{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N33USZ6JGDCPSMXEDCOJ35CHTD","short_pith_number":"pith:N33USZ6J","schema_version":"1.0","canonical_sha256":"6ef74967c930c4f932e4189c9df44798e08d1c3c3b310ddbdfdaea311289c00a","source":{"kind":"arxiv","id":"2505.05609","version":1},"attestation_state":"computed","paper":{"title":"On Corruption-Robustness in Performative Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Debmalya Mandal, Goran Radanovic, Vasilis Pollatos","submitted_at":"2025-05-08T19:37:35Z","abstract_excerpt":"In performative Reinforcement Learning (RL), an agent faces a policy-dependent environment: the reward and transition functions depend on the agent's policy. Prior work on performative RL has studied the convergence of repeated retraining approaches to a performatively stable policy. In the finite sample regime, these approaches repeatedly solve for a saddle point of a convex-concave objective, which estimates the Lagrangian of a regularized version of the reinforcement learning problem. In this paper, we aim to extend such repeated retraining approaches, enabling them to operate under corrupt"},"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":"2505.05609","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-08T19:37:35Z","cross_cats_sorted":[],"title_canon_sha256":"e19f6ffbf63f2c823798122df9af2d54e8b527faa57eb115b0c8f2c4176e9846","abstract_canon_sha256":"b450722099a8902b71a841c731d16b2de69ec5e7b5036e048822f026162c374a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:28.975961Z","signature_b64":"cZkM41RdtmP6lCOSJDry1W/5GOASALsdmYCpOLyXx6FG6engZVQ9G/tdumFt8/n5g0IMs+O80jUlxof3pfrSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ef74967c930c4f932e4189c9df44798e08d1c3c3b310ddbdfdaea311289c00a","last_reissued_at":"2026-07-05T11:00:28.975553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:28.975553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Corruption-Robustness in Performative Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Debmalya Mandal, Goran Radanovic, Vasilis Pollatos","submitted_at":"2025-05-08T19:37:35Z","abstract_excerpt":"In performative Reinforcement Learning (RL), an agent faces a policy-dependent environment: the reward and transition functions depend on the agent's policy. Prior work on performative RL has studied the convergence of repeated retraining approaches to a performatively stable policy. In the finite sample regime, these approaches repeatedly solve for a saddle point of a convex-concave objective, which estimates the Lagrangian of a regularized version of the reinforcement learning problem. In this paper, we aim to extend such repeated retraining approaches, enabling them to operate under corrupt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05609","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/2505.05609/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":"2505.05609","created_at":"2026-07-05T11:00:28.975611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05609v1","created_at":"2026-07-05T11:00:28.975611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05609","created_at":"2026-07-05T11:00:28.975611+00:00"},{"alias_kind":"pith_short_12","alias_value":"N33USZ6JGDCP","created_at":"2026-07-05T11:00:28.975611+00:00"},{"alias_kind":"pith_short_16","alias_value":"N33USZ6JGDCPSMXE","created_at":"2026-07-05T11:00:28.975611+00:00"},{"alias_kind":"pith_short_8","alias_value":"N33USZ6J","created_at":"2026-07-05T11:00:28.975611+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/N33USZ6JGDCPSMXEDCOJ35CHTD","json":"https://pith.science/pith/N33USZ6JGDCPSMXEDCOJ35CHTD.json","graph_json":"https://pith.science/api/pith-number/N33USZ6JGDCPSMXEDCOJ35CHTD/graph.json","events_json":"https://pith.science/api/pith-number/N33USZ6JGDCPSMXEDCOJ35CHTD/events.json","paper":"https://pith.science/paper/N33USZ6J"},"agent_actions":{"view_html":"https://pith.science/pith/N33USZ6JGDCPSMXEDCOJ35CHTD","download_json":"https://pith.science/pith/N33USZ6JGDCPSMXEDCOJ35CHTD.json","view_paper":"https://pith.science/paper/N33USZ6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05609&json=true","fetch_graph":"https://pith.science/api/pith-number/N33USZ6JGDCPSMXEDCOJ35CHTD/graph.json","fetch_events":"https://pith.science/api/pith-number/N33USZ6JGDCPSMXEDCOJ35CHTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N33USZ6JGDCPSMXEDCOJ35CHTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N33USZ6JGDCPSMXEDCOJ35CHTD/action/storage_attestation","attest_author":"https://pith.science/pith/N33USZ6JGDCPSMXEDCOJ35CHTD/action/author_attestation","sign_citation":"https://pith.science/pith/N33USZ6JGDCPSMXEDCOJ35CHTD/action/citation_signature","submit_replication":"https://pith.science/pith/N33USZ6JGDCPSMXEDCOJ35CHTD/action/replication_record"}},"created_at":"2026-07-05T11:00:28.975611+00:00","updated_at":"2026-07-05T11:00:28.975611+00:00"}