.31320/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics. Existing approaches typically rely on either strict safety enforcement via action interventions, which introduce discontinuities in system interaction and learning, or soft safety constraint formulations, which preserve smooth learning but provide limited safety assurance. We propose AutoSafe, a safety-aware policy architecture that integrates structured safety monitoring and intervention directly into the action generation process. This design enables smooth, risk","authors_text":"Hongpeng Cao, Liqun Zhao, Lui Sha, Marco Caccamo, Naira Hovakimyan, Yuliang Gu","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T08:26:50Z","title":"Safe Online Learning via Smooth Safety-Structured Policy Composition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31320","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":"sha256:303170d1c78a82541fe77ea225dc5ebb774783ef04994061e52364583091848c","target":"record","created_at":"2026-07-01T01:17:59Z","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":"ac499164d658074b678d40d306d6b2a6ff95f845c55b1591f3e5dfdee85c7d00","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T08:26:50Z","title_canon_sha256":"707c028e3ebc6a268d1dbe31c8ccc2a17258350d3b461781e99fa7b082c95640"},"schema_version":"1.0","source":{"id":"2606.31320","kind":"arxiv","version":1}},"canonical_sha256":"31fb88b725b75b2bcaf4088165ac02be44d3fd1432a5347f7c265008000737ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31fb88b725b75b2bcaf4088165ac02be44d3fd1432a5347f7c265008000737ef","first_computed_at":"2026-07-01T01:17:59.103331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:59.103331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YB5L5F9IbqqhLQm7z3NbAE03zVAohyrztBCPgn/7/tMQ0vzd5BRtFM3yh/cMTKXIEPljoop2OXNSWQ4HzGWQCA==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:59.103785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31320","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:303170d1c78a82541fe77ea225dc5ebb774783ef04994061e52364583091848c","sha256:e9149ceeffe263075495d459a6795d763b00631083c1987916a98d87641c73fa","sha256:ea26d7edfed4ebc4bbd615c2f760d54dc72faa0ad308b6cea14dc0a79717607d"],"state_sha256":"772a257cbe9a7472abd0e7bcbc9031242dd8a3bc3a6acc80df49c96e02df07ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pcVDH1qZl91gf35UxUdNhh51kTLvLrD25UjaRk/VrUQLhfBY2R9UxBECJ5qFQ83q6W14T41Wl8SEEZvAUYh4DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:11:02.816815Z","bundle_sha256":"e05934a54883d084f8d944b9f3c9c06be1d21aba977a19ef550e2444531b1465"}}