{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LCJYSECAY5XV44HSYJKLO2HDAT","short_pith_number":"pith:LCJYSECA","schema_version":"1.0","canonical_sha256":"5893891040c76f5e70f2c254b768e304c1210bb9c3890d023c9f21befe445a2e","source":{"kind":"arxiv","id":"2109.08236","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning on Encrypted Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alberto Jesu, Alessandro Staffolani, Mirco Musolesi, Rebecca Montanari, Victor-Alexandru Darvariu","submitted_at":"2021-09-16T21:59:37Z","abstract_excerpt":"The growing number of applications of Reinforcement Learning (RL) in real-world domains has led to the development of privacy-preserving techniques due to the inherently sensitive nature of data. Most existing works focus on differential privacy, in which information is revealed in the clear to an agent whose learned model should be robust against information leakage to malicious third parties. Motivated by use cases in which only encrypted data might be shared, such as information from sensitive sites, in this work we consider scenarios in which the inputs themselves are sensitive and cannot "},"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":"2109.08236","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-16T21:59:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1c065186bc828970ab175f0776350c97f3df936f1502935294c5ff1658a635af","abstract_canon_sha256":"0a46150a828fcb8da3df92f6bab5072c6a4d32257755a40e3f6b524f2058a6c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:13.467570Z","signature_b64":"HkqPU1KTSRmvGmYWCvULqzk5SW9DCgbfn7HYB1I9h4Liz7p6ebvxze3MlNjDkUScQP1BYn1grNEzWkMJagryBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5893891040c76f5e70f2c254b768e304c1210bb9c3890d023c9f21befe445a2e","last_reissued_at":"2026-07-05T03:15:13.467144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:13.467144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning on Encrypted Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alberto Jesu, Alessandro Staffolani, Mirco Musolesi, Rebecca Montanari, Victor-Alexandru Darvariu","submitted_at":"2021-09-16T21:59:37Z","abstract_excerpt":"The growing number of applications of Reinforcement Learning (RL) in real-world domains has led to the development of privacy-preserving techniques due to the inherently sensitive nature of data. Most existing works focus on differential privacy, in which information is revealed in the clear to an agent whose learned model should be robust against information leakage to malicious third parties. Motivated by use cases in which only encrypted data might be shared, such as information from sensitive sites, in this work we consider scenarios in which the inputs themselves are sensitive and cannot "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08236","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/2109.08236/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":"2109.08236","created_at":"2026-07-05T03:15:13.467200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.08236v1","created_at":"2026-07-05T03:15:13.467200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08236","created_at":"2026-07-05T03:15:13.467200+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCJYSECAY5XV","created_at":"2026-07-05T03:15:13.467200+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCJYSECAY5XV44HS","created_at":"2026-07-05T03:15:13.467200+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCJYSECA","created_at":"2026-07-05T03:15:13.467200+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCJYSECAY5XV44HSYJKLO2HDAT","json":"https://pith.science/pith/LCJYSECAY5XV44HSYJKLO2HDAT.json","graph_json":"https://pith.science/api/pith-number/LCJYSECAY5XV44HSYJKLO2HDAT/graph.json","events_json":"https://pith.science/api/pith-number/LCJYSECAY5XV44HSYJKLO2HDAT/events.json","paper":"https://pith.science/paper/LCJYSECA"},"agent_actions":{"view_html":"https://pith.science/pith/LCJYSECAY5XV44HSYJKLO2HDAT","download_json":"https://pith.science/pith/LCJYSECAY5XV44HSYJKLO2HDAT.json","view_paper":"https://pith.science/paper/LCJYSECA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.08236&json=true","fetch_graph":"https://pith.science/api/pith-number/LCJYSECAY5XV44HSYJKLO2HDAT/graph.json","fetch_events":"https://pith.science/api/pith-number/LCJYSECAY5XV44HSYJKLO2HDAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCJYSECAY5XV44HSYJKLO2HDAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCJYSECAY5XV44HSYJKLO2HDAT/action/storage_attestation","attest_author":"https://pith.science/pith/LCJYSECAY5XV44HSYJKLO2HDAT/action/author_attestation","sign_citation":"https://pith.science/pith/LCJYSECAY5XV44HSYJKLO2HDAT/action/citation_signature","submit_replication":"https://pith.science/pith/LCJYSECAY5XV44HSYJKLO2HDAT/action/replication_record"}},"created_at":"2026-07-05T03:15:13.467200+00:00","updated_at":"2026-07-05T03:15:13.467200+00:00"}