{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DIS7JSXN2KNQMC2QTAHS63MDAK","short_pith_number":"pith:DIS7JSXN","canonical_record":{"source":{"id":"1812.01487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:30:23Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"26a3d0deeed1a157f93ae79bc3a031bb6dd978f86e4bf0f430fbd02c4aad4f83","abstract_canon_sha256":"6521c736e7d25b2150b5cd79ba36e5c5c13d324d0bc4f61dc3c541c7e80d2815"},"schema_version":"1.0"},"canonical_sha256":"1a25f4caedd29b060b50980f2f6d8302bef75474c43009ca7cc42b32a0959470","source":{"kind":"arxiv","id":"1812.01487","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.01487","created_at":"2026-05-17T23:53:49Z"},{"alias_kind":"arxiv_version","alias_value":"1812.01487v2","created_at":"2026-05-17T23:53:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01487","created_at":"2026-05-17T23:53:49Z"},{"alias_kind":"pith_short_12","alias_value":"DIS7JSXN2KNQ","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DIS7JSXN2KNQMC2Q","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DIS7JSXN","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DIS7JSXN2KNQMC2QTAHS63MDAK","target":"record","payload":{"canonical_record":{"source":{"id":"1812.01487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:30:23Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"26a3d0deeed1a157f93ae79bc3a031bb6dd978f86e4bf0f430fbd02c4aad4f83","abstract_canon_sha256":"6521c736e7d25b2150b5cd79ba36e5c5c13d324d0bc4f61dc3c541c7e80d2815"},"schema_version":"1.0"},"canonical_sha256":"1a25f4caedd29b060b50980f2f6d8302bef75474c43009ca7cc42b32a0959470","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:49.966484Z","signature_b64":"R6742h+5wx35vW4e83zYXLG8rsW0iDWQ6sHM7YUWmOvrDlAwSuJbbZeD/A0gGPLRreGAMWEySv8h6z4n+o4BDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a25f4caedd29b060b50980f2f6d8302bef75474c43009ca7cc42b32a0959470","last_reissued_at":"2026-05-17T23:53:49.965848Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:49.965848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.01487","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":"2026-05-17T23:53:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uipLAevSnyJa84gZdg9lvL9ayX2Gnkj23sbws9X9hojsGsbVxk2CTUVsQeCxKXmlrNx72ewppcSCCOo8ZN1WBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T15:04:25.310066Z"},"content_sha256":"50c065c286be74f6947512ee4ab9ee5a6d4c334b6762c008e9763c5a57c36fdd","schema_version":"1.0","event_id":"sha256:50c065c286be74f6947512ee4ab9ee5a6d4c334b6762c008e9763c5a57c36fdd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DIS7JSXN2KNQMC2QTAHS63MDAK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hyperbolic Embeddings for Learning Options in Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"M. Prannoy, Saket Tiwari","submitted_at":"2018-12-04T15:30:23Z","abstract_excerpt":"Hierarchical reinforcement learning deals with the problem of breaking down large tasks into meaningful sub-tasks. Autonomous discovery of these sub-tasks has remained a challenging problem. We propose a novel method of learning sub-tasks by combining paradigms of routing in computer networks and graph based skill discovery within the options framework to define meaningful sub-goals. We apply the recent advancements of learning embeddings using Riemannian optimisation in the hyperbolic space to embed the state set into the hyperbolic space and create a model of the environment. In doing so we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01487","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":""},"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":"2026-05-17T23:53:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ep3C3kUsnnYrqN4WI6QiEh1clPwa6Zxzb4DZ25yHe6w1tQKgVjyA7OGUZxoaO9jaTdkI0p7iYUmlaFgrBkEDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T15:04:25.310786Z"},"content_sha256":"218278dbcf467a5878246612424c1c8424c8434a42d186c05e40ea5e6e33e278","schema_version":"1.0","event_id":"sha256:218278dbcf467a5878246612424c1c8424c8434a42d186c05e40ea5e6e33e278"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DIS7JSXN2KNQMC2QTAHS63MDAK/bundle.json","state_url":"https://pith.science/pith/DIS7JSXN2KNQMC2QTAHS63MDAK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DIS7JSXN2KNQMC2QTAHS63MDAK/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":"2026-06-06T15:04:25Z","links":{"resolver":"https://pith.science/pith/DIS7JSXN2KNQMC2QTAHS63MDAK","bundle":"https://pith.science/pith/DIS7JSXN2KNQMC2QTAHS63MDAK/bundle.json","state":"https://pith.science/pith/DIS7JSXN2KNQMC2QTAHS63MDAK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DIS7JSXN2KNQMC2QTAHS63MDAK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DIS7JSXN2KNQMC2QTAHS63MDAK","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":"6521c736e7d25b2150b5cd79ba36e5c5c13d324d0bc4f61dc3c541c7e80d2815","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:30:23Z","title_canon_sha256":"26a3d0deeed1a157f93ae79bc3a031bb6dd978f86e4bf0f430fbd02c4aad4f83"},"schema_version":"1.0","source":{"id":"1812.01487","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.01487","created_at":"2026-05-17T23:53:49Z"},{"alias_kind":"arxiv_version","alias_value":"1812.01487v2","created_at":"2026-05-17T23:53:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01487","created_at":"2026-05-17T23:53:49Z"},{"alias_kind":"pith_short_12","alias_value":"DIS7JSXN2KNQ","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DIS7JSXN2KNQMC2Q","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DIS7JSXN","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:218278dbcf467a5878246612424c1c8424c8434a42d186c05e40ea5e6e33e278","target":"graph","created_at":"2026-05-17T23:53:49Z","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"},"paper":{"abstract_excerpt":"Hierarchical reinforcement learning deals with the problem of breaking down large tasks into meaningful sub-tasks. Autonomous discovery of these sub-tasks has remained a challenging problem. We propose a novel method of learning sub-tasks by combining paradigms of routing in computer networks and graph based skill discovery within the options framework to define meaningful sub-goals. We apply the recent advancements of learning embeddings using Riemannian optimisation in the hyperbolic space to embed the state set into the hyperbolic space and create a model of the environment. In doing so we ","authors_text":"M. Prannoy, Saket Tiwari","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:30:23Z","title":"Hyperbolic Embeddings for Learning Options in Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01487","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":"sha256:50c065c286be74f6947512ee4ab9ee5a6d4c334b6762c008e9763c5a57c36fdd","target":"record","created_at":"2026-05-17T23:53:49Z","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":"6521c736e7d25b2150b5cd79ba36e5c5c13d324d0bc4f61dc3c541c7e80d2815","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:30:23Z","title_canon_sha256":"26a3d0deeed1a157f93ae79bc3a031bb6dd978f86e4bf0f430fbd02c4aad4f83"},"schema_version":"1.0","source":{"id":"1812.01487","kind":"arxiv","version":2}},"canonical_sha256":"1a25f4caedd29b060b50980f2f6d8302bef75474c43009ca7cc42b32a0959470","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a25f4caedd29b060b50980f2f6d8302bef75474c43009ca7cc42b32a0959470","first_computed_at":"2026-05-17T23:53:49.965848Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:49.965848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R6742h+5wx35vW4e83zYXLG8rsW0iDWQ6sHM7YUWmOvrDlAwSuJbbZeD/A0gGPLRreGAMWEySv8h6z4n+o4BDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:49.966484Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.01487","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50c065c286be74f6947512ee4ab9ee5a6d4c334b6762c008e9763c5a57c36fdd","sha256:218278dbcf467a5878246612424c1c8424c8434a42d186c05e40ea5e6e33e278"],"state_sha256":"d55c47161a4fcefdf5c3a81c2ec306e68bc8452debbc855029a56a8b86b7c2ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HGOpT35TwuJXttAoup5zOphmll3Q6Jx/u4QCLq9F2B8r3tBQLt1NQvHztMK2MpTVlWm3XShovv4FweVyLKj8Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T15:04:25.314278Z","bundle_sha256":"688b8153712dc0f68adf3feeaff20bee5d2f026252de0fb70e30faa3001c56e0"}}