{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:P3AUEYKDAQIL37QZMX62N6QBX6","short_pith_number":"pith:P3AUEYKD","canonical_record":{"source":{"id":"1903.00606","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-02T02:17:52Z","cross_cats_sorted":[],"title_canon_sha256":"e751604b732ce688e6d93faf1028395c576d70677b969f03fdf2677779820bde","abstract_canon_sha256":"6bf20645dc9705451b7e06afa0dbb0c8bd419f8618b259f5b3ac730ba8861633"},"schema_version":"1.0"},"canonical_sha256":"7ec14261430410bdfe1965fda6fa01bfbafdf787c8758b452249d8ceadc6a1d7","source":{"kind":"arxiv","id":"1903.00606","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00606","created_at":"2026-05-17T23:51:09Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00606v2","created_at":"2026-05-17T23:51:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00606","created_at":"2026-05-17T23:51:09Z"},{"alias_kind":"pith_short_12","alias_value":"P3AUEYKDAQIL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"P3AUEYKDAQIL37QZ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"P3AUEYKD","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:P3AUEYKDAQIL37QZMX62N6QBX6","target":"record","payload":{"canonical_record":{"source":{"id":"1903.00606","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-02T02:17:52Z","cross_cats_sorted":[],"title_canon_sha256":"e751604b732ce688e6d93faf1028395c576d70677b969f03fdf2677779820bde","abstract_canon_sha256":"6bf20645dc9705451b7e06afa0dbb0c8bd419f8618b259f5b3ac730ba8861633"},"schema_version":"1.0"},"canonical_sha256":"7ec14261430410bdfe1965fda6fa01bfbafdf787c8758b452249d8ceadc6a1d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:09.310442Z","signature_b64":"yJrNtoKPuUSiI0PPeaT82be6i75dXewVCukb8xNpQK4WD+N6j9Ho6HafFa6V69hUE7RhQV6xKoTgD/zqkbhIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ec14261430410bdfe1965fda6fa01bfbafdf787c8758b452249d8ceadc6a1d7","last_reissued_at":"2026-05-17T23:51:09.309783Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:09.309783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.00606","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":"2026-05-17T23:51:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sXOeH3kx00MBnqFBTYgf6GmQNh8s57kYdJR09T0mMKifwAu79tWFf/pDjfMj+jRv7mrnIjaiQiEnXkrb57OACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T02:33:29.125109Z"},"content_sha256":"ec1b6cf0b2791c9e94bd625ad6f778778752020b24dacf5477c695c508c7f75d","schema_version":"1.0","event_id":"sha256:ec1b6cf0b2791c9e94bd625ad6f778778752020b24dacf5477c695c508c7f75d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:P3AUEYKDAQIL37QZMX62N6QBX6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discovering Options for Exploration by Minimizing Cover Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"David Abel, George Konidaris, Jee Won Park, Yuu Jinnai","submitted_at":"2019-03-02T02:17:52Z","abstract_excerpt":"One of the main challenges in reinforcement learning is solving tasks with sparse reward. We show that the difficulty of discovering a distant rewarding state in an MDP is bounded by the expected cover time of a random walk over the graph induced by the MDP's transition dynamics. We therefore propose to accelerate exploration by constructing options that minimize cover time. The proposed algorithm finds an option which provably diminishes the expected number of steps to visit every state in the state space by a uniform random walk. We show empirically that the proposed algorithm improves the l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00606","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":"2026-05-17T23:51:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xfrg8LysPY4coNZ8yXXfxOiQoTOs/0KIUKH4QSMAEGS/U7ndSvQtP7yHil3jZkPGEtBEq+kGqgK74ftLKqE+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T02:33:29.125498Z"},"content_sha256":"7feed5229357a87c839f1c3a2ae909f87954c76e6b155b1fd4cb40d6157e6526","schema_version":"1.0","event_id":"sha256:7feed5229357a87c839f1c3a2ae909f87954c76e6b155b1fd4cb40d6157e6526"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P3AUEYKDAQIL37QZMX62N6QBX6/bundle.json","state_url":"https://pith.science/pith/P3AUEYKDAQIL37QZMX62N6QBX6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P3AUEYKDAQIL37QZMX62N6QBX6/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":"2026-05-28T02:33:29Z","links":{"resolver":"https://pith.science/pith/P3AUEYKDAQIL37QZMX62N6QBX6","bundle":"https://pith.science/pith/P3AUEYKDAQIL37QZMX62N6QBX6/bundle.json","state":"https://pith.science/pith/P3AUEYKDAQIL37QZMX62N6QBX6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P3AUEYKDAQIL37QZMX62N6QBX6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:P3AUEYKDAQIL37QZMX62N6QBX6","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":"6bf20645dc9705451b7e06afa0dbb0c8bd419f8618b259f5b3ac730ba8861633","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-02T02:17:52Z","title_canon_sha256":"e751604b732ce688e6d93faf1028395c576d70677b969f03fdf2677779820bde"},"schema_version":"1.0","source":{"id":"1903.00606","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.00606","created_at":"2026-05-17T23:51:09Z"},{"alias_kind":"arxiv_version","alias_value":"1903.00606v2","created_at":"2026-05-17T23:51:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00606","created_at":"2026-05-17T23:51:09Z"},{"alias_kind":"pith_short_12","alias_value":"P3AUEYKDAQIL","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"P3AUEYKDAQIL37QZ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"P3AUEYKD","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:7feed5229357a87c839f1c3a2ae909f87954c76e6b155b1fd4cb40d6157e6526","target":"graph","created_at":"2026-05-17T23:51:09Z","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":"One of the main challenges in reinforcement learning is solving tasks with sparse reward. We show that the difficulty of discovering a distant rewarding state in an MDP is bounded by the expected cover time of a random walk over the graph induced by the MDP's transition dynamics. We therefore propose to accelerate exploration by constructing options that minimize cover time. The proposed algorithm finds an option which provably diminishes the expected number of steps to visit every state in the state space by a uniform random walk. We show empirically that the proposed algorithm improves the l","authors_text":"David Abel, George Konidaris, Jee Won Park, Yuu Jinnai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-02T02:17:52Z","title":"Discovering Options for Exploration by Minimizing Cover Time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00606","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:ec1b6cf0b2791c9e94bd625ad6f778778752020b24dacf5477c695c508c7f75d","target":"record","created_at":"2026-05-17T23:51:09Z","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":"6bf20645dc9705451b7e06afa0dbb0c8bd419f8618b259f5b3ac730ba8861633","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-02T02:17:52Z","title_canon_sha256":"e751604b732ce688e6d93faf1028395c576d70677b969f03fdf2677779820bde"},"schema_version":"1.0","source":{"id":"1903.00606","kind":"arxiv","version":2}},"canonical_sha256":"7ec14261430410bdfe1965fda6fa01bfbafdf787c8758b452249d8ceadc6a1d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ec14261430410bdfe1965fda6fa01bfbafdf787c8758b452249d8ceadc6a1d7","first_computed_at":"2026-05-17T23:51:09.309783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:09.309783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yJrNtoKPuUSiI0PPeaT82be6i75dXewVCukb8xNpQK4WD+N6j9Ho6HafFa6V69hUE7RhQV6xKoTgD/zqkbhIAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:09.310442Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.00606","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec1b6cf0b2791c9e94bd625ad6f778778752020b24dacf5477c695c508c7f75d","sha256:7feed5229357a87c839f1c3a2ae909f87954c76e6b155b1fd4cb40d6157e6526"],"state_sha256":"6b9cf2add32a584a97ee112c368b7e92af1f81f0e93174e0e23f8f024d65c0e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vHBasaX0yNjw78wWO4s+T68kEB830PMkZkQc6yEyZYTrtjEnyaXXpZ+yHsdHoB5kS/by/nCgWMSN9L6ikvNvBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T02:33:29.127542Z","bundle_sha256":"042783a07eb54c6a89598551aeb06f5e3c5c3bc17dc17167f447a6cc20342cd4"}}