{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:M6WYNB7VG6EIPBXP4XVCPC7ITD","short_pith_number":"pith:M6WYNB7V","canonical_record":{"source":{"id":"1809.06482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-18T00:09:08Z","cross_cats_sorted":[],"title_canon_sha256":"20d0ef1c33be3f9d57eaeb69282fbca701cc86f5aba4ded9b40048de45272bba","abstract_canon_sha256":"d35c7ce5415f660b0a40babb27bb24c4e3343bb02c65d855429155782ab1e0c7"},"schema_version":"1.0"},"canonical_sha256":"67ad8687f537888786efe5ea278be898e44326c0ea630cac29212ed5c91b0cc0","source":{"kind":"arxiv","id":"1809.06482","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.06482","created_at":"2026-05-18T00:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"1809.06482v1","created_at":"2026-05-18T00:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06482","created_at":"2026-05-18T00:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"M6WYNB7VG6EI","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"M6WYNB7VG6EIPBXP","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"M6WYNB7V","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:M6WYNB7VG6EIPBXP4XVCPC7ITD","target":"record","payload":{"canonical_record":{"source":{"id":"1809.06482","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-18T00:09:08Z","cross_cats_sorted":[],"title_canon_sha256":"20d0ef1c33be3f9d57eaeb69282fbca701cc86f5aba4ded9b40048de45272bba","abstract_canon_sha256":"d35c7ce5415f660b0a40babb27bb24c4e3343bb02c65d855429155782ab1e0c7"},"schema_version":"1.0"},"canonical_sha256":"67ad8687f537888786efe5ea278be898e44326c0ea630cac29212ed5c91b0cc0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:27.043063Z","signature_b64":"2lZhR/61zFV/WFYLAwtiiq2QqJC/qI1UmzDgEwFUeiNqULNwgzbICHSvcKwpcIqJ2Qrjx8LbkDvLona4NaptCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67ad8687f537888786efe5ea278be898e44326c0ea630cac29212ed5c91b0cc0","last_reissued_at":"2026-05-18T00:05:27.042524Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:27.042524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.06482","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":"2026-05-18T00:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dQ7gdIfiTkaxjxW44egO0NXPPPTjOqduHYLNFeByRTOFgMyoQc2h5dEUZpYENs77rCY+BaoYgkeQNfyUwZEaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:43:15.567468Z"},"content_sha256":"e00546c019c72580533f1a88a4aad545d4330b137979fc8e41e267e139d5f0e5","schema_version":"1.0","event_id":"sha256:e00546c019c72580533f1a88a4aad545d4330b137979fc8e41e267e139d5f0e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:M6WYNB7VG6EIPBXP4XVCPC7ITD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Least Inferable Policies for Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Melkior Ornik, Mustafa O. Karabag, Ufuk Topcu","submitted_at":"2018-09-18T00:09:08Z","abstract_excerpt":"In a variety of applications, an agent's success depends on the knowledge that an adversarial observer has or can gather about the agent's decisions. It is therefore desirable for the agent to achieve a task while reducing the ability of an observer to infer the agent's policy. We consider the task of the agent as a reachability problem in a Markov decision process and study the synthesis of policies that minimize the observer's ability to infer the transition probabilities of the agent between the states of the Markov decision process. We introduce a metric that is based on the Fisher informa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06482","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":"2026-05-18T00:05:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wM/saG6OIxto2xrWzDKNObJgoGOSOZuxqfdJ+nMW1BtSlOqIJJaV9EfzbiCdm4eKsMxkEhDreJ79Uzfq7AenCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:43:15.567813Z"},"content_sha256":"e9694d5a65e1727168ae0ad369c3bf06a817bbb93f404988fece5b5337046c18","schema_version":"1.0","event_id":"sha256:e9694d5a65e1727168ae0ad369c3bf06a817bbb93f404988fece5b5337046c18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M6WYNB7VG6EIPBXP4XVCPC7ITD/bundle.json","state_url":"https://pith.science/pith/M6WYNB7VG6EIPBXP4XVCPC7ITD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M6WYNB7VG6EIPBXP4XVCPC7ITD/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":"2026-06-07T14:43:15Z","links":{"resolver":"https://pith.science/pith/M6WYNB7VG6EIPBXP4XVCPC7ITD","bundle":"https://pith.science/pith/M6WYNB7VG6EIPBXP4XVCPC7ITD/bundle.json","state":"https://pith.science/pith/M6WYNB7VG6EIPBXP4XVCPC7ITD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M6WYNB7VG6EIPBXP4XVCPC7ITD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:M6WYNB7VG6EIPBXP4XVCPC7ITD","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":"d35c7ce5415f660b0a40babb27bb24c4e3343bb02c65d855429155782ab1e0c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-18T00:09:08Z","title_canon_sha256":"20d0ef1c33be3f9d57eaeb69282fbca701cc86f5aba4ded9b40048de45272bba"},"schema_version":"1.0","source":{"id":"1809.06482","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.06482","created_at":"2026-05-18T00:05:27Z"},{"alias_kind":"arxiv_version","alias_value":"1809.06482v1","created_at":"2026-05-18T00:05:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06482","created_at":"2026-05-18T00:05:27Z"},{"alias_kind":"pith_short_12","alias_value":"M6WYNB7VG6EI","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"M6WYNB7VG6EIPBXP","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"M6WYNB7V","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:e9694d5a65e1727168ae0ad369c3bf06a817bbb93f404988fece5b5337046c18","target":"graph","created_at":"2026-05-18T00:05:27Z","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":"In a variety of applications, an agent's success depends on the knowledge that an adversarial observer has or can gather about the agent's decisions. It is therefore desirable for the agent to achieve a task while reducing the ability of an observer to infer the agent's policy. We consider the task of the agent as a reachability problem in a Markov decision process and study the synthesis of policies that minimize the observer's ability to infer the transition probabilities of the agent between the states of the Markov decision process. We introduce a metric that is based on the Fisher informa","authors_text":"Melkior Ornik, Mustafa O. Karabag, Ufuk Topcu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-18T00:09:08Z","title":"Least Inferable Policies for Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06482","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:e00546c019c72580533f1a88a4aad545d4330b137979fc8e41e267e139d5f0e5","target":"record","created_at":"2026-05-18T00:05:27Z","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":"d35c7ce5415f660b0a40babb27bb24c4e3343bb02c65d855429155782ab1e0c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-18T00:09:08Z","title_canon_sha256":"20d0ef1c33be3f9d57eaeb69282fbca701cc86f5aba4ded9b40048de45272bba"},"schema_version":"1.0","source":{"id":"1809.06482","kind":"arxiv","version":1}},"canonical_sha256":"67ad8687f537888786efe5ea278be898e44326c0ea630cac29212ed5c91b0cc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67ad8687f537888786efe5ea278be898e44326c0ea630cac29212ed5c91b0cc0","first_computed_at":"2026-05-18T00:05:27.042524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:27.042524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2lZhR/61zFV/WFYLAwtiiq2QqJC/qI1UmzDgEwFUeiNqULNwgzbICHSvcKwpcIqJ2Qrjx8LbkDvLona4NaptCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:27.043063Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.06482","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e00546c019c72580533f1a88a4aad545d4330b137979fc8e41e267e139d5f0e5","sha256:e9694d5a65e1727168ae0ad369c3bf06a817bbb93f404988fece5b5337046c18"],"state_sha256":"d4e2f3b8021c4132d414f2c7105c98cedd5fdb0db155ecb4cc9c8e460cb9fab9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rGBDxPBH0MAQtqK1tNd43nbhPBhpxOPGe5gCMm1G43pbttbzT0sODTYxOzIcWXeFBpp8D25IzEuUSDrBdUQnDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T14:43:15.569641Z","bundle_sha256":"eebda369e1c239cec9021a89c5c2bd33b6308a55f069451e440fea408f8bad82"}}