{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UVAXZSYRSH5ZI5WKDAFV2V5OQT","short_pith_number":"pith:UVAXZSYR","canonical_record":{"source":{"id":"2303.04118","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-07T18:29:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48c2c9db95f854a2a0e55757ff22d2f32aeb59e46ffb2232f3b7de9c82624dc9","abstract_canon_sha256":"e848826624977118addafb6ef7a354e7ba6f9d41a262d67a361f3b219e80ad63"},"schema_version":"1.0"},"canonical_sha256":"a5417ccb1191fb9476ca180b5d57ae84fa86ea3792adc77fc15e2cb3dc7b1fc2","source":{"kind":"arxiv","id":"2303.04118","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.04118","created_at":"2026-07-05T05:49:03Z"},{"alias_kind":"arxiv_version","alias_value":"2303.04118v1","created_at":"2026-07-05T05:49:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04118","created_at":"2026-07-05T05:49:03Z"},{"alias_kind":"pith_short_12","alias_value":"UVAXZSYRSH5Z","created_at":"2026-07-05T05:49:03Z"},{"alias_kind":"pith_short_16","alias_value":"UVAXZSYRSH5ZI5WK","created_at":"2026-07-05T05:49:03Z"},{"alias_kind":"pith_short_8","alias_value":"UVAXZSYR","created_at":"2026-07-05T05:49:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UVAXZSYRSH5ZI5WKDAFV2V5OQT","target":"record","payload":{"canonical_record":{"source":{"id":"2303.04118","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-07T18:29:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"48c2c9db95f854a2a0e55757ff22d2f32aeb59e46ffb2232f3b7de9c82624dc9","abstract_canon_sha256":"e848826624977118addafb6ef7a354e7ba6f9d41a262d67a361f3b219e80ad63"},"schema_version":"1.0"},"canonical_sha256":"a5417ccb1191fb9476ca180b5d57ae84fa86ea3792adc77fc15e2cb3dc7b1fc2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:03.335682Z","signature_b64":"2+4hjutp6TrjQs7rc6yHNcwRa85uGf5Qp4tXhxrHgRBshBWTW8VhIvDCn3n81FduFNkJznL/JyGJFk0pfn4PCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5417ccb1191fb9476ca180b5d57ae84fa86ea3792adc77fc15e2cb3dc7b1fc2","last_reissued_at":"2026-07-05T05:49:03.335269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:03.335269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.04118","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":"2026-07-05T05:49:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jYmNpWpA9+KJkNSl08IdspYtA+96NgbdUxSy0qd/NQGU//l3q4Vc3rdO/DPfndIwq8Y33gcbspLeXXoVDhBDBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:28:20.222156Z"},"content_sha256":"bc594abe7721b060165160ec198151d35c29fb8228444860db3498a868d378f3","schema_version":"1.0","event_id":"sha256:bc594abe7721b060165160ec198151d35c29fb8228444860db3498a868d378f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UVAXZSYRSH5ZI5WKDAFV2V5OQT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Multiplicative Value Function for Safe and Efficient Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Alexander Liniger, Fisher Yu, Luc Van Gool, Nick B\\\"uhrer, Zhejun Zhang","submitted_at":"2023-03-07T18:29:15Z","abstract_excerpt":"An emerging field of sequential decision problems is safe Reinforcement Learning (RL), where the objective is to maximize the reward while obeying safety constraints. Being able to handle constraints is essential for deploying RL agents in real-world environments, where constraint violations can harm the agent and the environment. To this end, we propose a safe model-free RL algorithm with a novel multiplicative value function consisting of a safety critic and a reward critic. The safety critic predicts the probability of constraint violation and discounts the reward critic that only estimates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04118","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/2303.04118/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":"2026-07-05T05:49:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQS6Bevkv7pyyGpgobHc6i3mHVSijSXH8VMy9EppiSjcPaPg56iZ/70mhE9gHbwXHOP409Y1e3+qnTAvsDnmDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T17:28:20.222659Z"},"content_sha256":"624893cf31811983107ebc4299bef82ea81ff430dab1c174e933ed0a116e0e75","schema_version":"1.0","event_id":"sha256:624893cf31811983107ebc4299bef82ea81ff430dab1c174e933ed0a116e0e75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UVAXZSYRSH5ZI5WKDAFV2V5OQT/bundle.json","state_url":"https://pith.science/pith/UVAXZSYRSH5ZI5WKDAFV2V5OQT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UVAXZSYRSH5ZI5WKDAFV2V5OQT/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":"2026-08-17T17:28:20Z","links":{"resolver":"https://pith.science/pith/UVAXZSYRSH5ZI5WKDAFV2V5OQT","bundle":"https://pith.science/pith/UVAXZSYRSH5ZI5WKDAFV2V5OQT/bundle.json","state":"https://pith.science/pith/UVAXZSYRSH5ZI5WKDAFV2V5OQT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UVAXZSYRSH5ZI5WKDAFV2V5OQT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UVAXZSYRSH5ZI5WKDAFV2V5OQT","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":"e848826624977118addafb6ef7a354e7ba6f9d41a262d67a361f3b219e80ad63","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-07T18:29:15Z","title_canon_sha256":"48c2c9db95f854a2a0e55757ff22d2f32aeb59e46ffb2232f3b7de9c82624dc9"},"schema_version":"1.0","source":{"id":"2303.04118","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.04118","created_at":"2026-07-05T05:49:03Z"},{"alias_kind":"arxiv_version","alias_value":"2303.04118v1","created_at":"2026-07-05T05:49:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04118","created_at":"2026-07-05T05:49:03Z"},{"alias_kind":"pith_short_12","alias_value":"UVAXZSYRSH5Z","created_at":"2026-07-05T05:49:03Z"},{"alias_kind":"pith_short_16","alias_value":"UVAXZSYRSH5ZI5WK","created_at":"2026-07-05T05:49:03Z"},{"alias_kind":"pith_short_8","alias_value":"UVAXZSYR","created_at":"2026-07-05T05:49:03Z"}],"graph_snapshots":[{"event_id":"sha256:624893cf31811983107ebc4299bef82ea81ff430dab1c174e933ed0a116e0e75","target":"graph","created_at":"2026-07-05T05:49:03Z","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/2303.04118/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An emerging field of sequential decision problems is safe Reinforcement Learning (RL), where the objective is to maximize the reward while obeying safety constraints. Being able to handle constraints is essential for deploying RL agents in real-world environments, where constraint violations can harm the agent and the environment. To this end, we propose a safe model-free RL algorithm with a novel multiplicative value function consisting of a safety critic and a reward critic. The safety critic predicts the probability of constraint violation and discounts the reward critic that only estimates","authors_text":"Alexander Liniger, Fisher Yu, Luc Van Gool, Nick B\\\"uhrer, Zhejun Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-07T18:29:15Z","title":"A Multiplicative Value Function for Safe and Efficient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04118","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:bc594abe7721b060165160ec198151d35c29fb8228444860db3498a868d378f3","target":"record","created_at":"2026-07-05T05:49:03Z","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":"e848826624977118addafb6ef7a354e7ba6f9d41a262d67a361f3b219e80ad63","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-03-07T18:29:15Z","title_canon_sha256":"48c2c9db95f854a2a0e55757ff22d2f32aeb59e46ffb2232f3b7de9c82624dc9"},"schema_version":"1.0","source":{"id":"2303.04118","kind":"arxiv","version":1}},"canonical_sha256":"a5417ccb1191fb9476ca180b5d57ae84fa86ea3792adc77fc15e2cb3dc7b1fc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5417ccb1191fb9476ca180b5d57ae84fa86ea3792adc77fc15e2cb3dc7b1fc2","first_computed_at":"2026-07-05T05:49:03.335269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:03.335269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2+4hjutp6TrjQs7rc6yHNcwRa85uGf5Qp4tXhxrHgRBshBWTW8VhIvDCn3n81FduFNkJznL/JyGJFk0pfn4PCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:03.335682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.04118","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc594abe7721b060165160ec198151d35c29fb8228444860db3498a868d378f3","sha256:624893cf31811983107ebc4299bef82ea81ff430dab1c174e933ed0a116e0e75"],"state_sha256":"4ad1d333824a87274b7d7d82590b2c9851dd38aebdf2cdee11f829a2c9776c26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/CS/2CLz1HA0suWeAiPqmX0mF+feyZSlltzakBVf8ogmSEG9uYCVKaXus9n1N6/u5HFIQ4I/wkYSIJgwiDcGAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T17:28:20.227112Z","bundle_sha256":"0dfd1b9c3efff415e11a4bee09e64ccf8ea2e45f4c47f8303f189a32c555d8b8"}}