{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:H65HPER5RC6AS5UJ7LF4K7PRN6","short_pith_number":"pith:H65HPER5","canonical_record":{"source":{"id":"1803.00606","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-01T20:08:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bcbc17206465ebf0c07f85f31473a1218a378610f19538f7d7f3af7a59dea247","abstract_canon_sha256":"1c41eff31933f18a38c77c80e4f832bae4879152d8794f3f212b3a2e3e195c88"},"schema_version":"1.0"},"canonical_sha256":"3fba77923d88bc097689facbc57df16fa222d1521440617b3a452a895ed1a65f","source":{"kind":"arxiv","id":"1803.00606","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.00606","created_at":"2026-05-17T23:56:10Z"},{"alias_kind":"arxiv_version","alias_value":"1803.00606v4","created_at":"2026-05-17T23:56:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00606","created_at":"2026-05-17T23:56:10Z"},{"alias_kind":"pith_short_12","alias_value":"H65HPER5RC6A","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H65HPER5RC6AS5UJ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H65HPER5","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:H65HPER5RC6AS5UJ7LF4K7PRN6","target":"record","payload":{"canonical_record":{"source":{"id":"1803.00606","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-01T20:08:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bcbc17206465ebf0c07f85f31473a1218a378610f19538f7d7f3af7a59dea247","abstract_canon_sha256":"1c41eff31933f18a38c77c80e4f832bae4879152d8794f3f212b3a2e3e195c88"},"schema_version":"1.0"},"canonical_sha256":"3fba77923d88bc097689facbc57df16fa222d1521440617b3a452a895ed1a65f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:10.297168Z","signature_b64":"yZpLmnDhphlsa3ijRcVPXKxK9BfBfaWBZH2fHChlWtrRL4aUmKXKqIxwi6LfmrCFGNo+n2v9DxN/6M+L5jHzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fba77923d88bc097689facbc57df16fa222d1521440617b3a452a895ed1a65f","last_reissued_at":"2026-05-17T23:56:10.296489Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:10.296489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.00606","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vbS2oN4am/4l6xcZ43Ka4t127285bWvuN6H66+Xef5KcwyHey23uHEyIDA1QbSFtaxJAKUVGli7VuLb1sMrQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:44:26.659456Z"},"content_sha256":"122cfabe825fc80c2487532582f43cc2db0e01d073283e19c49521f6a76a5fbf","schema_version":"1.0","event_id":"sha256:122cfabe825fc80c2487532582f43cc2db0e01d073283e19c49521f6a76a5fbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:H65HPER5RC6AS5UJ7LF4K7PRN6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Oracle-Efficient PAC RL with Rich Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Alekh Agarwal, Christoph Dann, John Langford, Nan Jiang, Robert E. Schapire","submitted_at":"2018-03-01T20:08:06Z","abstract_excerpt":"We study the computational tractability of PAC reinforcement learning with rich observations. We present new provably sample-efficient algorithms for environments with deterministic hidden state dynamics and stochastic rich observations. These methods operate in an oracle model of computation -- accessing policy and value function classes exclusively through standard optimization primitives -- and therefore represent computationally efficient alternatives to prior algorithms that require enumeration. With stochastic hidden state dynamics, we prove that the only known sample-efficient algorithm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00606","kind":"arxiv","version":4},"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":"2026-05-17T23:56:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qc0KUzgLTc09NlwlPRRGkRemV6e4oLa5m30Tok8+KFMbx9zNzJV9oMnsUyoSe9Zfbrsm57dUzuj9ZuOgCP6nDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T20:44:26.660194Z"},"content_sha256":"3ffad65c528564161a0b6e1175221e2f75b9d6724d44bea7df160ca6b808790b","schema_version":"1.0","event_id":"sha256:3ffad65c528564161a0b6e1175221e2f75b9d6724d44bea7df160ca6b808790b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H65HPER5RC6AS5UJ7LF4K7PRN6/bundle.json","state_url":"https://pith.science/pith/H65HPER5RC6AS5UJ7LF4K7PRN6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H65HPER5RC6AS5UJ7LF4K7PRN6/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":"2026-05-26T20:44:26Z","links":{"resolver":"https://pith.science/pith/H65HPER5RC6AS5UJ7LF4K7PRN6","bundle":"https://pith.science/pith/H65HPER5RC6AS5UJ7LF4K7PRN6/bundle.json","state":"https://pith.science/pith/H65HPER5RC6AS5UJ7LF4K7PRN6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H65HPER5RC6AS5UJ7LF4K7PRN6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:H65HPER5RC6AS5UJ7LF4K7PRN6","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":"1c41eff31933f18a38c77c80e4f832bae4879152d8794f3f212b3a2e3e195c88","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-01T20:08:06Z","title_canon_sha256":"bcbc17206465ebf0c07f85f31473a1218a378610f19538f7d7f3af7a59dea247"},"schema_version":"1.0","source":{"id":"1803.00606","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.00606","created_at":"2026-05-17T23:56:10Z"},{"alias_kind":"arxiv_version","alias_value":"1803.00606v4","created_at":"2026-05-17T23:56:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00606","created_at":"2026-05-17T23:56:10Z"},{"alias_kind":"pith_short_12","alias_value":"H65HPER5RC6A","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"H65HPER5RC6AS5UJ","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"H65HPER5","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:3ffad65c528564161a0b6e1175221e2f75b9d6724d44bea7df160ca6b808790b","target":"graph","created_at":"2026-05-17T23:56:10Z","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":"We study the computational tractability of PAC reinforcement learning with rich observations. We present new provably sample-efficient algorithms for environments with deterministic hidden state dynamics and stochastic rich observations. These methods operate in an oracle model of computation -- accessing policy and value function classes exclusively through standard optimization primitives -- and therefore represent computationally efficient alternatives to prior algorithms that require enumeration. With stochastic hidden state dynamics, we prove that the only known sample-efficient algorithm","authors_text":"Akshay Krishnamurthy, Alekh Agarwal, Christoph Dann, John Langford, Nan Jiang, Robert E. Schapire","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-01T20:08:06Z","title":"On Oracle-Efficient PAC RL with Rich Observations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00606","kind":"arxiv","version":4},"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":"sha256:122cfabe825fc80c2487532582f43cc2db0e01d073283e19c49521f6a76a5fbf","target":"record","created_at":"2026-05-17T23:56:10Z","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":"1c41eff31933f18a38c77c80e4f832bae4879152d8794f3f212b3a2e3e195c88","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-01T20:08:06Z","title_canon_sha256":"bcbc17206465ebf0c07f85f31473a1218a378610f19538f7d7f3af7a59dea247"},"schema_version":"1.0","source":{"id":"1803.00606","kind":"arxiv","version":4}},"canonical_sha256":"3fba77923d88bc097689facbc57df16fa222d1521440617b3a452a895ed1a65f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fba77923d88bc097689facbc57df16fa222d1521440617b3a452a895ed1a65f","first_computed_at":"2026-05-17T23:56:10.296489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:10.296489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yZpLmnDhphlsa3ijRcVPXKxK9BfBfaWBZH2fHChlWtrRL4aUmKXKqIxwi6LfmrCFGNo+n2v9DxN/6M+L5jHzAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:10.297168Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.00606","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:122cfabe825fc80c2487532582f43cc2db0e01d073283e19c49521f6a76a5fbf","sha256:3ffad65c528564161a0b6e1175221e2f75b9d6724d44bea7df160ca6b808790b"],"state_sha256":"0d470dd8d5de9f57f936a05295f880e1c3c68d1f5633887f1f60d893c96bd0ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jfwGvtqtzeZTDkZCZue3pTKHZaezZXPQz1LKsJTrUZsuyww0zLtZqYHPXtNA+iaCyE43OBczhzzYVt4vWJnJBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T20:44:26.663865Z","bundle_sha256":"61d4c537eb1fca8387f97bc5582fcb8312150b000168f15407949dcea662bd71"}}