{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:BADH7PE4IBP3IASYXQVCLTXWIQ","short_pith_number":"pith:BADH7PE4","canonical_record":{"source":{"id":"1102.5561","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-02-27T23:47:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5fd3b230095b4be2123f396eb42c2eca8fba43407c108567aafd7109334511ff","abstract_canon_sha256":"5698c01ae55ed37a878e611f3035225cb1b224e0edf86e23d6b0c2fb2afa9dfb"},"schema_version":"1.0"},"canonical_sha256":"08067fbc9c405fb40258bc2a25cef64417ce52099af5c90d806d92036f401060","source":{"kind":"arxiv","id":"1102.5561","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1102.5561","created_at":"2026-05-18T04:27:37Z"},{"alias_kind":"arxiv_version","alias_value":"1102.5561v2","created_at":"2026-05-18T04:27:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1102.5561","created_at":"2026-05-18T04:27:37Z"},{"alias_kind":"pith_short_12","alias_value":"BADH7PE4IBP3","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"BADH7PE4IBP3IASY","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"BADH7PE4","created_at":"2026-05-18T12:26:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:BADH7PE4IBP3IASYXQVCLTXWIQ","target":"record","payload":{"canonical_record":{"source":{"id":"1102.5561","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-02-27T23:47:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5fd3b230095b4be2123f396eb42c2eca8fba43407c108567aafd7109334511ff","abstract_canon_sha256":"5698c01ae55ed37a878e611f3035225cb1b224e0edf86e23d6b0c2fb2afa9dfb"},"schema_version":"1.0"},"canonical_sha256":"08067fbc9c405fb40258bc2a25cef64417ce52099af5c90d806d92036f401060","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:27:37.552065Z","signature_b64":"ZB+RcF4Zb4KHDHNiRUqcc9BnFeL44yghT1/I//6qSDNRxqPLaBXCy5e2w1PdM91A95HqGhQ4k2d2VSXEb/DbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08067fbc9c405fb40258bc2a25cef64417ce52099af5c90d806d92036f401060","last_reissued_at":"2026-05-18T04:27:37.551385Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:27:37.551385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1102.5561","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":"2026-05-18T04:27:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GFbyGE6WGGeO1pGRTYWB/3sfZGfb2hZRMUxnJm8hzPKGds5AfkNaPz0uqoc+SNy+GcvNKIyhBg0qGgXbzeOwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T08:24:28.235951Z"},"content_sha256":"3c62096334c3b870ecf4018b6e47bc4ef77ce43d50ea449dfc4113b2611f35c2","schema_version":"1.0","event_id":"sha256:3c62096334c3b870ecf4018b6e47bc4ef77ce43d50ea449dfc4113b2611f35c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:BADH7PE4IBP3IASYXQVCLTXWIQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decision Making Agent Searching for Markov Models in Near-Deterministic World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Andras Lorincz, Gabor Matuz","submitted_at":"2011-02-27T23:47:13Z","abstract_excerpt":"Reinforcement learning has solid foundations, but becomes inefficient in partially observed (non-Markovian) environments. Thus, a learning agent -born with a representation and a policy- might wish to investigate to what extent the Markov property holds. We propose a learning architecture that utilizes combinatorial policy optimization to overcome non-Markovity and to develop efficient behaviors, which are easy to inherit, tests the Markov property of the behavioral states, and corrects against non-Markovity by running a deterministic factored Finite State Model, which can be learned. We illus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1102.5561","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":"2026-05-18T04:27:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1qEIfWw25KZnwFhCdnX7JVTBG9laYzKsmAdlXqi/25GMf1wwLv6zvePQmHIt3qDg7IsSnPVGD9MWtKLYqZCQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T08:24:28.236292Z"},"content_sha256":"3841a1553044f8a56ed9212f7d7f259759679c601b0d7e56879cb6453c85f235","schema_version":"1.0","event_id":"sha256:3841a1553044f8a56ed9212f7d7f259759679c601b0d7e56879cb6453c85f235"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ/bundle.json","state_url":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BADH7PE4IBP3IASYXQVCLTXWIQ/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":"2026-06-01T08:24:28Z","links":{"resolver":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ","bundle":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ/bundle.json","state":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BADH7PE4IBP3IASYXQVCLTXWIQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:BADH7PE4IBP3IASYXQVCLTXWIQ","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":"5698c01ae55ed37a878e611f3035225cb1b224e0edf86e23d6b0c2fb2afa9dfb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-02-27T23:47:13Z","title_canon_sha256":"5fd3b230095b4be2123f396eb42c2eca8fba43407c108567aafd7109334511ff"},"schema_version":"1.0","source":{"id":"1102.5561","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1102.5561","created_at":"2026-05-18T04:27:37Z"},{"alias_kind":"arxiv_version","alias_value":"1102.5561v2","created_at":"2026-05-18T04:27:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1102.5561","created_at":"2026-05-18T04:27:37Z"},{"alias_kind":"pith_short_12","alias_value":"BADH7PE4IBP3","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"BADH7PE4IBP3IASY","created_at":"2026-05-18T12:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"BADH7PE4","created_at":"2026-05-18T12:26:24Z"}],"graph_snapshots":[{"event_id":"sha256:3841a1553044f8a56ed9212f7d7f259759679c601b0d7e56879cb6453c85f235","target":"graph","created_at":"2026-05-18T04:27:37Z","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 has solid foundations, but becomes inefficient in partially observed (non-Markovian) environments. Thus, a learning agent -born with a representation and a policy- might wish to investigate to what extent the Markov property holds. We propose a learning architecture that utilizes combinatorial policy optimization to overcome non-Markovity and to develop efficient behaviors, which are easy to inherit, tests the Markov property of the behavioral states, and corrects against non-Markovity by running a deterministic factored Finite State Model, which can be learned. We illus","authors_text":"Andras Lorincz, Gabor Matuz","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-02-27T23:47:13Z","title":"Decision Making Agent Searching for Markov Models in Near-Deterministic World"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1102.5561","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":"sha256:3c62096334c3b870ecf4018b6e47bc4ef77ce43d50ea449dfc4113b2611f35c2","target":"record","created_at":"2026-05-18T04:27:37Z","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":"5698c01ae55ed37a878e611f3035225cb1b224e0edf86e23d6b0c2fb2afa9dfb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-02-27T23:47:13Z","title_canon_sha256":"5fd3b230095b4be2123f396eb42c2eca8fba43407c108567aafd7109334511ff"},"schema_version":"1.0","source":{"id":"1102.5561","kind":"arxiv","version":2}},"canonical_sha256":"08067fbc9c405fb40258bc2a25cef64417ce52099af5c90d806d92036f401060","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08067fbc9c405fb40258bc2a25cef64417ce52099af5c90d806d92036f401060","first_computed_at":"2026-05-18T04:27:37.551385Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:27:37.551385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZB+RcF4Zb4KHDHNiRUqcc9BnFeL44yghT1/I//6qSDNRxqPLaBXCy5e2w1PdM91A95HqGhQ4k2d2VSXEb/DbCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T04:27:37.552065Z","signed_message":"canonical_sha256_bytes"},"source_id":"1102.5561","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c62096334c3b870ecf4018b6e47bc4ef77ce43d50ea449dfc4113b2611f35c2","sha256:3841a1553044f8a56ed9212f7d7f259759679c601b0d7e56879cb6453c85f235"],"state_sha256":"dd5edebd330d936bb948a76e3e79f8c184c8b15f362bc9cf7932ecbd4a75a026"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VSAgR7qtSwLPVMMvXWVOh40QSFmcEPNKc+pCGnnDr+nQmp/NMEOF4cayVqwQ63IpdlqiXHwh4IAYwYasLBcNBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T08:24:28.238192Z","bundle_sha256":"e556491ff4b2ab9077247e2bf7bf21b6586cc17f31a0fad59173324547ca4e32"}}