{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:QYE7WR4RE745XCFJZP65Z24V3M","short_pith_number":"pith:QYE7WR4R","canonical_record":{"source":{"id":"1510.06460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2015-10-22T00:17:09Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"f0b2f1c1b09d708560b5a76360cf5df770338d221fb1043aa49123d9f3fcfa24","abstract_canon_sha256":"60102ea91bc1be47ae287e79b8a41a6bd99d39242e8d5df315d17a05a98562a8"},"schema_version":"1.0"},"canonical_sha256":"8609fb479127f9db88a9cbfddceb95db35e46ffb7b235b1c957b698bbb3e50c6","source":{"kind":"arxiv","id":"1510.06460","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.06460","created_at":"2026-05-18T01:29:30Z"},{"alias_kind":"arxiv_version","alias_value":"1510.06460v1","created_at":"2026-05-18T01:29:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.06460","created_at":"2026-05-18T01:29:30Z"},{"alias_kind":"pith_short_12","alias_value":"QYE7WR4RE745","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"QYE7WR4RE745XCFJ","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"QYE7WR4R","created_at":"2026-05-18T12:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:QYE7WR4RE745XCFJZP65Z24V3M","target":"record","payload":{"canonical_record":{"source":{"id":"1510.06460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2015-10-22T00:17:09Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"f0b2f1c1b09d708560b5a76360cf5df770338d221fb1043aa49123d9f3fcfa24","abstract_canon_sha256":"60102ea91bc1be47ae287e79b8a41a6bd99d39242e8d5df315d17a05a98562a8"},"schema_version":"1.0"},"canonical_sha256":"8609fb479127f9db88a9cbfddceb95db35e46ffb7b235b1c957b698bbb3e50c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:29:30.912535Z","signature_b64":"B04iYmtGqxx4Pdsh4BEHNvlDBxqV8uv+VEGChSpLpZ8k2qBgef2XLQjv9QVKriCbB4UpigzG+Hg6Mx/3dLdwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8609fb479127f9db88a9cbfddceb95db35e46ffb7b235b1c957b698bbb3e50c6","last_reissued_at":"2026-05-18T01:29:30.912094Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:29:30.912094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1510.06460","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":"2026-05-18T01:29:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gg2mH0HAvDMPAp/KqS+3nKtZiLOwNFFe259kR0t6+KXIrXdhzR2Hf410shtdJHg9sjc7UeB3LCBbIo10oefrAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:15:08.174298Z"},"content_sha256":"696bf69dcd17b2082cf2f5d505759d013028723813f64cd38be82f4cec936610","schema_version":"1.0","event_id":"sha256:696bf69dcd17b2082cf2f5d505759d013028723813f64cd38be82f4cec936610"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:QYE7WR4RE745XCFJZP65Z24V3M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Satisfaction of Temporal Logic Specifications via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.SY","authors_text":"Austin Jones, Calin Belta, Derya Aksaray, Mac Schwager, Zhaodan Kong","submitted_at":"2015-10-22T00:17:09Z","abstract_excerpt":"We consider the problem of steering a system with unknown, stochastic dynamics to satisfy a rich, temporally layered task given as a signal temporal logic formula. We represent the system as a Markov decision process in which the states are built from a partition of the state space and the transition probabilities are unknown. We present provably convergent reinforcement learning algorithms to maximize the probability of satisfying a given formula and to maximize the average expected robustness, i.e., a measure of how strongly the formula is satisfied. We demonstrate via a pair of robot naviga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.06460","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":"2026-05-18T01:29:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5uZe5qHjO5evOufDmDEEpMk52RHNswav1D5Ao9QivQve7pxO+O5k9nNjY3BaMKkO7Xr50hwXYGJj4uwvQDwdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:15:08.175127Z"},"content_sha256":"b55f46d65661b490b05a79edb39376dc3ab75db82ab2fa6272f357f57efbd815","schema_version":"1.0","event_id":"sha256:b55f46d65661b490b05a79edb39376dc3ab75db82ab2fa6272f357f57efbd815"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QYE7WR4RE745XCFJZP65Z24V3M/bundle.json","state_url":"https://pith.science/pith/QYE7WR4RE745XCFJZP65Z24V3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QYE7WR4RE745XCFJZP65Z24V3M/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":"2026-05-31T01:15:08Z","links":{"resolver":"https://pith.science/pith/QYE7WR4RE745XCFJZP65Z24V3M","bundle":"https://pith.science/pith/QYE7WR4RE745XCFJZP65Z24V3M/bundle.json","state":"https://pith.science/pith/QYE7WR4RE745XCFJZP65Z24V3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QYE7WR4RE745XCFJZP65Z24V3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:QYE7WR4RE745XCFJZP65Z24V3M","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":"60102ea91bc1be47ae287e79b8a41a6bd99d39242e8d5df315d17a05a98562a8","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2015-10-22T00:17:09Z","title_canon_sha256":"f0b2f1c1b09d708560b5a76360cf5df770338d221fb1043aa49123d9f3fcfa24"},"schema_version":"1.0","source":{"id":"1510.06460","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1510.06460","created_at":"2026-05-18T01:29:30Z"},{"alias_kind":"arxiv_version","alias_value":"1510.06460v1","created_at":"2026-05-18T01:29:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.06460","created_at":"2026-05-18T01:29:30Z"},{"alias_kind":"pith_short_12","alias_value":"QYE7WR4RE745","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"QYE7WR4RE745XCFJ","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"QYE7WR4R","created_at":"2026-05-18T12:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:b55f46d65661b490b05a79edb39376dc3ab75db82ab2fa6272f357f57efbd815","target":"graph","created_at":"2026-05-18T01:29:30Z","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 consider the problem of steering a system with unknown, stochastic dynamics to satisfy a rich, temporally layered task given as a signal temporal logic formula. We represent the system as a Markov decision process in which the states are built from a partition of the state space and the transition probabilities are unknown. We present provably convergent reinforcement learning algorithms to maximize the probability of satisfying a given formula and to maximize the average expected robustness, i.e., a measure of how strongly the formula is satisfied. We demonstrate via a pair of robot naviga","authors_text":"Austin Jones, Calin Belta, Derya Aksaray, Mac Schwager, Zhaodan Kong","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2015-10-22T00:17:09Z","title":"Robust Satisfaction of Temporal Logic Specifications via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.06460","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":"sha256:696bf69dcd17b2082cf2f5d505759d013028723813f64cd38be82f4cec936610","target":"record","created_at":"2026-05-18T01:29:30Z","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":"60102ea91bc1be47ae287e79b8a41a6bd99d39242e8d5df315d17a05a98562a8","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2015-10-22T00:17:09Z","title_canon_sha256":"f0b2f1c1b09d708560b5a76360cf5df770338d221fb1043aa49123d9f3fcfa24"},"schema_version":"1.0","source":{"id":"1510.06460","kind":"arxiv","version":1}},"canonical_sha256":"8609fb479127f9db88a9cbfddceb95db35e46ffb7b235b1c957b698bbb3e50c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8609fb479127f9db88a9cbfddceb95db35e46ffb7b235b1c957b698bbb3e50c6","first_computed_at":"2026-05-18T01:29:30.912094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:29:30.912094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B04iYmtGqxx4Pdsh4BEHNvlDBxqV8uv+VEGChSpLpZ8k2qBgef2XLQjv9QVKriCbB4UpigzG+Hg6Mx/3dLdwBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:29:30.912535Z","signed_message":"canonical_sha256_bytes"},"source_id":"1510.06460","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:696bf69dcd17b2082cf2f5d505759d013028723813f64cd38be82f4cec936610","sha256:b55f46d65661b490b05a79edb39376dc3ab75db82ab2fa6272f357f57efbd815"],"state_sha256":"5efabc2179f596907094a58c539712325d2920ba7e621719881cb7230bff70ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YNlHjoLWNcavYXw2wMTcbY/SosbxZQ4Z+drJzH9wS38nm+hWs1HTxr5FKIA7UoRzTp87jTW8johIgGtE1U02Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T01:15:08.178939Z","bundle_sha256":"d9284e28c9f38294ab966ded74a7f435bc03f983b5e09ca47c99563dcd77c292"}}