{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:MQUPQDAD3BOZ5YKAJ2ZOIGURFG","short_pith_number":"pith:MQUPQDAD","canonical_record":{"source":{"id":"1611.03907","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-11T22:39:01Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7e0820f3c2e7567b370ad59a5a6ed391b914419bfc65d144529f8982c67efdf4","abstract_canon_sha256":"a1ca8e764590bb6459e17a598f8875957562209f0148683733f3b3f89f6aa792"},"schema_version":"1.0"},"canonical_sha256":"6428f80c03d85d9ee1404eb2e41a91299d9ebd2c73bca067d5d3d9baf854adaf","source":{"kind":"arxiv","id":"1611.03907","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.03907","created_at":"2026-05-18T00:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"1611.03907v4","created_at":"2026-05-18T00:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.03907","created_at":"2026-05-18T00:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"MQUPQDAD3BOZ","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MQUPQDAD3BOZ5YKA","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MQUPQDAD","created_at":"2026-05-18T12:30:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:MQUPQDAD3BOZ5YKAJ2ZOIGURFG","target":"record","payload":{"canonical_record":{"source":{"id":"1611.03907","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-11T22:39:01Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7e0820f3c2e7567b370ad59a5a6ed391b914419bfc65d144529f8982c67efdf4","abstract_canon_sha256":"a1ca8e764590bb6459e17a598f8875957562209f0148683733f3b3f89f6aa792"},"schema_version":"1.0"},"canonical_sha256":"6428f80c03d85d9ee1404eb2e41a91299d9ebd2c73bca067d5d3d9baf854adaf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:49.049348Z","signature_b64":"HMqN1NkUqRdCFfqvX/o+r9aC0NS8plEZQeRepLupi1mwxtLmXVDt02B2JcTntFPxUXlkvujd87rghox3M4uuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6428f80c03d85d9ee1404eb2e41a91299d9ebd2c73bca067d5d3d9baf854adaf","last_reissued_at":"2026-05-18T00:12:49.048730Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:49.048730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.03907","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":"2026-05-18T00:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QOV+3x8ZRu42yfnJ6NRM/bLCbBQ1V5SWiS4At4VwJiTJGPb4NGsr1PITkS3QIkYofi/Ff4ep3h+aBL2ywH96Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T12:17:39.637711Z"},"content_sha256":"502a440b196a497beed4f81879e5cc2d4fd1080f91056df46daa3ef6329ff50b","schema_version":"1.0","event_id":"sha256:502a440b196a497beed4f81879e5cc2d4fd1080f91056df46daa3ef6329ff50b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:MQUPQDAD3BOZ5YKAJ2ZOIGURFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning in Rich-Observation MDPs using Spectral Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Alessandro Lazaric, Animashree Anandkumar, Kamyar Azizzadenesheli","submitted_at":"2016-11-11T22:39:01Z","abstract_excerpt":"Reinforcement learning (RL) in Markov decision processes (MDPs) with large state spaces is a challenging problem. The performance of standard RL algorithms degrades drastically with the dimensionality of state space. However, in practice, these large MDPs typically incorporate a latent or hidden low-dimensional structure. In this paper, we study the setting of rich-observation Markov decision processes (ROMDP), where there are a small number of hidden states which possess an injective mapping to the observation states. In other words, every observation state is generated through a single hidde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.03907","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":"2026-05-18T00:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2znhjLomw6rOxuRqjrLqsVEsZtXnFIOQaK4mSW57fFWD89Mtmd4vSlx9pAblPIP3smMl0VSb4l8eJdG2DJRtAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T12:17:39.638433Z"},"content_sha256":"ce7c41c4d3a40b77abc0ffe0f5e3757e67c725556827eb610eae0e2ded93d0dc","schema_version":"1.0","event_id":"sha256:ce7c41c4d3a40b77abc0ffe0f5e3757e67c725556827eb610eae0e2ded93d0dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MQUPQDAD3BOZ5YKAJ2ZOIGURFG/bundle.json","state_url":"https://pith.science/pith/MQUPQDAD3BOZ5YKAJ2ZOIGURFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MQUPQDAD3BOZ5YKAJ2ZOIGURFG/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":"2026-05-23T12:17:39Z","links":{"resolver":"https://pith.science/pith/MQUPQDAD3BOZ5YKAJ2ZOIGURFG","bundle":"https://pith.science/pith/MQUPQDAD3BOZ5YKAJ2ZOIGURFG/bundle.json","state":"https://pith.science/pith/MQUPQDAD3BOZ5YKAJ2ZOIGURFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MQUPQDAD3BOZ5YKAJ2ZOIGURFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:MQUPQDAD3BOZ5YKAJ2ZOIGURFG","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":"a1ca8e764590bb6459e17a598f8875957562209f0148683733f3b3f89f6aa792","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-11T22:39:01Z","title_canon_sha256":"7e0820f3c2e7567b370ad59a5a6ed391b914419bfc65d144529f8982c67efdf4"},"schema_version":"1.0","source":{"id":"1611.03907","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.03907","created_at":"2026-05-18T00:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"1611.03907v4","created_at":"2026-05-18T00:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.03907","created_at":"2026-05-18T00:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"MQUPQDAD3BOZ","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MQUPQDAD3BOZ5YKA","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MQUPQDAD","created_at":"2026-05-18T12:30:32Z"}],"graph_snapshots":[{"event_id":"sha256:ce7c41c4d3a40b77abc0ffe0f5e3757e67c725556827eb610eae0e2ded93d0dc","target":"graph","created_at":"2026-05-18T00:12:49Z","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":"Reinforcement learning (RL) in Markov decision processes (MDPs) with large state spaces is a challenging problem. The performance of standard RL algorithms degrades drastically with the dimensionality of state space. However, in practice, these large MDPs typically incorporate a latent or hidden low-dimensional structure. In this paper, we study the setting of rich-observation Markov decision processes (ROMDP), where there are a small number of hidden states which possess an injective mapping to the observation states. In other words, every observation state is generated through a single hidde","authors_text":"Alessandro Lazaric, Animashree Anandkumar, Kamyar Azizzadenesheli","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-11T22:39:01Z","title":"Reinforcement Learning in Rich-Observation MDPs using Spectral Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.03907","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":"sha256:502a440b196a497beed4f81879e5cc2d4fd1080f91056df46daa3ef6329ff50b","target":"record","created_at":"2026-05-18T00:12:49Z","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":"a1ca8e764590bb6459e17a598f8875957562209f0148683733f3b3f89f6aa792","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-11T22:39:01Z","title_canon_sha256":"7e0820f3c2e7567b370ad59a5a6ed391b914419bfc65d144529f8982c67efdf4"},"schema_version":"1.0","source":{"id":"1611.03907","kind":"arxiv","version":4}},"canonical_sha256":"6428f80c03d85d9ee1404eb2e41a91299d9ebd2c73bca067d5d3d9baf854adaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6428f80c03d85d9ee1404eb2e41a91299d9ebd2c73bca067d5d3d9baf854adaf","first_computed_at":"2026-05-18T00:12:49.048730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:49.048730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HMqN1NkUqRdCFfqvX/o+r9aC0NS8plEZQeRepLupi1mwxtLmXVDt02B2JcTntFPxUXlkvujd87rghox3M4uuDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:49.049348Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.03907","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:502a440b196a497beed4f81879e5cc2d4fd1080f91056df46daa3ef6329ff50b","sha256:ce7c41c4d3a40b77abc0ffe0f5e3757e67c725556827eb610eae0e2ded93d0dc"],"state_sha256":"dfb27a2529a201ac88cded1ac71d560ed84a9d2665cf104ba6269bb713f8c82a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RNyW/VWzzCE2/yKPqVP0m9cZYJXO9h8yxLGb0vNTy20vV64sT8dzIbSr6ctsHQkHP/O0BoeGe9NUg3OG/NekCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T12:17:39.642130Z","bundle_sha256":"fac8dd16dfeb858eb397cf048804a93838be96f557315dff87c4f80c921b547a"}}