{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CPFI3IRSJI6U5TKUMQBLUCCYZX","short_pith_number":"pith:CPFI3IRS","canonical_record":{"source":{"id":"2006.07446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T19:58:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e67f9c5cf44fb79027d2f785e4b6bdcc17c422812a8e9b4c349856ce9b73122","abstract_canon_sha256":"b1a5063e3a028f21f55c4be35bea81cdabfae7f7cfccce20db6d9f6c3d9507d2"},"schema_version":"1.0"},"canonical_sha256":"13ca8da2324a3d4ecd546402ba0858cdd769b0d7ddae61eb367c82fb3a9992d8","source":{"kind":"arxiv","id":"2006.07446","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07446","created_at":"2026-07-05T01:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07446v1","created_at":"2026-07-05T01:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07446","created_at":"2026-07-05T01:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"CPFI3IRSJI6U","created_at":"2026-07-05T01:10:00Z"},{"alias_kind":"pith_short_16","alias_value":"CPFI3IRSJI6U5TKU","created_at":"2026-07-05T01:10:00Z"},{"alias_kind":"pith_short_8","alias_value":"CPFI3IRS","created_at":"2026-07-05T01:10:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CPFI3IRSJI6U5TKUMQBLUCCYZX","target":"record","payload":{"canonical_record":{"source":{"id":"2006.07446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T19:58:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1e67f9c5cf44fb79027d2f785e4b6bdcc17c422812a8e9b4c349856ce9b73122","abstract_canon_sha256":"b1a5063e3a028f21f55c4be35bea81cdabfae7f7cfccce20db6d9f6c3d9507d2"},"schema_version":"1.0"},"canonical_sha256":"13ca8da2324a3d4ecd546402ba0858cdd769b0d7ddae61eb367c82fb3a9992d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:00.052759Z","signature_b64":"N1/Nhce56+Bic5PKBcMXOzd1vi5MOS8m2LyHPFXKGggYRs7e4XuTxsrz1sctBefmt+RE/Q+QWJHtFjny7Y5xBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13ca8da2324a3d4ecd546402ba0858cdd769b0d7ddae61eb367c82fb3a9992d8","last_reissued_at":"2026-07-05T01:10:00.052343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:00.052343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.07446","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":"2026-07-05T01:10:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5FVNklkV/aGzYUy/gjcET4KG+m8lobkAkME5Is4sLTo0medftKKGMMcCJPtmVH4xTm4oYVo2HzNDbw7DbEzEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:00:27.511317Z"},"content_sha256":"462d1969b2e77bf78898b428d6a09e7b2f39dafc1bb1d44a334929094f193a92","schema_version":"1.0","event_id":"sha256:462d1969b2e77bf78898b428d6a09e7b2f39dafc1bb1d44a334929094f193a92"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CPFI3IRSJI6U5TKUMQBLUCCYZX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safety-guaranteed Reinforcement Learning based on Multi-class Support Vector Machine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akshita Gupta, Hong-Cheol Choi, Inseok Hwang, Kwangyeon Kim","submitted_at":"2020-06-12T19:58:49Z","abstract_excerpt":"Several works have addressed the problem of incorporating constraints in the reinforcement learning (RL) framework, however majority of them can only guarantee the satisfaction of soft constraints. In this work, we address the problem of satisfying hard state constraints in a model-free RL setting with the deterministic system dynamics. The proposed algorithm is developed for the discrete state and action space and utilizes a multi-class support vector machine (SVM) to represent the policy. The state constraints are incorporated in the SVM optimization framework to derive an analytical solutio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07446","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/2006.07446/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":"2026-07-05T01:10:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WaRiw22+jhaGItNbAzWmKqfjJOfXZIH4cz2UUKZhdOGWxQK+iNHLiGHqxP+kBMlw1jAPLtRoCfzzlCwNNWMwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:00:27.512123Z"},"content_sha256":"cf296f1cb8da91b50124e5db9544cbaa6c168fd237cbbf3204c3ee32a81cb2d9","schema_version":"1.0","event_id":"sha256:cf296f1cb8da91b50124e5db9544cbaa6c168fd237cbbf3204c3ee32a81cb2d9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CPFI3IRSJI6U5TKUMQBLUCCYZX/bundle.json","state_url":"https://pith.science/pith/CPFI3IRSJI6U5TKUMQBLUCCYZX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CPFI3IRSJI6U5TKUMQBLUCCYZX/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":"2026-08-11T19:00:27Z","links":{"resolver":"https://pith.science/pith/CPFI3IRSJI6U5TKUMQBLUCCYZX","bundle":"https://pith.science/pith/CPFI3IRSJI6U5TKUMQBLUCCYZX/bundle.json","state":"https://pith.science/pith/CPFI3IRSJI6U5TKUMQBLUCCYZX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CPFI3IRSJI6U5TKUMQBLUCCYZX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CPFI3IRSJI6U5TKUMQBLUCCYZX","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":"b1a5063e3a028f21f55c4be35bea81cdabfae7f7cfccce20db6d9f6c3d9507d2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T19:58:49Z","title_canon_sha256":"1e67f9c5cf44fb79027d2f785e4b6bdcc17c422812a8e9b4c349856ce9b73122"},"schema_version":"1.0","source":{"id":"2006.07446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07446","created_at":"2026-07-05T01:10:00Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07446v1","created_at":"2026-07-05T01:10:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07446","created_at":"2026-07-05T01:10:00Z"},{"alias_kind":"pith_short_12","alias_value":"CPFI3IRSJI6U","created_at":"2026-07-05T01:10:00Z"},{"alias_kind":"pith_short_16","alias_value":"CPFI3IRSJI6U5TKU","created_at":"2026-07-05T01:10:00Z"},{"alias_kind":"pith_short_8","alias_value":"CPFI3IRS","created_at":"2026-07-05T01:10:00Z"}],"graph_snapshots":[{"event_id":"sha256:cf296f1cb8da91b50124e5db9544cbaa6c168fd237cbbf3204c3ee32a81cb2d9","target":"graph","created_at":"2026-07-05T01:10:00Z","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/2006.07446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Several works have addressed the problem of incorporating constraints in the reinforcement learning (RL) framework, however majority of them can only guarantee the satisfaction of soft constraints. In this work, we address the problem of satisfying hard state constraints in a model-free RL setting with the deterministic system dynamics. The proposed algorithm is developed for the discrete state and action space and utilizes a multi-class support vector machine (SVM) to represent the policy. The state constraints are incorporated in the SVM optimization framework to derive an analytical solutio","authors_text":"Akshita Gupta, Hong-Cheol Choi, Inseok Hwang, Kwangyeon Kim","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T19:58:49Z","title":"Safety-guaranteed Reinforcement Learning based on Multi-class Support Vector Machine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07446","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":"sha256:462d1969b2e77bf78898b428d6a09e7b2f39dafc1bb1d44a334929094f193a92","target":"record","created_at":"2026-07-05T01:10:00Z","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":"b1a5063e3a028f21f55c4be35bea81cdabfae7f7cfccce20db6d9f6c3d9507d2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T19:58:49Z","title_canon_sha256":"1e67f9c5cf44fb79027d2f785e4b6bdcc17c422812a8e9b4c349856ce9b73122"},"schema_version":"1.0","source":{"id":"2006.07446","kind":"arxiv","version":1}},"canonical_sha256":"13ca8da2324a3d4ecd546402ba0858cdd769b0d7ddae61eb367c82fb3a9992d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13ca8da2324a3d4ecd546402ba0858cdd769b0d7ddae61eb367c82fb3a9992d8","first_computed_at":"2026-07-05T01:10:00.052343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:10:00.052343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N1/Nhce56+Bic5PKBcMXOzd1vi5MOS8m2LyHPFXKGggYRs7e4XuTxsrz1sctBefmt+RE/Q+QWJHtFjny7Y5xBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:10:00.052759Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.07446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:462d1969b2e77bf78898b428d6a09e7b2f39dafc1bb1d44a334929094f193a92","sha256:cf296f1cb8da91b50124e5db9544cbaa6c168fd237cbbf3204c3ee32a81cb2d9"],"state_sha256":"72131bdf5eda8050294cf1a26f7402fff8acb53eee3bf89f09f74b4af9eaee98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mu991+a9+29hyhOI1vLF+NlGusAJAmzMJ1a51aTD0mvDZuglDVE1EcEVUPKpnBJ4GaNi158UK5AIvmghtOITAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:00:27.519983Z","bundle_sha256":"6ba3e5169ff81e564d13bb90bac8a5ad30742f6fcd0da5502520110ab5997bdf"}}