{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LXLGEQORUBTMT2OTMMQHMVC4PW","short_pith_number":"pith:LXLGEQOR","schema_version":"1.0","canonical_sha256":"5dd66241d1a066c9e9d3632076545c7db3aa83d1527dceb3fb6f6d77f6f12a60","source":{"kind":"arxiv","id":"2211.12470","version":1},"attestation_state":"computed","paper":{"title":"A Deep Reinforcement Learning Approach to Rare Event Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anthony Corso, Grace Gao, Kyu-Young Kim, Mykel J. Kochenderfer, Shubh Gupta","submitted_at":"2022-11-22T18:29:14Z","abstract_excerpt":"An important step in the design of autonomous systems is to evaluate the probability that a failure will occur. In safety-critical domains, the failure probability is extremely small so that the evaluation of a policy through Monte Carlo sampling is inefficient. Adaptive importance sampling approaches have been developed for rare event estimation but do not scale well to sequential systems with long horizons. In this work, we develop two adaptive importance sampling algorithms that can efficiently estimate the probability of rare events for sequential decision making systems. The basis for the"},"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":"2211.12470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-22T18:29:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"01c6ca225d707cba1fd1e5da2723689c6cd99089e85c39865a88245fcff9464f","abstract_canon_sha256":"5c6844ed0a46cc8ab5fc25fcfe29ead505ade7363520ba6e6e0bed15a535c71b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:17.331602Z","signature_b64":"fpWvLqXMvRBaUyzlKf6TS14IS5sqozz1I8Hx0sr+AvzfY85UFXlf1LqcOEXH7V7OGKYkAnR/nlIAtW7PnqPmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dd66241d1a066c9e9d3632076545c7db3aa83d1527dceb3fb6f6d77f6f12a60","last_reissued_at":"2026-07-05T05:18:17.331149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:17.331149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Deep Reinforcement Learning Approach to Rare Event Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anthony Corso, Grace Gao, Kyu-Young Kim, Mykel J. Kochenderfer, Shubh Gupta","submitted_at":"2022-11-22T18:29:14Z","abstract_excerpt":"An important step in the design of autonomous systems is to evaluate the probability that a failure will occur. In safety-critical domains, the failure probability is extremely small so that the evaluation of a policy through Monte Carlo sampling is inefficient. Adaptive importance sampling approaches have been developed for rare event estimation but do not scale well to sequential systems with long horizons. In this work, we develop two adaptive importance sampling algorithms that can efficiently estimate the probability of rare events for sequential decision making systems. The basis for the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12470","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/2211.12470/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":"2211.12470","created_at":"2026-07-05T05:18:17.331206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12470v1","created_at":"2026-07-05T05:18:17.331206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12470","created_at":"2026-07-05T05:18:17.331206+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXLGEQORUBTM","created_at":"2026-07-05T05:18:17.331206+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXLGEQORUBTMT2OT","created_at":"2026-07-05T05:18:17.331206+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXLGEQOR","created_at":"2026-07-05T05:18:17.331206+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.02154","citing_title":"Failure Probability Estimation for Black-Box Autonomous Systems using State-Dependent Importance Sampling Proposals","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LXLGEQORUBTMT2OTMMQHMVC4PW","json":"https://pith.science/pith/LXLGEQORUBTMT2OTMMQHMVC4PW.json","graph_json":"https://pith.science/api/pith-number/LXLGEQORUBTMT2OTMMQHMVC4PW/graph.json","events_json":"https://pith.science/api/pith-number/LXLGEQORUBTMT2OTMMQHMVC4PW/events.json","paper":"https://pith.science/paper/LXLGEQOR"},"agent_actions":{"view_html":"https://pith.science/pith/LXLGEQORUBTMT2OTMMQHMVC4PW","download_json":"https://pith.science/pith/LXLGEQORUBTMT2OTMMQHMVC4PW.json","view_paper":"https://pith.science/paper/LXLGEQOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12470&json=true","fetch_graph":"https://pith.science/api/pith-number/LXLGEQORUBTMT2OTMMQHMVC4PW/graph.json","fetch_events":"https://pith.science/api/pith-number/LXLGEQORUBTMT2OTMMQHMVC4PW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXLGEQORUBTMT2OTMMQHMVC4PW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXLGEQORUBTMT2OTMMQHMVC4PW/action/storage_attestation","attest_author":"https://pith.science/pith/LXLGEQORUBTMT2OTMMQHMVC4PW/action/author_attestation","sign_citation":"https://pith.science/pith/LXLGEQORUBTMT2OTMMQHMVC4PW/action/citation_signature","submit_replication":"https://pith.science/pith/LXLGEQORUBTMT2OTMMQHMVC4PW/action/replication_record"}},"created_at":"2026-07-05T05:18:17.331206+00:00","updated_at":"2026-07-05T05:18:17.331206+00:00"}