{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P4CLVLB2Z63VXSOMXYLH6IVS43","short_pith_number":"pith:P4CLVLB2","schema_version":"1.0","canonical_sha256":"7f04baac3acfb75bc9ccbe167f22b2e6e6b16b106011d1426887c0ebe4081bd7","source":{"kind":"arxiv","id":"2402.18246","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning and Graph Neural Networks for Probabilistic Risk Assessment","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Andrey Morozov, Joachim Grimstad","submitted_at":"2024-02-28T11:21:32Z","abstract_excerpt":"This paper presents a new approach to the solution of Probabilistic Risk Assessment (PRA) models using the combination of Reinforcement Learning (RL) and Graph Neural Networks (GNNs). The paper introduces and demonstrates the concept using one of the most popular PRA models - Fault Trees. This paper's original idea is to apply RL algorithms to solve a PRA model represented with a graph model. Given enough training data, or through RL, such an approach helps train generic PRA solvers that can optimize and partially substitute classical PRA solvers that are based on existing formal methods. Such"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.18246","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.SY","submitted_at":"2024-02-28T11:21:32Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"c6ccefb30f9b525349765b03d222afa9de62650667b2cb3a0d6354d33f0ceeef","abstract_canon_sha256":"51b54add78a4031a37da5ef77965a3f37d771aef0b4b9a71758f65780936fa4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:14.222719Z","signature_b64":"pW7z/iXyvgfCd3Zw/4F400acv6JSCVxcfgsnF2jD7z8Rbd426M6JBj4Bmo1b1bE6Ww3VkKCm81Yk6XyNLLQiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f04baac3acfb75bc9ccbe167f22b2e6e6b16b106011d1426887c0ebe4081bd7","last_reissued_at":"2026-07-05T07:50:14.222217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:14.222217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning and Graph Neural Networks for Probabilistic Risk Assessment","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Andrey Morozov, Joachim Grimstad","submitted_at":"2024-02-28T11:21:32Z","abstract_excerpt":"This paper presents a new approach to the solution of Probabilistic Risk Assessment (PRA) models using the combination of Reinforcement Learning (RL) and Graph Neural Networks (GNNs). The paper introduces and demonstrates the concept using one of the most popular PRA models - Fault Trees. This paper's original idea is to apply RL algorithms to solve a PRA model represented with a graph model. Given enough training data, or through RL, such an approach helps train generic PRA solvers that can optimize and partially substitute classical PRA solvers that are based on existing formal methods. Such"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18246","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/2402.18246/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.18246","created_at":"2026-07-05T07:50:14.222283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18246v1","created_at":"2026-07-05T07:50:14.222283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18246","created_at":"2026-07-05T07:50:14.222283+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4CLVLB2Z63V","created_at":"2026-07-05T07:50:14.222283+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4CLVLB2Z63VXSOM","created_at":"2026-07-05T07:50:14.222283+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4CLVLB2","created_at":"2026-07-05T07:50:14.222283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10484","citing_title":"A Hybrid Real-Time Framework for Efficient Fussell-Vesely Importance Evaluation Using Virtual Fault Trees and Graph Neural Networks","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P4CLVLB2Z63VXSOMXYLH6IVS43","json":"https://pith.science/pith/P4CLVLB2Z63VXSOMXYLH6IVS43.json","graph_json":"https://pith.science/api/pith-number/P4CLVLB2Z63VXSOMXYLH6IVS43/graph.json","events_json":"https://pith.science/api/pith-number/P4CLVLB2Z63VXSOMXYLH6IVS43/events.json","paper":"https://pith.science/paper/P4CLVLB2"},"agent_actions":{"view_html":"https://pith.science/pith/P4CLVLB2Z63VXSOMXYLH6IVS43","download_json":"https://pith.science/pith/P4CLVLB2Z63VXSOMXYLH6IVS43.json","view_paper":"https://pith.science/paper/P4CLVLB2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18246&json=true","fetch_graph":"https://pith.science/api/pith-number/P4CLVLB2Z63VXSOMXYLH6IVS43/graph.json","fetch_events":"https://pith.science/api/pith-number/P4CLVLB2Z63VXSOMXYLH6IVS43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4CLVLB2Z63VXSOMXYLH6IVS43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4CLVLB2Z63VXSOMXYLH6IVS43/action/storage_attestation","attest_author":"https://pith.science/pith/P4CLVLB2Z63VXSOMXYLH6IVS43/action/author_attestation","sign_citation":"https://pith.science/pith/P4CLVLB2Z63VXSOMXYLH6IVS43/action/citation_signature","submit_replication":"https://pith.science/pith/P4CLVLB2Z63VXSOMXYLH6IVS43/action/replication_record"}},"created_at":"2026-07-05T07:50:14.222283+00:00","updated_at":"2026-07-05T07:50:14.222283+00:00"}