{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:H2AFJTQQBHGSZGUPRFJ3XUJBJI","short_pith_number":"pith:H2AFJTQQ","canonical_record":{"source":{"id":"2002.09869","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-23T09:10:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2d66c1a53d71044a41d1c2c4bafe070bea07ba40bbb0782fb96b5821b15ca5b2","abstract_canon_sha256":"d08ccbdfdc96d734cefa7d0e9bdfcf2abf02c0f3da361ef1dfee8156cbe00569"},"schema_version":"1.0"},"canonical_sha256":"3e8054ce1009cd2c9a8f8953bbd1214a3365d6ed64db757bccaa72203a31d2eb","source":{"kind":"arxiv","id":"2002.09869","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09869","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09869v1","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09869","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"pith_short_12","alias_value":"H2AFJTQQBHGS","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"pith_short_16","alias_value":"H2AFJTQQBHGSZGUP","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"pith_short_8","alias_value":"H2AFJTQQ","created_at":"2026-07-05T00:43:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:H2AFJTQQBHGSZGUPRFJ3XUJBJI","target":"record","payload":{"canonical_record":{"source":{"id":"2002.09869","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-23T09:10:14Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2d66c1a53d71044a41d1c2c4bafe070bea07ba40bbb0782fb96b5821b15ca5b2","abstract_canon_sha256":"d08ccbdfdc96d734cefa7d0e9bdfcf2abf02c0f3da361ef1dfee8156cbe00569"},"schema_version":"1.0"},"canonical_sha256":"3e8054ce1009cd2c9a8f8953bbd1214a3365d6ed64db757bccaa72203a31d2eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:12.590468Z","signature_b64":"VbhgzfEHOngmHdtupGuR1ypd63ZekQ62mdQvqiB9tKfH5DNbG3gVXg1ckI+cvc46tvu9NvYPYiSRKVqwMDGHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e8054ce1009cd2c9a8f8953bbd1214a3365d6ed64db757bccaa72203a31d2eb","last_reissued_at":"2026-07-05T00:43:12.590037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:12.590037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.09869","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:43:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+jt4JCTrtqZbjV8c3sgevSrhh9gHiXGQcbaaLhooDr3UmRO0xvbSiKi8r0qYYxrhbZP7jewF5x7Ou+8zEgOzBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:36:02.896036Z"},"content_sha256":"d5b950fa37b760ff6746da17c3ba92c8acc77be4384ab59dfbf12dedddb88271","schema_version":"1.0","event_id":"sha256:d5b950fa37b760ff6746da17c3ba92c8acc77be4384ab59dfbf12dedddb88271"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:H2AFJTQQBHGSZGUPRFJ3XUJBJI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Near-optimal Regret Bounds for Stochastic Shortest Path","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alon Cohen, Aviv Rosenberg, Haim Kaplan, Yishay Mansour","submitted_at":"2020-02-23T09:10:14Z","abstract_excerpt":"Stochastic shortest path (SSP) is a well-known problem in planning and control, in which an agent has to reach a goal state in minimum total expected cost. In the learning formulation of the problem, the agent is unaware of the environment dynamics (i.e., the transition function) and has to repeatedly play for a given number of episodes while reasoning about the problem's optimal solution. Unlike other well-studied models in reinforcement learning (RL), the length of an episode is not predetermined (or bounded) and is influenced by the agent's actions. Recently, Tarbouriech et al. (2019) studi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09869","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/2002.09869/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":"2026-07-05T00:43:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qzeKtrem3MsTBLbQ5P2SboEQTkUrIhGQ8Q7yjqVxB1oQDWzu+FsX26WxfbZWO7rE1Z01+S4krj+ZiFQ5Zpd0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:36:02.896707Z"},"content_sha256":"8ed1d0515a70c64d739ce24de3549cafa7db6bca4191b19a403bda00acaddabe","schema_version":"1.0","event_id":"sha256:8ed1d0515a70c64d739ce24de3549cafa7db6bca4191b19a403bda00acaddabe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H2AFJTQQBHGSZGUPRFJ3XUJBJI/bundle.json","state_url":"https://pith.science/pith/H2AFJTQQBHGSZGUPRFJ3XUJBJI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H2AFJTQQBHGSZGUPRFJ3XUJBJI/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":"2026-08-04T15:36:02Z","links":{"resolver":"https://pith.science/pith/H2AFJTQQBHGSZGUPRFJ3XUJBJI","bundle":"https://pith.science/pith/H2AFJTQQBHGSZGUPRFJ3XUJBJI/bundle.json","state":"https://pith.science/pith/H2AFJTQQBHGSZGUPRFJ3XUJBJI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H2AFJTQQBHGSZGUPRFJ3XUJBJI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:H2AFJTQQBHGSZGUPRFJ3XUJBJI","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":"d08ccbdfdc96d734cefa7d0e9bdfcf2abf02c0f3da361ef1dfee8156cbe00569","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-23T09:10:14Z","title_canon_sha256":"2d66c1a53d71044a41d1c2c4bafe070bea07ba40bbb0782fb96b5821b15ca5b2"},"schema_version":"1.0","source":{"id":"2002.09869","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09869","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09869v1","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09869","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"pith_short_12","alias_value":"H2AFJTQQBHGS","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"pith_short_16","alias_value":"H2AFJTQQBHGSZGUP","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"pith_short_8","alias_value":"H2AFJTQQ","created_at":"2026-07-05T00:43:12Z"}],"graph_snapshots":[{"event_id":"sha256:8ed1d0515a70c64d739ce24de3549cafa7db6bca4191b19a403bda00acaddabe","target":"graph","created_at":"2026-07-05T00:43:12Z","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/2002.09869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic shortest path (SSP) is a well-known problem in planning and control, in which an agent has to reach a goal state in minimum total expected cost. In the learning formulation of the problem, the agent is unaware of the environment dynamics (i.e., the transition function) and has to repeatedly play for a given number of episodes while reasoning about the problem's optimal solution. Unlike other well-studied models in reinforcement learning (RL), the length of an episode is not predetermined (or bounded) and is influenced by the agent's actions. Recently, Tarbouriech et al. (2019) studi","authors_text":"Alon Cohen, Aviv Rosenberg, Haim Kaplan, Yishay Mansour","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-23T09:10:14Z","title":"Near-optimal Regret Bounds for Stochastic Shortest Path"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09869","kind":"arxiv","version":1},"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:d5b950fa37b760ff6746da17c3ba92c8acc77be4384ab59dfbf12dedddb88271","target":"record","created_at":"2026-07-05T00:43:12Z","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":"d08ccbdfdc96d734cefa7d0e9bdfcf2abf02c0f3da361ef1dfee8156cbe00569","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-23T09:10:14Z","title_canon_sha256":"2d66c1a53d71044a41d1c2c4bafe070bea07ba40bbb0782fb96b5821b15ca5b2"},"schema_version":"1.0","source":{"id":"2002.09869","kind":"arxiv","version":1}},"canonical_sha256":"3e8054ce1009cd2c9a8f8953bbd1214a3365d6ed64db757bccaa72203a31d2eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e8054ce1009cd2c9a8f8953bbd1214a3365d6ed64db757bccaa72203a31d2eb","first_computed_at":"2026-07-05T00:43:12.590037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:43:12.590037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VbhgzfEHOngmHdtupGuR1ypd63ZekQ62mdQvqiB9tKfH5DNbG3gVXg1ckI+cvc46tvu9NvYPYiSRKVqwMDGHCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:43:12.590468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.09869","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5b950fa37b760ff6746da17c3ba92c8acc77be4384ab59dfbf12dedddb88271","sha256:8ed1d0515a70c64d739ce24de3549cafa7db6bca4191b19a403bda00acaddabe"],"state_sha256":"1bace38f1052101480368bbe86f98615273a0e3c041955fd16afae0eec9db20c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UF16eWkLyXPSe77pFVXpD1WLHSwHu74BhpBBjea16fSb6iL7e5Wk/sAqpQnVmJmQ9lor3mAv8fxLjEE3zVmODg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:36:02.911770Z","bundle_sha256":"3892e3489663d810c8e3b54bf36b0257f524655b52c285486f1d38977f0b957f"}}