{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TU3KYV7OXQVYAX43DRZBT6N5XT","short_pith_number":"pith:TU3KYV7O","canonical_record":{"source":{"id":"2403.14508","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T16:02:52Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"127279dc8432f3a4abf7689400018462f0d693c8d385d4aea76b32b7b32fd813","abstract_canon_sha256":"6ec93019d59dae1195de849afc3f4052f872022ec4742710364b0d7755b6ba68"},"schema_version":"1.0"},"canonical_sha256":"9d36ac57eebc2b805f9b1c7219f9bdbccdd34cfb4da4fe93f94500235883736c","source":{"kind":"arxiv","id":"2403.14508","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14508","created_at":"2026-07-05T07:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14508v1","created_at":"2026-07-05T07:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14508","created_at":"2026-07-05T07:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"TU3KYV7OXQVY","created_at":"2026-07-05T07:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"TU3KYV7OXQVYAX43","created_at":"2026-07-05T07:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"TU3KYV7O","created_at":"2026-07-05T07:59:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TU3KYV7OXQVYAX43DRZBT6N5XT","target":"record","payload":{"canonical_record":{"source":{"id":"2403.14508","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T16:02:52Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"127279dc8432f3a4abf7689400018462f0d693c8d385d4aea76b32b7b32fd813","abstract_canon_sha256":"6ec93019d59dae1195de849afc3f4052f872022ec4742710364b0d7755b6ba68"},"schema_version":"1.0"},"canonical_sha256":"9d36ac57eebc2b805f9b1c7219f9bdbccdd34cfb4da4fe93f94500235883736c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:10.133057Z","signature_b64":"Jmv+LRGI+FsCj7pJIduWu9lFp0VqC3qCcZ0DmhBiGBwvo0lgqOVkRKAteSwielFYE5lLGdHMjYN7pykxd0MgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d36ac57eebc2b805f9b1c7219f9bdbccdd34cfb4da4fe93f94500235883736c","last_reissued_at":"2026-07-05T07:59:10.132561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:10.132561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.14508","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":"2026-07-05T07:59:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y/gzv03w0LAfzlnBB3QZmSn02MLUX3JaixqQMwv1AbvjYAzH+FewLD/cBYyx9HkqvmkrEwMGv4Zg8+njoi7aBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:12:56.274948Z"},"content_sha256":"5adab5f36d421fd0981539805c0a578bab1c812a7fd3e8da068add31d16342da","schema_version":"1.0","event_id":"sha256:5adab5f36d421fd0981539805c0a578bab1c812a7fd3e8da068add31d16342da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TU3KYV7OXQVYAX43DRZBT6N5XT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained Reinforcement Learning with Smoothed Log Barrier Function","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Baohe Zhang, Joschka B\\\"odecker, Lilli Frison, Thomas Brox, Yuan Zhang","submitted_at":"2024-03-21T16:02:52Z","abstract_excerpt":"Reinforcement Learning (RL) has been widely applied to many control tasks and substantially improved the performances compared to conventional control methods in many domains where the reward function is well defined. However, for many real-world problems, it is often more convenient to formulate optimization problems in terms of rewards and constraints simultaneously. Optimizing such constrained problems via reward shaping can be difficult as it requires tedious manual tuning of reward functions with several interacting terms. Recent formulations which include constraints mostly require a pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14508","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/2403.14508/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":"2026-07-05T07:59:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ImHZMVpq2VGlcv/xFuhnj1tJzoivCCIuoYtFIg1PnooXUK4PRcwGUsJIjXmKWK8YMCQZaCZ6LBNxohpcyWlAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:12:56.275930Z"},"content_sha256":"512010454c140d756d8ad97355334a7d596fa6687424d0f79672a66efdeb6315","schema_version":"1.0","event_id":"sha256:512010454c140d756d8ad97355334a7d596fa6687424d0f79672a66efdeb6315"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TU3KYV7OXQVYAX43DRZBT6N5XT/bundle.json","state_url":"https://pith.science/pith/TU3KYV7OXQVYAX43DRZBT6N5XT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TU3KYV7OXQVYAX43DRZBT6N5XT/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":"2026-08-08T13:12:56Z","links":{"resolver":"https://pith.science/pith/TU3KYV7OXQVYAX43DRZBT6N5XT","bundle":"https://pith.science/pith/TU3KYV7OXQVYAX43DRZBT6N5XT/bundle.json","state":"https://pith.science/pith/TU3KYV7OXQVYAX43DRZBT6N5XT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TU3KYV7OXQVYAX43DRZBT6N5XT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TU3KYV7OXQVYAX43DRZBT6N5XT","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":"6ec93019d59dae1195de849afc3f4052f872022ec4742710364b0d7755b6ba68","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T16:02:52Z","title_canon_sha256":"127279dc8432f3a4abf7689400018462f0d693c8d385d4aea76b32b7b32fd813"},"schema_version":"1.0","source":{"id":"2403.14508","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14508","created_at":"2026-07-05T07:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14508v1","created_at":"2026-07-05T07:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14508","created_at":"2026-07-05T07:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"TU3KYV7OXQVY","created_at":"2026-07-05T07:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"TU3KYV7OXQVYAX43","created_at":"2026-07-05T07:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"TU3KYV7O","created_at":"2026-07-05T07:59:10Z"}],"graph_snapshots":[{"event_id":"sha256:512010454c140d756d8ad97355334a7d596fa6687424d0f79672a66efdeb6315","target":"graph","created_at":"2026-07-05T07:59:10Z","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/2403.14508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has been widely applied to many control tasks and substantially improved the performances compared to conventional control methods in many domains where the reward function is well defined. However, for many real-world problems, it is often more convenient to formulate optimization problems in terms of rewards and constraints simultaneously. Optimizing such constrained problems via reward shaping can be difficult as it requires tedious manual tuning of reward functions with several interacting terms. Recent formulations which include constraints mostly require a pre","authors_text":"Baohe Zhang, Joschka B\\\"odecker, Lilli Frison, Thomas Brox, Yuan Zhang","cross_cats":["cs.AI","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T16:02:52Z","title":"Constrained Reinforcement Learning with Smoothed Log Barrier Function"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14508","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":"sha256:5adab5f36d421fd0981539805c0a578bab1c812a7fd3e8da068add31d16342da","target":"record","created_at":"2026-07-05T07:59:10Z","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":"6ec93019d59dae1195de849afc3f4052f872022ec4742710364b0d7755b6ba68","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T16:02:52Z","title_canon_sha256":"127279dc8432f3a4abf7689400018462f0d693c8d385d4aea76b32b7b32fd813"},"schema_version":"1.0","source":{"id":"2403.14508","kind":"arxiv","version":1}},"canonical_sha256":"9d36ac57eebc2b805f9b1c7219f9bdbccdd34cfb4da4fe93f94500235883736c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d36ac57eebc2b805f9b1c7219f9bdbccdd34cfb4da4fe93f94500235883736c","first_computed_at":"2026-07-05T07:59:10.132561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:10.132561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jmv+LRGI+FsCj7pJIduWu9lFp0VqC3qCcZ0DmhBiGBwvo0lgqOVkRKAteSwielFYE5lLGdHMjYN7pykxd0MgBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:10.133057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.14508","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5adab5f36d421fd0981539805c0a578bab1c812a7fd3e8da068add31d16342da","sha256:512010454c140d756d8ad97355334a7d596fa6687424d0f79672a66efdeb6315"],"state_sha256":"1a0271542d3bf0ef568ddf893a224911c111be527c32a188a6affea1ac4a151f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z55JGytV+HLmDsPaQB0nNccHPJMaWNVJMdi9avoS2V7yhZnPLf9h5TUN8jk/ArTT7D05ZU+nzyUiP+nhqoRkBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:12:56.282367Z","bundle_sha256":"987fa104d76d4ecd4057b54522b07a2829189f7dde70e0dbf5d07b31de5562b7"}}