{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:LWZLCVZSIL4LCIYU5ZNMM7O4T2","short_pith_number":"pith:LWZLCVZS","canonical_record":{"source":{"id":"1602.07764","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-02-25T01:25:36Z","cross_cats_sorted":["cs.LG","cs.NA","math.OC","stat.ML"],"title_canon_sha256":"eea3d70a1d3e8a2f297aaae292698ddc671a218a0b4121a907ee06ea79076b1f","abstract_canon_sha256":"1a0a7b71b474b43794041e0cfa815d89536fa3152de2f8abe31642b7a1d7522a"},"schema_version":"1.0"},"canonical_sha256":"5db2b1573242f8b12314ee5ac67ddc9e9e602b8cb5d310a11d095cd6e8d91c9d","source":{"kind":"arxiv","id":"1602.07764","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.07764","created_at":"2026-05-18T00:42:13Z"},{"alias_kind":"arxiv_version","alias_value":"1602.07764v2","created_at":"2026-05-18T00:42:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.07764","created_at":"2026-05-18T00:42:13Z"},{"alias_kind":"pith_short_12","alias_value":"LWZLCVZSIL4L","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"LWZLCVZSIL4LCIYU","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"LWZLCVZS","created_at":"2026-05-18T12:30:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:LWZLCVZSIL4LCIYU5ZNMM7O4T2","target":"record","payload":{"canonical_record":{"source":{"id":"1602.07764","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-02-25T01:25:36Z","cross_cats_sorted":["cs.LG","cs.NA","math.OC","stat.ML"],"title_canon_sha256":"eea3d70a1d3e8a2f297aaae292698ddc671a218a0b4121a907ee06ea79076b1f","abstract_canon_sha256":"1a0a7b71b474b43794041e0cfa815d89536fa3152de2f8abe31642b7a1d7522a"},"schema_version":"1.0"},"canonical_sha256":"5db2b1573242f8b12314ee5ac67ddc9e9e602b8cb5d310a11d095cd6e8d91c9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:13.263713Z","signature_b64":"nG8j7/9ZEEaaVPmyQA1G2QVS0Cq4hfMYhoRSbZ66Hj0nKGMEDXYivrhH4GYDMDkFvRwVLeuF5sUikFgKy67xCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5db2b1573242f8b12314ee5ac67ddc9e9e602b8cb5d310a11d095cd6e8d91c9d","last_reissued_at":"2026-05-18T00:42:13.262946Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:13.262946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.07764","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":"2026-05-18T00:42:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+duqITqHf+TeVw1OIWHlWnJQsK8wPnA9LAp/LXFLwkhKMvrEsy9O9Za/Pir6HxLreaACXK7sJqLQsYA+OCDFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T17:32:31.500739Z"},"content_sha256":"43f6416d9fb4e188d848f9212d578cc0f831eb7a717dfab2bfa9f793bc5deea5","schema_version":"1.0","event_id":"sha256:43f6416d9fb4e188d848f9212d578cc0f831eb7a717dfab2bfa9f793bc5deea5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:LWZLCVZSIL4LCIYU5ZNMM7O4T2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning of POMDPs using Spectral Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.OC","stat.ML"],"primary_cat":"cs.AI","authors_text":"Alessandro Lazaric, Animashree Anandkumar, Kamyar Azizzadenesheli","submitted_at":"2016-02-25T01:25:36Z","abstract_excerpt":"We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive) latent variable models such as hidden Markov models, POMDPs are more challenging since the learner interacts with the environment and possibly changes the future observations in the process. We devise a learning algorithm running through episodes, in each episode we employ spectral techniques to learn the POMDP parameters from a trajectory generated by a fix"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.07764","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":"2026-05-18T00:42:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F0eEtVRGO+JrOz5vob8Fe90XOGBUxYc30jbOmATjSP29QEGF8p0THy9MqRGBf4vvCbXKBex58xyY7H9tS/iHBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-18T17:32:31.501080Z"},"content_sha256":"3074349d8194cac60aaa70c04f48f5ad843ff4541ff888bbddd1ee016a4262db","schema_version":"1.0","event_id":"sha256:3074349d8194cac60aaa70c04f48f5ad843ff4541ff888bbddd1ee016a4262db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LWZLCVZSIL4LCIYU5ZNMM7O4T2/bundle.json","state_url":"https://pith.science/pith/LWZLCVZSIL4LCIYU5ZNMM7O4T2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LWZLCVZSIL4LCIYU5ZNMM7O4T2/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":"2026-07-18T17:32:31Z","links":{"resolver":"https://pith.science/pith/LWZLCVZSIL4LCIYU5ZNMM7O4T2","bundle":"https://pith.science/pith/LWZLCVZSIL4LCIYU5ZNMM7O4T2/bundle.json","state":"https://pith.science/pith/LWZLCVZSIL4LCIYU5ZNMM7O4T2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LWZLCVZSIL4LCIYU5ZNMM7O4T2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:LWZLCVZSIL4LCIYU5ZNMM7O4T2","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":"1a0a7b71b474b43794041e0cfa815d89536fa3152de2f8abe31642b7a1d7522a","cross_cats_sorted":["cs.LG","cs.NA","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-02-25T01:25:36Z","title_canon_sha256":"eea3d70a1d3e8a2f297aaae292698ddc671a218a0b4121a907ee06ea79076b1f"},"schema_version":"1.0","source":{"id":"1602.07764","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.07764","created_at":"2026-05-18T00:42:13Z"},{"alias_kind":"arxiv_version","alias_value":"1602.07764v2","created_at":"2026-05-18T00:42:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.07764","created_at":"2026-05-18T00:42:13Z"},{"alias_kind":"pith_short_12","alias_value":"LWZLCVZSIL4L","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"LWZLCVZSIL4LCIYU","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"LWZLCVZS","created_at":"2026-05-18T12:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:3074349d8194cac60aaa70c04f48f5ad843ff4541ff888bbddd1ee016a4262db","target":"graph","created_at":"2026-05-18T00:42:13Z","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"},"paper":{"abstract_excerpt":"We propose a new reinforcement learning algorithm for partially observable Markov decision processes (POMDP) based on spectral decomposition methods. While spectral methods have been previously employed for consistent learning of (passive) latent variable models such as hidden Markov models, POMDPs are more challenging since the learner interacts with the environment and possibly changes the future observations in the process. We devise a learning algorithm running through episodes, in each episode we employ spectral techniques to learn the POMDP parameters from a trajectory generated by a fix","authors_text":"Alessandro Lazaric, Animashree Anandkumar, Kamyar Azizzadenesheli","cross_cats":["cs.LG","cs.NA","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-02-25T01:25:36Z","title":"Reinforcement Learning of POMDPs using Spectral Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.07764","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":"sha256:43f6416d9fb4e188d848f9212d578cc0f831eb7a717dfab2bfa9f793bc5deea5","target":"record","created_at":"2026-05-18T00:42:13Z","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":"1a0a7b71b474b43794041e0cfa815d89536fa3152de2f8abe31642b7a1d7522a","cross_cats_sorted":["cs.LG","cs.NA","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-02-25T01:25:36Z","title_canon_sha256":"eea3d70a1d3e8a2f297aaae292698ddc671a218a0b4121a907ee06ea79076b1f"},"schema_version":"1.0","source":{"id":"1602.07764","kind":"arxiv","version":2}},"canonical_sha256":"5db2b1573242f8b12314ee5ac67ddc9e9e602b8cb5d310a11d095cd6e8d91c9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5db2b1573242f8b12314ee5ac67ddc9e9e602b8cb5d310a11d095cd6e8d91c9d","first_computed_at":"2026-05-18T00:42:13.262946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:13.262946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nG8j7/9ZEEaaVPmyQA1G2QVS0Cq4hfMYhoRSbZ66Hj0nKGMEDXYivrhH4GYDMDkFvRwVLeuF5sUikFgKy67xCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:13.263713Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.07764","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43f6416d9fb4e188d848f9212d578cc0f831eb7a717dfab2bfa9f793bc5deea5","sha256:3074349d8194cac60aaa70c04f48f5ad843ff4541ff888bbddd1ee016a4262db"],"state_sha256":"d6cad4e821535595108f7b48cc0c8858656a05e321535bb6499b7eca191c5934"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NFCXEmBs6PT4rhV7klkkgVX3WhlHeV9DA8NPkqzg+kxllUh/nBeAnYrW0oAhVQlNCUMewcVTPD7kdxBcfb/DCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-18T17:32:31.503451Z","bundle_sha256":"da8139c86cd18e8d404a4deaed1902aa5c2861122cf1e0c176aa08172ed7d8c7"}}