{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2DGP7J3RA7ILNEG3MHXZLR6XXT","short_pith_number":"pith:2DGP7J3R","canonical_record":{"source":{"id":"2104.11186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-22T17:20:48Z","cross_cats_sorted":[],"title_canon_sha256":"febc227a8cc3464b2d2453c23d45a0ef9d65882a74aaedd71b64a857d5a498c1","abstract_canon_sha256":"e2dc6bc223a0045362d13252c2a75182b699a9222e2d216ddbc1121a6d8dce61"},"schema_version":"1.0"},"canonical_sha256":"d0ccffa77107d0b690db61ef95c7d7bce7312018be923d04d3a3ed6ef82a18a3","source":{"kind":"arxiv","id":"2104.11186","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2DGP7J3RA7ILNEG3MHXZLR6XXT","target":"record","payload":{"canonical_record":{"source":{"id":"2104.11186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-22T17:20:48Z","cross_cats_sorted":[],"title_canon_sha256":"febc227a8cc3464b2d2453c23d45a0ef9d65882a74aaedd71b64a857d5a498c1","abstract_canon_sha256":"e2dc6bc223a0045362d13252c2a75182b699a9222e2d216ddbc1121a6d8dce61"},"schema_version":"1.0"},"canonical_sha256":"d0ccffa77107d0b690db61ef95c7d7bce7312018be923d04d3a3ed6ef82a18a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:48.039446Z","signature_b64":"BPlFbgMwS/zU9VuLoVKfiDF2R+y4UMFY7BcnItn1wZBCE7mIsFO1Eslyj7dmxXXl5CkLMMqDHMK0jzdfzftrAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0ccffa77107d0b690db61ef95c7d7bce7312018be923d04d3a3ed6ef82a18a3","last_reissued_at":"2026-07-05T03:39:48.039007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:48.039007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.11186","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:39:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+qAr/suVCt87h7IYhtW8p7blcCxY+hVWK2NRI3zgiCcEAVaysmH9RmXzrxjdqVPk4JEWKIgdW8ZB4JPS5CBHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:07:08.360655Z"},"content_sha256":"e41d23a1de4e6eef2c45e979f3a2701b56b161f775b7bbbf6b82cc5fb65b3286","schema_version":"1.0","event_id":"sha256:e41d23a1de4e6eef2c45e979f3a2701b56b161f775b7bbbf6b82cc5fb65b3286"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2DGP7J3RA7ILNEG3MHXZLR6XXT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Jean Tarbouriech, Matteo Pirotta, Michal Valko, Runlong Zhou, Simon S. Du","submitted_at":"2021-04-22T17:20:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.11186","kind":"arxiv","version":2},"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/2104.11186/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:39:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S4Ir42UvZfFQN8+1MPSF0CJqWxPWzVG+huZ/+JKck/pnX/1NpVGPvCOCCZmPA268qAlxphXfyAmkvHa8D2qoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:07:08.361033Z"},"content_sha256":"3156a65e25dd7e8d58d5ebfa6c01ec88a6270613375f451fdebe4daf4a474933","schema_version":"1.0","event_id":"sha256:3156a65e25dd7e8d58d5ebfa6c01ec88a6270613375f451fdebe4daf4a474933"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2DGP7J3RA7ILNEG3MHXZLR6XXT/bundle.json","state_url":"https://pith.science/pith/2DGP7J3RA7ILNEG3MHXZLR6XXT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2DGP7J3RA7ILNEG3MHXZLR6XXT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T19:07:08Z","links":{"resolver":"https://pith.science/pith/2DGP7J3RA7ILNEG3MHXZLR6XXT","bundle":"https://pith.science/pith/2DGP7J3RA7ILNEG3MHXZLR6XXT/bundle.json","state":"https://pith.science/pith/2DGP7J3RA7ILNEG3MHXZLR6XXT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2DGP7J3RA7ILNEG3MHXZLR6XXT/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xsfuN0iNZy4P1+QagEUBnaJaYPo//XFHYty2Rqyo8Q/25e9rNk8N6Cf/8J3L65ikOcS2klFe7A6GEKoGQX4TAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:07:08.363005Z","bundle_sha256":"9c69529c555d606cd2c9670ca57ef502049d543e210f253deb50a915d4774672"}}