{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7N7K4G5NOOW7ISP2RJNQMDH6WT","short_pith_number":"pith:7N7K4G5N","canonical_record":{"source":{"id":"2607.29294","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T11:12:31Z","cross_cats_sorted":[],"title_canon_sha256":"7e4f7b292608148a7311d216102a812c0fa3682bd4657446021b2080f0adb5c6","abstract_canon_sha256":"004940a426688b205028f0d8c09a793893f6c66337157466edbbb84777f5cf93"},"schema_version":"1.0"},"canonical_sha256":"fb7eae1bad73adf449fa8a5b060cfeb4e04858f811fe580e04baab0b3b17e252","source":{"kind":"arxiv","id":"2607.29294","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29294","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29294v1","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29294","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"7N7K4G5NOOW7","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"pith_short_16","alias_value":"7N7K4G5NOOW7ISP2","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"pith_short_8","alias_value":"7N7K4G5N","created_at":"2026-08-03T01:23:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7N7K4G5NOOW7ISP2RJNQMDH6WT","target":"record","payload":{"canonical_record":{"source":{"id":"2607.29294","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T11:12:31Z","cross_cats_sorted":[],"title_canon_sha256":"7e4f7b292608148a7311d216102a812c0fa3682bd4657446021b2080f0adb5c6","abstract_canon_sha256":"004940a426688b205028f0d8c09a793893f6c66337157466edbbb84777f5cf93"},"schema_version":"1.0"},"canonical_sha256":"fb7eae1bad73adf449fa8a5b060cfeb4e04858f811fe580e04baab0b3b17e252","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:23:58.921665Z","signature_b64":"DtH1+3A/XgIV4fMDbdK7XkaAFhcFu+j02rjVuhXfA2j6MDPGnAiS1837c/NdJWJPzGosGtOdEc8yy8wfsOppBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb7eae1bad73adf449fa8a5b060cfeb4e04858f811fe580e04baab0b3b17e252","last_reissued_at":"2026-08-03T01:23:58.919866Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:23:58.919866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.29294","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":"2026-08-03T01:23:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h+mgE9T9OT75VbrByII6jxLCWlaTMjZqqpJLQ2+bYkOn/oCArbfCc9FmkTrno2M8ccA61WrIfnVQsG443FFLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:17:12.964389Z"},"content_sha256":"c72aac895045674f1bceae27aed68832d9135b0c0c3a064269a16c01975ea98d","schema_version":"1.0","event_id":"sha256:c72aac895045674f1bceae27aed68832d9135b0c0c3a064269a16c01975ea98d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7N7K4G5NOOW7ISP2RJNQMDH6WT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anders Jonsson, Emilie Kaufmann, Gianmarco Tedeschi, Lorenzo Steccanella","submitted_at":"2026-07-31T11:12:31Z","abstract_excerpt":"We present HBPI-UCRL, a model-based algorithm for hierarchical reinforcement learning (HRL) that learns high-level and low-level policies in parallel. HBPI-UCRL exploits the fact that a high-level transition corresponds to a multi-step transition at the low level. We introduce two conditions on the low-level dynamics that are sufficient to make parallel HRL learnable. When these conditions hold, we prove that HBPI-UCRL has a polynomial sample complexity in the problem parameters. In the sparse-reward, goal-directed setting, our sample complexity upper bound for HBPI-UCRL is strictly lower than"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29294","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/2607.29294/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":"2026-08-03T01:23:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f6xwcgq3y91QV9OmdXEjRt8Uf3B0i5ugX4oLa+Ubx26L5mG4CfZ33hF63OPBOWZIlBgaxmJN/8/XBPvJx0qqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:17:12.965149Z"},"content_sha256":"002fbba924cc1f51c61f91454ea49d264bb7a5491bed9442987d743541dd3cd4","schema_version":"1.0","event_id":"sha256:002fbba924cc1f51c61f91454ea49d264bb7a5491bed9442987d743541dd3cd4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7N7K4G5NOOW7ISP2RJNQMDH6WT/bundle.json","state_url":"https://pith.science/pith/7N7K4G5NOOW7ISP2RJNQMDH6WT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7N7K4G5NOOW7ISP2RJNQMDH6WT/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":"2026-08-04T11:17:12Z","links":{"resolver":"https://pith.science/pith/7N7K4G5NOOW7ISP2RJNQMDH6WT","bundle":"https://pith.science/pith/7N7K4G5NOOW7ISP2RJNQMDH6WT/bundle.json","state":"https://pith.science/pith/7N7K4G5NOOW7ISP2RJNQMDH6WT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7N7K4G5NOOW7ISP2RJNQMDH6WT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7N7K4G5NOOW7ISP2RJNQMDH6WT","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":"004940a426688b205028f0d8c09a793893f6c66337157466edbbb84777f5cf93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T11:12:31Z","title_canon_sha256":"7e4f7b292608148a7311d216102a812c0fa3682bd4657446021b2080f0adb5c6"},"schema_version":"1.0","source":{"id":"2607.29294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29294","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29294v1","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29294","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"7N7K4G5NOOW7","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"pith_short_16","alias_value":"7N7K4G5NOOW7ISP2","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"pith_short_8","alias_value":"7N7K4G5N","created_at":"2026-08-03T01:23:58Z"}],"graph_snapshots":[{"event_id":"sha256:002fbba924cc1f51c61f91454ea49d264bb7a5491bed9442987d743541dd3cd4","target":"graph","created_at":"2026-08-03T01:23:58Z","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/2607.29294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present HBPI-UCRL, a model-based algorithm for hierarchical reinforcement learning (HRL) that learns high-level and low-level policies in parallel. HBPI-UCRL exploits the fact that a high-level transition corresponds to a multi-step transition at the low level. We introduce two conditions on the low-level dynamics that are sufficient to make parallel HRL learnable. When these conditions hold, we prove that HBPI-UCRL has a polynomial sample complexity in the problem parameters. In the sparse-reward, goal-directed setting, our sample complexity upper bound for HBPI-UCRL is strictly lower than","authors_text":"Anders Jonsson, Emilie Kaufmann, Gianmarco Tedeschi, Lorenzo Steccanella","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T11:12:31Z","title":"Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29294","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:c72aac895045674f1bceae27aed68832d9135b0c0c3a064269a16c01975ea98d","target":"record","created_at":"2026-08-03T01:23:58Z","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":"004940a426688b205028f0d8c09a793893f6c66337157466edbbb84777f5cf93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T11:12:31Z","title_canon_sha256":"7e4f7b292608148a7311d216102a812c0fa3682bd4657446021b2080f0adb5c6"},"schema_version":"1.0","source":{"id":"2607.29294","kind":"arxiv","version":1}},"canonical_sha256":"fb7eae1bad73adf449fa8a5b060cfeb4e04858f811fe580e04baab0b3b17e252","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb7eae1bad73adf449fa8a5b060cfeb4e04858f811fe580e04baab0b3b17e252","first_computed_at":"2026-08-03T01:23:58.919866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:23:58.919866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DtH1+3A/XgIV4fMDbdK7XkaAFhcFu+j02rjVuhXfA2j6MDPGnAiS1837c/NdJWJPzGosGtOdEc8yy8wfsOppBg==","signature_status":"signed_v1","signed_at":"2026-08-03T01:23:58.921665Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.29294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c72aac895045674f1bceae27aed68832d9135b0c0c3a064269a16c01975ea98d","sha256:002fbba924cc1f51c61f91454ea49d264bb7a5491bed9442987d743541dd3cd4"],"state_sha256":"c6caf9772d4426bec98ced2c2aa6e7579add980ab7d31f699349ee377a3b364b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KSVQTcO8+ucpeKxV6TzOmUiEUVTfKVWr9X6IpHQvFBBkEsPluNpptoxtTQGEPJ8ncCfnOgTnrXxQCUQo7WjiDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:17:12.969801Z","bundle_sha256":"7ea2ce102392226ff34aaa314e94e62335b4241ed5babc245d5b4293abb56967"}}