{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SMHGVMY2JOJTCIJHE4UF2N7V6O","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":"5c4daad012820149bac36e02d389f8e3e3096f80c075138c73c382ca66d12e36","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T16:03:34Z","title_canon_sha256":"9bc0818df9ff6e27e5603d1251eeaf295257a97a2b935a87a1a1151225731fdb"},"schema_version":"1.0","source":{"id":"2607.19232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19232","created_at":"2026-07-22T01:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19232v1","created_at":"2026-07-22T01:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19232","created_at":"2026-07-22T01:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"SMHGVMY2JOJT","created_at":"2026-07-22T01:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"SMHGVMY2JOJTCIJH","created_at":"2026-07-22T01:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"SMHGVMY2","created_at":"2026-07-22T01:24:15Z"}],"graph_snapshots":[{"event_id":"sha256:8719f959179f21dcba4fc8cf9c276054c43478449207cf2c723170e8de615db3","target":"graph","created_at":"2026-07-22T01:24:15Z","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/2607.19232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical Reinforcement Learning (HRL) intends to separate strategic planning from primitive execution. It has been widely successful in solving long-horizon and complex tasks, where flat-RL algorithms have difficulty in learning. However, while the low-level agent in HRL benefits from dense feedback and abundant trial opportunities, the high-level agent receives sparse, delayed feedback from the environment and its performance depends on the low-level execution capability. In this paper, we study whether subgoal selection by the high-level agent can be performed more strategically, by prov","authors_text":"Kshitij Jerath, Kshitij Kumar Srivastava","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T16:03:34Z","title":"S3: Stable Subgoal Selection by Constraining Uncertainty of Coarse Dynamics in Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19232","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":"sha256:00f36ad8715c79df000311fb2e656efe676fd9bb33abdc2e1b3af119ad074c5a","target":"record","created_at":"2026-07-22T01:24:15Z","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":"5c4daad012820149bac36e02d389f8e3e3096f80c075138c73c382ca66d12e36","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T16:03:34Z","title_canon_sha256":"9bc0818df9ff6e27e5603d1251eeaf295257a97a2b935a87a1a1151225731fdb"},"schema_version":"1.0","source":{"id":"2607.19232","kind":"arxiv","version":1}},"canonical_sha256":"930e6ab31a4b9331212727285d37f5f3b1ae9d6858fada7a5411dbdcd44231c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"930e6ab31a4b9331212727285d37f5f3b1ae9d6858fada7a5411dbdcd44231c5","first_computed_at":"2026-07-22T01:24:15.552100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:24:15.552100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4lKXJyFod3RmXd4t4AtixEdXKLHpIz0VBTv81sJrMyTA8mS+6+/qrrkhZT5F++8630ZDnFs0ZimaP0br3MkJBg==","signature_status":"signed_v1","signed_at":"2026-07-22T01:24:15.552915Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00f36ad8715c79df000311fb2e656efe676fd9bb33abdc2e1b3af119ad074c5a","sha256:8719f959179f21dcba4fc8cf9c276054c43478449207cf2c723170e8de615db3"],"state_sha256":"dae7d0ab7bdcba21707d8bfc311f62b5a64f4b4fe421e28dceca8746ea212c41"}