{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JMXPKGYDZTTHKOEZGO7LONVMPQ","short_pith_number":"pith:JMXPKGYD","canonical_record":{"source":{"id":"2103.12558","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-03-23T14:01:35Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"c17e689cbfae5be7f70fe6096c032f2a592f9cad3c1fd9539a4f992aa4490a89","abstract_canon_sha256":"84112ec5f5bbce2d20ced02ec14ef3629d828fdb5ae8fd24be4cb22bdbb851d3"},"schema_version":"1.0"},"canonical_sha256":"4b2ef51b03cce675389933beb736ac7c247bf1d66ac6b33a12bb7409e4940a68","source":{"kind":"arxiv","id":"2103.12558","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12558","created_at":"2026-07-05T02:32:49Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12558v2","created_at":"2026-07-05T02:32:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12558","created_at":"2026-07-05T02:32:49Z"},{"alias_kind":"pith_short_12","alias_value":"JMXPKGYDZTTH","created_at":"2026-07-05T02:32:49Z"},{"alias_kind":"pith_short_16","alias_value":"JMXPKGYDZTTHKOEZ","created_at":"2026-07-05T02:32:49Z"},{"alias_kind":"pith_short_8","alias_value":"JMXPKGYD","created_at":"2026-07-05T02:32:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JMXPKGYDZTTHKOEZGO7LONVMPQ","target":"record","payload":{"canonical_record":{"source":{"id":"2103.12558","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-03-23T14:01:35Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"c17e689cbfae5be7f70fe6096c032f2a592f9cad3c1fd9539a4f992aa4490a89","abstract_canon_sha256":"84112ec5f5bbce2d20ced02ec14ef3629d828fdb5ae8fd24be4cb22bdbb851d3"},"schema_version":"1.0"},"canonical_sha256":"4b2ef51b03cce675389933beb736ac7c247bf1d66ac6b33a12bb7409e4940a68","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:49.323132Z","signature_b64":"Q35JoXKPpyWtGmjxvRbLQ/ffdLvOW2eL2+oZmo9kdtwbohvfICt1lnZPpIWxqcGIqNEHvtW+2Ca8Zc73r5WnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b2ef51b03cce675389933beb736ac7c247bf1d66ac6b33a12bb7409e4940a68","last_reissued_at":"2026-07-05T02:32:49.322685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:49.322685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.12558","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":"2026-07-05T02:32:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3v0NnOCFFb4Eh4S00A6nOtmM1n1weixe6UYhI894EDEJL9T1qTUqTlFAzDPdXENiVlV007Ax1B5tZoAnWB/1BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T08:43:04.187900Z"},"content_sha256":"3b00659c42abbb290384428e2c75aa8c5cb903e73f7f9c32d482b7fba8f73257","schema_version":"1.0","event_id":"sha256:3b00659c42abbb290384428e2c75aa8c5cb903e73f7f9c32d482b7fba8f73257"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JMXPKGYDZTTHKOEZGO7LONVMPQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Assured Learning-enabled Autonomy: A Metacognitive Reinforcement Learning Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Aquib Mustafa, Hamidreza Modares, Majid Mazouchi, Subramanya Nageshrao","submitted_at":"2021-03-23T14:01:35Z","abstract_excerpt":"Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety constraints across variety of circumstances, an assured autonomous control framework is presented in this paper by empowering RL algorithms with metacognitive learning capabilities. More specifically, adapting the reward function parameters of the RL agent is performed in a metacognitive decision-making layer to assure the feasibility of RL agent. That is, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12558","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.12558/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:32:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XvRACOf1JlXAdaNlpc9wwGHbH5lR+PgGRBquur46PfuuWnHtq9xfby/8NNvmKr8Gi0Pyb79I4kE+yHl1kSC2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T08:43:04.188570Z"},"content_sha256":"5e5a1860d44b773564662a5cf44e9ebaef884c35e88fbd101486e77d01209669","schema_version":"1.0","event_id":"sha256:5e5a1860d44b773564662a5cf44e9ebaef884c35e88fbd101486e77d01209669"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMXPKGYDZTTHKOEZGO7LONVMPQ/bundle.json","state_url":"https://pith.science/pith/JMXPKGYDZTTHKOEZGO7LONVMPQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMXPKGYDZTTHKOEZGO7LONVMPQ/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":"2026-08-01T08:43:04Z","links":{"resolver":"https://pith.science/pith/JMXPKGYDZTTHKOEZGO7LONVMPQ","bundle":"https://pith.science/pith/JMXPKGYDZTTHKOEZGO7LONVMPQ/bundle.json","state":"https://pith.science/pith/JMXPKGYDZTTHKOEZGO7LONVMPQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMXPKGYDZTTHKOEZGO7LONVMPQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JMXPKGYDZTTHKOEZGO7LONVMPQ","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":"84112ec5f5bbce2d20ced02ec14ef3629d828fdb5ae8fd24be4cb22bdbb851d3","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-03-23T14:01:35Z","title_canon_sha256":"c17e689cbfae5be7f70fe6096c032f2a592f9cad3c1fd9539a4f992aa4490a89"},"schema_version":"1.0","source":{"id":"2103.12558","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12558","created_at":"2026-07-05T02:32:49Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12558v2","created_at":"2026-07-05T02:32:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12558","created_at":"2026-07-05T02:32:49Z"},{"alias_kind":"pith_short_12","alias_value":"JMXPKGYDZTTH","created_at":"2026-07-05T02:32:49Z"},{"alias_kind":"pith_short_16","alias_value":"JMXPKGYDZTTHKOEZ","created_at":"2026-07-05T02:32:49Z"},{"alias_kind":"pith_short_8","alias_value":"JMXPKGYD","created_at":"2026-07-05T02:32:49Z"}],"graph_snapshots":[{"event_id":"sha256:5e5a1860d44b773564662a5cf44e9ebaef884c35e88fbd101486e77d01209669","target":"graph","created_at":"2026-07-05T02:32:49Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.12558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety constraints across variety of circumstances, an assured autonomous control framework is presented in this paper by empowering RL algorithms with metacognitive learning capabilities. More specifically, adapting the reward function parameters of the RL agent is performed in a metacognitive decision-making layer to assure the feasibility of RL agent. That is, ","authors_text":"Aquib Mustafa, Hamidreza Modares, Majid Mazouchi, Subramanya Nageshrao","cross_cats":["cs.LG","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-03-23T14:01:35Z","title":"Assured Learning-enabled Autonomy: A Metacognitive Reinforcement Learning Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12558","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":"sha256:3b00659c42abbb290384428e2c75aa8c5cb903e73f7f9c32d482b7fba8f73257","target":"record","created_at":"2026-07-05T02:32:49Z","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":"84112ec5f5bbce2d20ced02ec14ef3629d828fdb5ae8fd24be4cb22bdbb851d3","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-03-23T14:01:35Z","title_canon_sha256":"c17e689cbfae5be7f70fe6096c032f2a592f9cad3c1fd9539a4f992aa4490a89"},"schema_version":"1.0","source":{"id":"2103.12558","kind":"arxiv","version":2}},"canonical_sha256":"4b2ef51b03cce675389933beb736ac7c247bf1d66ac6b33a12bb7409e4940a68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b2ef51b03cce675389933beb736ac7c247bf1d66ac6b33a12bb7409e4940a68","first_computed_at":"2026-07-05T02:32:49.322685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:49.322685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q35JoXKPpyWtGmjxvRbLQ/ffdLvOW2eL2+oZmo9kdtwbohvfICt1lnZPpIWxqcGIqNEHvtW+2Ca8Zc73r5WnBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:49.323132Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.12558","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b00659c42abbb290384428e2c75aa8c5cb903e73f7f9c32d482b7fba8f73257","sha256:5e5a1860d44b773564662a5cf44e9ebaef884c35e88fbd101486e77d01209669"],"state_sha256":"f9439a7237e6b2b170334b79ee09f775b195ad0b1ff743c88db7b4e30fd8142e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pucYM0ONpox/oiwbAAe0ZHzBhPlRpOuC10fMsaCeVwo7TxsUaYz6397Jr7k2vERaMhocFWbzEC9C8YtGmxP0BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T08:43:04.191612Z","bundle_sha256":"cde1c8228dad6f176316a4c685c29fbed11d31b29763ed60e72ace90e448c9e3"}}