{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:M3EG5H6IXB65PBAJGMCGOMHCFP","short_pith_number":"pith:M3EG5H6I","canonical_record":{"source":{"id":"1301.6721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-23T15:59:46Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"b1eba76758f4ea8c3cd149d6ab7b2b2a6a2ea60f397d9b15bd00f8ba66e9feb3","abstract_canon_sha256":"fe50ed3b135fc3f23b9c7df70c00eb7e4408fc73bb8264be0e7996c98ab887d8"},"schema_version":"1.0"},"canonical_sha256":"66c86e9fc8b87dd7840933046730e22bc458e84f205c5035dd4f8ae4e3e2148d","source":{"kind":"arxiv","id":"1301.6721","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.6721","created_at":"2026-05-18T03:35:12Z"},{"alias_kind":"arxiv_version","alias_value":"1301.6721v1","created_at":"2026-05-18T03:35:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.6721","created_at":"2026-05-18T03:35:12Z"},{"alias_kind":"pith_short_12","alias_value":"M3EG5H6IXB65","created_at":"2026-05-18T12:27:51Z"},{"alias_kind":"pith_short_16","alias_value":"M3EG5H6IXB65PBAJ","created_at":"2026-05-18T12:27:51Z"},{"alias_kind":"pith_short_8","alias_value":"M3EG5H6I","created_at":"2026-05-18T12:27:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:M3EG5H6IXB65PBAJGMCGOMHCFP","target":"record","payload":{"canonical_record":{"source":{"id":"1301.6721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-23T15:59:46Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"b1eba76758f4ea8c3cd149d6ab7b2b2a6a2ea60f397d9b15bd00f8ba66e9feb3","abstract_canon_sha256":"fe50ed3b135fc3f23b9c7df70c00eb7e4408fc73bb8264be0e7996c98ab887d8"},"schema_version":"1.0"},"canonical_sha256":"66c86e9fc8b87dd7840933046730e22bc458e84f205c5035dd4f8ae4e3e2148d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:35:12.735005Z","signature_b64":"D2vJxQFzjFRnKofYs0Hqig7acyyUpErwOy//WazBqeN2MSl93HA+6m4QBGPxAm/IDhK57ojb0VXTMP7qiv7ZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66c86e9fc8b87dd7840933046730e22bc458e84f205c5035dd4f8ae4e3e2148d","last_reissued_at":"2026-05-18T03:35:12.734280Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:35:12.734280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1301.6721","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:35:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EQ+khEsaoKLLbtAoFkrw/+phe3QP8tzTwku4IfOReYW2ab0KJ5TlPVcN7YWRWfBWYZHbjGxly8tTa/K4PMe8Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T04:25:27.667158Z"},"content_sha256":"d25bbc629da97e1500837afd365c67db3c382e76d364d73148c7d6a26e9a3d52","schema_version":"1.0","event_id":"sha256:d25bbc629da97e1500837afd365c67db3c382e76d364d73148c7d6a26e9a3d52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:M3EG5H6IXB65PBAJGMCGOMHCFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Finite-State Controllers for Partially Observable Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"cs.AI","authors_text":"Kee-Eung Kim, Leonid Peshkin, Leslie Pack Kaelbling, Nicolas Meuleau","submitted_at":"2013-01-23T15:59:46Z","abstract_excerpt":"Reactive (memoryless) policies are sufficient in completely observable Markov decision processes (MDPs), but some kind of memory is usually necessary for optimal control of a partially observable MDP. Policies with finite memory can be represented as finite-state automata. In this paper, we extend Baird and Moore's VAPS algorithm to the problem of learning general finite-state automata. Because it performs stochastic gradient descent, this algorithm can be shown to converge to a locally optimal finite-state controller. We provide the details of the algorithm and then consider the question of u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.6721","kind":"arxiv","version":1},"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":"2026-05-18T03:35:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SRW6ULW1gA7butPA7EbdpHDEcQ6cYQ4Sn7OvxyIl4o0y9QFq8LLl6dmyhDDLTDZ8FgiFcCGioWggkoexlkGYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T04:25:27.667841Z"},"content_sha256":"8569f69f6b9cb07273a4e2f1365359e0102de7a50d4730622fb85a3aae066745","schema_version":"1.0","event_id":"sha256:8569f69f6b9cb07273a4e2f1365359e0102de7a50d4730622fb85a3aae066745"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP/bundle.json","state_url":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M3EG5H6IXB65PBAJGMCGOMHCFP/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":"2026-05-27T04:25:27Z","links":{"resolver":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP","bundle":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP/bundle.json","state":"https://pith.science/pith/M3EG5H6IXB65PBAJGMCGOMHCFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M3EG5H6IXB65PBAJGMCGOMHCFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:M3EG5H6IXB65PBAJGMCGOMHCFP","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":"fe50ed3b135fc3f23b9c7df70c00eb7e4408fc73bb8264be0e7996c98ab887d8","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-23T15:59:46Z","title_canon_sha256":"b1eba76758f4ea8c3cd149d6ab7b2b2a6a2ea60f397d9b15bd00f8ba66e9feb3"},"schema_version":"1.0","source":{"id":"1301.6721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.6721","created_at":"2026-05-18T03:35:12Z"},{"alias_kind":"arxiv_version","alias_value":"1301.6721v1","created_at":"2026-05-18T03:35:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.6721","created_at":"2026-05-18T03:35:12Z"},{"alias_kind":"pith_short_12","alias_value":"M3EG5H6IXB65","created_at":"2026-05-18T12:27:51Z"},{"alias_kind":"pith_short_16","alias_value":"M3EG5H6IXB65PBAJ","created_at":"2026-05-18T12:27:51Z"},{"alias_kind":"pith_short_8","alias_value":"M3EG5H6I","created_at":"2026-05-18T12:27:51Z"}],"graph_snapshots":[{"event_id":"sha256:8569f69f6b9cb07273a4e2f1365359e0102de7a50d4730622fb85a3aae066745","target":"graph","created_at":"2026-05-18T03:35:12Z","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":"Reactive (memoryless) policies are sufficient in completely observable Markov decision processes (MDPs), but some kind of memory is usually necessary for optimal control of a partially observable MDP. Policies with finite memory can be represented as finite-state automata. In this paper, we extend Baird and Moore's VAPS algorithm to the problem of learning general finite-state automata. Because it performs stochastic gradient descent, this algorithm can be shown to converge to a locally optimal finite-state controller. We provide the details of the algorithm and then consider the question of u","authors_text":"Kee-Eung Kim, Leonid Peshkin, Leslie Pack Kaelbling, Nicolas Meuleau","cross_cats":["cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-23T15:59:46Z","title":"Learning Finite-State Controllers for Partially Observable Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.6721","kind":"arxiv","version":1},"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:d25bbc629da97e1500837afd365c67db3c382e76d364d73148c7d6a26e9a3d52","target":"record","created_at":"2026-05-18T03:35:12Z","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":"fe50ed3b135fc3f23b9c7df70c00eb7e4408fc73bb8264be0e7996c98ab887d8","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-23T15:59:46Z","title_canon_sha256":"b1eba76758f4ea8c3cd149d6ab7b2b2a6a2ea60f397d9b15bd00f8ba66e9feb3"},"schema_version":"1.0","source":{"id":"1301.6721","kind":"arxiv","version":1}},"canonical_sha256":"66c86e9fc8b87dd7840933046730e22bc458e84f205c5035dd4f8ae4e3e2148d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66c86e9fc8b87dd7840933046730e22bc458e84f205c5035dd4f8ae4e3e2148d","first_computed_at":"2026-05-18T03:35:12.734280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:35:12.734280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D2vJxQFzjFRnKofYs0Hqig7acyyUpErwOy//WazBqeN2MSl93HA+6m4QBGPxAm/IDhK57ojb0VXTMP7qiv7ZBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:35:12.735005Z","signed_message":"canonical_sha256_bytes"},"source_id":"1301.6721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d25bbc629da97e1500837afd365c67db3c382e76d364d73148c7d6a26e9a3d52","sha256:8569f69f6b9cb07273a4e2f1365359e0102de7a50d4730622fb85a3aae066745"],"state_sha256":"64e9300e5cd52e6747323936d4dfaf30ed79e57990f4207af897eba0eaf18591"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IvQAvyuRi3Xb4uSChd8hEy172XQ3ym/ZWSuTTvP9g82urY7xFUCZmThb38S5RDRG1BSsM3vh8dJ8Ut9sDwUMAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T04:25:27.671810Z","bundle_sha256":"09c117edcae59889387d05cf9a1d0cc843a5287bb98239493cd4a54cd2f0a0a1"}}