{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2DGP7J3RA7ILNEG3MHXZLR6XXT","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":"e2dc6bc223a0045362d13252c2a75182b699a9222e2d216ddbc1121a6d8dce61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-22T17:20:48Z","title_canon_sha256":"febc227a8cc3464b2d2453c23d45a0ef9d65882a74aaedd71b64a857d5a498c1"},"schema_version":"1.0","source":{"id":"2104.11186","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.11186","created_at":"2026-07-05T03:39:48Z"},{"alias_kind":"arxiv_version","alias_value":"2104.11186v2","created_at":"2026-07-05T03:39:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.11186","created_at":"2026-07-05T03:39:48Z"},{"alias_kind":"pith_short_12","alias_value":"2DGP7J3RA7IL","created_at":"2026-07-05T03:39:48Z"},{"alias_kind":"pith_short_16","alias_value":"2DGP7J3RA7ILNEG3","created_at":"2026-07-05T03:39:48Z"},{"alias_kind":"pith_short_8","alias_value":"2DGP7J3R","created_at":"2026-07-05T03:39:48Z"}],"graph_snapshots":[{"event_id":"sha256:3156a65e25dd7e8d58d5ebfa6c01ec88a6270613375f451fdebe4daf4a474933","target":"graph","created_at":"2026-07-05T03:39:48Z","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/2104.11186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of learning in the stochastic shortest path (SSP) setting, where an agent seeks to minimize the expected cost accumulated before reaching a goal state. We design a novel model-based algorithm EB-SSP that carefully skews the empirical transitions and perturbs the empirical costs with an exploration bonus to induce an optimistic SSP problem whose associated value iteration scheme is guaranteed to converge. We prove that EB-SSP achieves the minimax regret rate $\\tilde{O}(B_{\\star} \\sqrt{S A K})$, where $K$ is the number of episodes, $S$ is the number of states, $A$ is the num","authors_text":"Alessandro Lazaric, Jean Tarbouriech, Matteo Pirotta, Michal Valko, Runlong Zhou, Simon S. Du","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-22T17:20:48Z","title":"Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.11186","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:e41d23a1de4e6eef2c45e979f3a2701b56b161f775b7bbbf6b82cc5fb65b3286","target":"record","created_at":"2026-07-05T03:39:48Z","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":"e2dc6bc223a0045362d13252c2a75182b699a9222e2d216ddbc1121a6d8dce61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-22T17:20:48Z","title_canon_sha256":"febc227a8cc3464b2d2453c23d45a0ef9d65882a74aaedd71b64a857d5a498c1"},"schema_version":"1.0","source":{"id":"2104.11186","kind":"arxiv","version":2}},"canonical_sha256":"d0ccffa77107d0b690db61ef95c7d7bce7312018be923d04d3a3ed6ef82a18a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0ccffa77107d0b690db61ef95c7d7bce7312018be923d04d3a3ed6ef82a18a3","first_computed_at":"2026-07-05T03:39:48.039007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:39:48.039007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BPlFbgMwS/zU9VuLoVKfiDF2R+y4UMFY7BcnItn1wZBCE7mIsFO1Eslyj7dmxXXl5CkLMMqDHMK0jzdfzftrAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:39:48.039446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.11186","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e41d23a1de4e6eef2c45e979f3a2701b56b161f775b7bbbf6b82cc5fb65b3286","sha256:3156a65e25dd7e8d58d5ebfa6c01ec88a6270613375f451fdebe4daf4a474933"],"state_sha256":"122f8613ec7dce567fe4f01256a425e7f4360780d4c071ee4c2eca3ce99e0bd4"}