{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PJ7HTIVYV2FTRW3JYOVES3BRHO","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":"02d8e4d32ebd602fb66b1b84c0e72e4d4925e94fd6fd3d4e63da3f2a37369764","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T07:13:11Z","title_canon_sha256":"448e5f1d90c895d695da52110a7b00f361839efd21d81c472ba2d34401a10467"},"schema_version":"1.0","source":{"id":"2602.09474","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.09474","created_at":"2026-06-02T02:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2602.09474v2","created_at":"2026-06-02T02:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.09474","created_at":"2026-06-02T02:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"PJ7HTIVYV2FT","created_at":"2026-06-02T02:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"PJ7HTIVYV2FTRW3J","created_at":"2026-06-02T02:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"PJ7HTIVY","created_at":"2026-06-02T02:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:019e0149691bccf77264eee6eacf982c0b9b8b88cb7191fbb99e231a320c22aa","target":"graph","created_at":"2026-06-02T02:04:51Z","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/2602.09474/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of $\\Lambda$ steps per episode. This model captures environments that are stable except at a few vulnerable points. We introduce \\emph{conditioned occupancy measures}, which remain stable across episodes even with adversarial transitions, and use them to design two algorithms. The first handles arbitrary adversarial steps and achieves regret $\\tilde{O}(H S^{\\Lambda}\\sqrt{K S A^{\\Lambda+1}})$, where $K$ is the number of episodes, $S$ is the number of state","authors_text":"Ofir Schlisselberg, Tal Lancewicki, Yishay Mansour","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T07:13:11Z","title":"Online Learning in MDPs with Partially Adversarial Transitions and Losses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.09474","kind":"arxiv","version":2},"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":"sha256:6c45e73fa16201ba13ddefd8e9fb9dad11812c7615d6143fcba44c4b03ab29dd","target":"record","created_at":"2026-06-02T02:04:51Z","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":"02d8e4d32ebd602fb66b1b84c0e72e4d4925e94fd6fd3d4e63da3f2a37369764","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T07:13:11Z","title_canon_sha256":"448e5f1d90c895d695da52110a7b00f361839efd21d81c472ba2d34401a10467"},"schema_version":"1.0","source":{"id":"2602.09474","kind":"arxiv","version":2}},"canonical_sha256":"7a7e79a2b8ae8b38db69c3aa496c313bb699bc56bb65bfec8a1d6e0cf8fdd91e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a7e79a2b8ae8b38db69c3aa496c313bb699bc56bb65bfec8a1d6e0cf8fdd91e","first_computed_at":"2026-06-02T02:04:51.201416Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:51.201416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CR1srPJADyi4/FJb1ucY3AvjvpK7eCfvcPy+ZHsKj37WCyDTLDuMzaePcvqHbnWwb+s5xuBU/QfC7cR5jTNyBQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:51.201853Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.09474","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c45e73fa16201ba13ddefd8e9fb9dad11812c7615d6143fcba44c4b03ab29dd","sha256:019e0149691bccf77264eee6eacf982c0b9b8b88cb7191fbb99e231a320c22aa"],"state_sha256":"d3158d78f9d268ced2bc5dff082240e62e9f8edfd715e9050299d46f790b50fe"}