{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NKIPCMWVC6EOG2H42K42G53IR5","short_pith_number":"pith:NKIPCMWV","canonical_record":{"source":{"id":"2212.12786","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-12-24T17:21:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d9226deb589650d0b25ca2635ef22c1202bc237c8cebf5d5b1b3d2bf02f43d4e","abstract_canon_sha256":"f438b0ebad19187a2e795cb7d3ffa14cba839c0d1720d5c61a7301fe477fa4ed"},"schema_version":"1.0"},"canonical_sha256":"6a90f132d51788e368fcd2b9a377688f45f71a1e55e38a7e110482730cc2d966","source":{"kind":"arxiv","id":"2212.12786","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.12786","created_at":"2026-07-05T05:28:13Z"},{"alias_kind":"arxiv_version","alias_value":"2212.12786v1","created_at":"2026-07-05T05:28:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.12786","created_at":"2026-07-05T05:28:13Z"},{"alias_kind":"pith_short_12","alias_value":"NKIPCMWVC6EO","created_at":"2026-07-05T05:28:13Z"},{"alias_kind":"pith_short_16","alias_value":"NKIPCMWVC6EOG2H4","created_at":"2026-07-05T05:28:13Z"},{"alias_kind":"pith_short_8","alias_value":"NKIPCMWV","created_at":"2026-07-05T05:28:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NKIPCMWVC6EOG2H42K42G53IR5","target":"record","payload":{"canonical_record":{"source":{"id":"2212.12786","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-12-24T17:21:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d9226deb589650d0b25ca2635ef22c1202bc237c8cebf5d5b1b3d2bf02f43d4e","abstract_canon_sha256":"f438b0ebad19187a2e795cb7d3ffa14cba839c0d1720d5c61a7301fe477fa4ed"},"schema_version":"1.0"},"canonical_sha256":"6a90f132d51788e368fcd2b9a377688f45f71a1e55e38a7e110482730cc2d966","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:13.260974Z","signature_b64":"TOY6lvWBaGn60lfy1PUVY82QTXRdLxi6ZPCYVnuklxvOkOg5dTmuwnvEKVHqzVCqxzw8z4JTIVSbqScrEpKMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a90f132d51788e368fcd2b9a377688f45f71a1e55e38a7e110482730cc2d966","last_reissued_at":"2026-07-05T05:28:13.260558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:13.260558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.12786","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":"2026-07-05T05:28:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8clOMYntAXBAxCzGfLRxnnhxTB4P13jSwVkBXXxQ2t1YXyf7yMy41TR7GN3PeK/XL2iGUiBP5eTOuziQ56/cAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:53:19.641684Z"},"content_sha256":"2990c022b90270c9f4ca5763a5f29770f052774f9fb85bb0f807f848f5509281","schema_version":"1.0","event_id":"sha256:2990c022b90270c9f4ca5763a5f29770f052774f9fb85bb0f807f848f5509281"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NKIPCMWVC6EOG2H42K42G53IR5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SHIRO: Soft Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Kandai Watanabe, Mathew Strong, Omer Eldar","submitted_at":"2022-12-24T17:21:58Z","abstract_excerpt":"Hierarchical Reinforcement Learning (HRL) algorithms have been demonstrated to perform well on high-dimensional decision making and robotic control tasks. However, because they solely optimize for rewards, the agent tends to search the same space redundantly. This problem reduces the speed of learning and achieved reward. In this work, we present an Off-Policy HRL algorithm that maximizes entropy for efficient exploration. The algorithm learns a temporally abstracted low-level policy and is able to explore broadly through the addition of entropy to the high-level. The novelty of this work is t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.12786","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/2212.12786/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":"2026-07-05T05:28:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"067kxbvISDiKxlyYpXzb+IvqAsxlLaZ9VmXFqc8Xc4hriae9uw+gMMgsOS3Xdan+ZDB/Ln13cy5YAh4rPSqGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:53:19.642356Z"},"content_sha256":"e797621f3eeed7c184ac8accb444e22f55bc0d6b1c215754f721430c21f46047","schema_version":"1.0","event_id":"sha256:e797621f3eeed7c184ac8accb444e22f55bc0d6b1c215754f721430c21f46047"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NKIPCMWVC6EOG2H42K42G53IR5/bundle.json","state_url":"https://pith.science/pith/NKIPCMWVC6EOG2H42K42G53IR5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NKIPCMWVC6EOG2H42K42G53IR5/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":"2026-08-05T12:53:19Z","links":{"resolver":"https://pith.science/pith/NKIPCMWVC6EOG2H42K42G53IR5","bundle":"https://pith.science/pith/NKIPCMWVC6EOG2H42K42G53IR5/bundle.json","state":"https://pith.science/pith/NKIPCMWVC6EOG2H42K42G53IR5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NKIPCMWVC6EOG2H42K42G53IR5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NKIPCMWVC6EOG2H42K42G53IR5","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":"f438b0ebad19187a2e795cb7d3ffa14cba839c0d1720d5c61a7301fe477fa4ed","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-12-24T17:21:58Z","title_canon_sha256":"d9226deb589650d0b25ca2635ef22c1202bc237c8cebf5d5b1b3d2bf02f43d4e"},"schema_version":"1.0","source":{"id":"2212.12786","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.12786","created_at":"2026-07-05T05:28:13Z"},{"alias_kind":"arxiv_version","alias_value":"2212.12786v1","created_at":"2026-07-05T05:28:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.12786","created_at":"2026-07-05T05:28:13Z"},{"alias_kind":"pith_short_12","alias_value":"NKIPCMWVC6EO","created_at":"2026-07-05T05:28:13Z"},{"alias_kind":"pith_short_16","alias_value":"NKIPCMWVC6EOG2H4","created_at":"2026-07-05T05:28:13Z"},{"alias_kind":"pith_short_8","alias_value":"NKIPCMWV","created_at":"2026-07-05T05:28:13Z"}],"graph_snapshots":[{"event_id":"sha256:e797621f3eeed7c184ac8accb444e22f55bc0d6b1c215754f721430c21f46047","target":"graph","created_at":"2026-07-05T05:28:13Z","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/2212.12786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical Reinforcement Learning (HRL) algorithms have been demonstrated to perform well on high-dimensional decision making and robotic control tasks. However, because they solely optimize for rewards, the agent tends to search the same space redundantly. This problem reduces the speed of learning and achieved reward. In this work, we present an Off-Policy HRL algorithm that maximizes entropy for efficient exploration. The algorithm learns a temporally abstracted low-level policy and is able to explore broadly through the addition of entropy to the high-level. The novelty of this work is t","authors_text":"Kandai Watanabe, Mathew Strong, Omer Eldar","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-12-24T17:21:58Z","title":"SHIRO: Soft Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.12786","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":"sha256:2990c022b90270c9f4ca5763a5f29770f052774f9fb85bb0f807f848f5509281","target":"record","created_at":"2026-07-05T05:28:13Z","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":"f438b0ebad19187a2e795cb7d3ffa14cba839c0d1720d5c61a7301fe477fa4ed","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-12-24T17:21:58Z","title_canon_sha256":"d9226deb589650d0b25ca2635ef22c1202bc237c8cebf5d5b1b3d2bf02f43d4e"},"schema_version":"1.0","source":{"id":"2212.12786","kind":"arxiv","version":1}},"canonical_sha256":"6a90f132d51788e368fcd2b9a377688f45f71a1e55e38a7e110482730cc2d966","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a90f132d51788e368fcd2b9a377688f45f71a1e55e38a7e110482730cc2d966","first_computed_at":"2026-07-05T05:28:13.260558Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:28:13.260558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TOY6lvWBaGn60lfy1PUVY82QTXRdLxi6ZPCYVnuklxvOkOg5dTmuwnvEKVHqzVCqxzw8z4JTIVSbqScrEpKMBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:28:13.260974Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.12786","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2990c022b90270c9f4ca5763a5f29770f052774f9fb85bb0f807f848f5509281","sha256:e797621f3eeed7c184ac8accb444e22f55bc0d6b1c215754f721430c21f46047"],"state_sha256":"d74211cfceeb3e4745a241315f5a68c4cec6399fdeb81f750e843f2f6ff13cd4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h+k7lp1eMOXhbILjlCRNLkkJMsK6RobTe+poRDGnVcxKdimoQXgTGZnfaraNl8b6Mpa6IU4MLlDiQq676GJJCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:53:19.649083Z","bundle_sha256":"a7d7075916b28f7be50120c85ec747f6db4af774b8a8a169bb1760be793f8869"}}