{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OFRXNAW3BS6Y64QJLVP5SEG7MH","short_pith_number":"pith:OFRXNAW3","canonical_record":{"source":{"id":"2402.09992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T14:55:38Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"fb382541abcc6c1be807dc672f95ad3a0c48248aff69c7c752ec217d360e5a39","abstract_canon_sha256":"c9bbc6d957ab0a7d4284be6f7d1c585ce646147d4a72cd76242513456b88d9b1"},"schema_version":"1.0"},"canonical_sha256":"71637682db0cbd8f72095d5fd910df61f78c4b7e173628db77eaefa22c883dba","source":{"kind":"arxiv","id":"2402.09992","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09992","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09992v1","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09992","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"pith_short_12","alias_value":"OFRXNAW3BS6Y","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"pith_short_16","alias_value":"OFRXNAW3BS6Y64QJ","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"pith_short_8","alias_value":"OFRXNAW3","created_at":"2026-07-05T07:45:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OFRXNAW3BS6Y64QJLVP5SEG7MH","target":"record","payload":{"canonical_record":{"source":{"id":"2402.09992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T14:55:38Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"fb382541abcc6c1be807dc672f95ad3a0c48248aff69c7c752ec217d360e5a39","abstract_canon_sha256":"c9bbc6d957ab0a7d4284be6f7d1c585ce646147d4a72cd76242513456b88d9b1"},"schema_version":"1.0"},"canonical_sha256":"71637682db0cbd8f72095d5fd910df61f78c4b7e173628db77eaefa22c883dba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:39.980437Z","signature_b64":"dzsigh/Qf3ggvMKSJKTyuYnHuZBZateHowFxNrjtCf8RUevihim90WdxIG98/hEEisxtZKUariUKR99WJEP5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71637682db0cbd8f72095d5fd910df61f78c4b7e173628db77eaefa22c883dba","last_reissued_at":"2026-07-05T07:45:39.979986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:39.979986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.09992","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":"2026-07-05T07:45:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V0sODmCLUXm3FrHz51lb3F1VpL6ZZi861yTQH29HzU4DaOWAPI+SxSuBMau6NI0JFbIp2s17bBepPelzC54TDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:18:23.167338Z"},"content_sha256":"dcc8e61263dd8ce8c491e1529d56f810542b2dafe2aff7c8690f309c1b229ed2","schema_version":"1.0","event_id":"sha256:dcc8e61263dd8ce8c491e1529d56f810542b2dafe2aff7c8690f309c1b229ed2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OFRXNAW3BS6Y64QJLVP5SEG7MH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"James Harrison, Maximilian Schiffer, Tobias Enders","submitted_at":"2024-02-15T14:55:38Z","abstract_excerpt":"We study the robustness of deep reinforcement learning algorithms against distribution shifts within contextual multi-stage stochastic combinatorial optimization problems from the operations research domain. In this context, risk-sensitive algorithms promise to learn robust policies. While this field is of general interest to the reinforcement learning community, most studies up-to-date focus on theoretical results rather than real-world performance. With this work, we aim to bridge this gap by formally deriving a novel risk-sensitive deep reinforcement learning algorithm while providing numer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09992","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/2402.09992/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":"2026-07-05T07:45:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VNcbh2GWClUK6zHYqf32dNyZv2SdiFS5pNkhWAccfQmvdf+E0mp7EZgYtxZ8UUZmCGKtVgkpRn0mc/nKYhp0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:18:23.167923Z"},"content_sha256":"dd24c17683f28a8812caeeefbcb5b57b7bc8f896fd02f8a32491553b0ab900a1","schema_version":"1.0","event_id":"sha256:dd24c17683f28a8812caeeefbcb5b57b7bc8f896fd02f8a32491553b0ab900a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH/bundle.json","state_url":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH/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":"2026-08-10T12:18:23Z","links":{"resolver":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH","bundle":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH/bundle.json","state":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OFRXNAW3BS6Y64QJLVP5SEG7MH","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":"c9bbc6d957ab0a7d4284be6f7d1c585ce646147d4a72cd76242513456b88d9b1","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T14:55:38Z","title_canon_sha256":"fb382541abcc6c1be807dc672f95ad3a0c48248aff69c7c752ec217d360e5a39"},"schema_version":"1.0","source":{"id":"2402.09992","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09992","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09992v1","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09992","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"pith_short_12","alias_value":"OFRXNAW3BS6Y","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"pith_short_16","alias_value":"OFRXNAW3BS6Y64QJ","created_at":"2026-07-05T07:45:39Z"},{"alias_kind":"pith_short_8","alias_value":"OFRXNAW3","created_at":"2026-07-05T07:45:39Z"}],"graph_snapshots":[{"event_id":"sha256:dd24c17683f28a8812caeeefbcb5b57b7bc8f896fd02f8a32491553b0ab900a1","target":"graph","created_at":"2026-07-05T07:45:39Z","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/2402.09992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the robustness of deep reinforcement learning algorithms against distribution shifts within contextual multi-stage stochastic combinatorial optimization problems from the operations research domain. In this context, risk-sensitive algorithms promise to learn robust policies. While this field is of general interest to the reinforcement learning community, most studies up-to-date focus on theoretical results rather than real-world performance. With this work, we aim to bridge this gap by formally deriving a novel risk-sensitive deep reinforcement learning algorithm while providing numer","authors_text":"James Harrison, Maximilian Schiffer, Tobias Enders","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T14:55:38Z","title":"Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09992","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:dcc8e61263dd8ce8c491e1529d56f810542b2dafe2aff7c8690f309c1b229ed2","target":"record","created_at":"2026-07-05T07:45:39Z","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":"c9bbc6d957ab0a7d4284be6f7d1c585ce646147d4a72cd76242513456b88d9b1","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T14:55:38Z","title_canon_sha256":"fb382541abcc6c1be807dc672f95ad3a0c48248aff69c7c752ec217d360e5a39"},"schema_version":"1.0","source":{"id":"2402.09992","kind":"arxiv","version":1}},"canonical_sha256":"71637682db0cbd8f72095d5fd910df61f78c4b7e173628db77eaefa22c883dba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71637682db0cbd8f72095d5fd910df61f78c4b7e173628db77eaefa22c883dba","first_computed_at":"2026-07-05T07:45:39.979986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:45:39.979986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dzsigh/Qf3ggvMKSJKTyuYnHuZBZateHowFxNrjtCf8RUevihim90WdxIG98/hEEisxtZKUariUKR99WJEP5Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:45:39.980437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.09992","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcc8e61263dd8ce8c491e1529d56f810542b2dafe2aff7c8690f309c1b229ed2","sha256:dd24c17683f28a8812caeeefbcb5b57b7bc8f896fd02f8a32491553b0ab900a1"],"state_sha256":"c34697d949540e8948d29621b104d56094b21d0ccdf600ed4b70d6e561280cf1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cYzaXhFDnri5AKmFp8C/U5WqVbe8a9VbzKW0LgPLeaSdVGNMBUE7NfX2aWRL6jjNpDskT5Eisq2Njaz4QeZ0Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:18:23.171752Z","bundle_sha256":"ac011768ab95cdc395978ae746e917ead9ad7f1a72642973060cfa402721d853"}}