{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CJTPKVQDG6VC4KBZJPCKI6GJIK","short_pith_number":"pith:CJTPKVQD","canonical_record":{"source":{"id":"2411.12019","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-18T20:01:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e60707db5edf3b1351847e4055a1d7034676a9a481d3786053e7584f5e0d728d","abstract_canon_sha256":"104cdff2839e200118af12ba302d994c4bafa3ee40ddf0e37f843b3dd4508b9d"},"schema_version":"1.0"},"canonical_sha256":"1266f5560337aa2e28394bc4a478c942ae67c85be6a1240eb24303ba751f6642","source":{"kind":"arxiv","id":"2411.12019","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12019","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12019v2","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12019","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"CJTPKVQDG6VC","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"pith_short_16","alias_value":"CJTPKVQDG6VC4KBZ","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"pith_short_8","alias_value":"CJTPKVQD","created_at":"2026-07-05T11:17:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CJTPKVQDG6VC4KBZJPCKI6GJIK","target":"record","payload":{"canonical_record":{"source":{"id":"2411.12019","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-18T20:01:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e60707db5edf3b1351847e4055a1d7034676a9a481d3786053e7584f5e0d728d","abstract_canon_sha256":"104cdff2839e200118af12ba302d994c4bafa3ee40ddf0e37f843b3dd4508b9d"},"schema_version":"1.0"},"canonical_sha256":"1266f5560337aa2e28394bc4a478c942ae67c85be6a1240eb24303ba751f6642","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:22.919539Z","signature_b64":"0ItfYYZ2nMfLwtbi7/3tlvVnNcVNT6dkjhcYpOY3rmX3n3n+f5aw1F52e2wg9un+kMLLoeD+ZkzZOE5PDhgTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1266f5560337aa2e28394bc4a478c942ae67c85be6a1240eb24303ba751f6642","last_reissued_at":"2026-07-05T11:17:22.919078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:22.919078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.12019","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":"2026-07-05T11:17:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ForE/O9bIPxHdXsp9+vWmZEsbRvvTJ/OJgktVzLOkHFTEz6Q2cfdiXbWTxawQ5Oc3I43ejAwnqevud5ZodiMCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T05:34:57.781043Z"},"content_sha256":"d3ac416f754e9dce3243d1edb424a56f27f2ea15a2683c0e348018ea914eacd6","schema_version":"1.0","event_id":"sha256:d3ac416f754e9dce3243d1edb424a56f27f2ea15a2683c0e348018ea914eacd6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CJTPKVQDG6VC4KBZJPCKI6GJIK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regret-Free Reinforcement Learning for LTL Specifications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Mahmoud Salamati, Rupak Majumdar, Sadegh Soudjani","submitted_at":"2024-11-18T20:01:45Z","abstract_excerpt":"Learning to control an unknown dynamical system with respect to high-level temporal specifications is an important problem in control theory. We present the first regret-free online algorithm for learning a controller for linear temporal logic (LTL) specifications for systems with unknown dynamics. We assume that the underlying (unknown) dynamics is modeled by a finite-state and action Markov decision process (MDP). Our core technical result is a regret-free learning algorithm for infinite-horizon reach-avoid problems on MDPs. For general LTL specifications, we show that the synthesis problem "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12019","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/2411.12019/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":"2026-07-05T11:17:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2eareLTh/ibQ5MmDbZBuZdvHCtCATHpq79uh8JtxH4lSrPEKbYUVo0KXnjNTfvrgYynt12u+/+J8oBwcJh7iCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T05:34:57.782152Z"},"content_sha256":"4a4f1cd572ac7e5f271b291be374d13d7ee1ec18b89b027ccc7d9e88d6a4d896","schema_version":"1.0","event_id":"sha256:4a4f1cd572ac7e5f271b291be374d13d7ee1ec18b89b027ccc7d9e88d6a4d896"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CJTPKVQDG6VC4KBZJPCKI6GJIK/bundle.json","state_url":"https://pith.science/pith/CJTPKVQDG6VC4KBZJPCKI6GJIK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CJTPKVQDG6VC4KBZJPCKI6GJIK/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":"2026-08-21T05:34:57Z","links":{"resolver":"https://pith.science/pith/CJTPKVQDG6VC4KBZJPCKI6GJIK","bundle":"https://pith.science/pith/CJTPKVQDG6VC4KBZJPCKI6GJIK/bundle.json","state":"https://pith.science/pith/CJTPKVQDG6VC4KBZJPCKI6GJIK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CJTPKVQDG6VC4KBZJPCKI6GJIK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CJTPKVQDG6VC4KBZJPCKI6GJIK","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":"104cdff2839e200118af12ba302d994c4bafa3ee40ddf0e37f843b3dd4508b9d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-18T20:01:45Z","title_canon_sha256":"e60707db5edf3b1351847e4055a1d7034676a9a481d3786053e7584f5e0d728d"},"schema_version":"1.0","source":{"id":"2411.12019","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12019","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12019v2","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12019","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"CJTPKVQDG6VC","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"pith_short_16","alias_value":"CJTPKVQDG6VC4KBZ","created_at":"2026-07-05T11:17:22Z"},{"alias_kind":"pith_short_8","alias_value":"CJTPKVQD","created_at":"2026-07-05T11:17:22Z"}],"graph_snapshots":[{"event_id":"sha256:4a4f1cd572ac7e5f271b291be374d13d7ee1ec18b89b027ccc7d9e88d6a4d896","target":"graph","created_at":"2026-07-05T11:17:22Z","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/2411.12019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to control an unknown dynamical system with respect to high-level temporal specifications is an important problem in control theory. We present the first regret-free online algorithm for learning a controller for linear temporal logic (LTL) specifications for systems with unknown dynamics. We assume that the underlying (unknown) dynamics is modeled by a finite-state and action Markov decision process (MDP). Our core technical result is a regret-free learning algorithm for infinite-horizon reach-avoid problems on MDPs. For general LTL specifications, we show that the synthesis problem ","authors_text":"Mahmoud Salamati, Rupak Majumdar, Sadegh Soudjani","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-18T20:01:45Z","title":"Regret-Free Reinforcement Learning for LTL Specifications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12019","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:d3ac416f754e9dce3243d1edb424a56f27f2ea15a2683c0e348018ea914eacd6","target":"record","created_at":"2026-07-05T11:17:22Z","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":"104cdff2839e200118af12ba302d994c4bafa3ee40ddf0e37f843b3dd4508b9d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-18T20:01:45Z","title_canon_sha256":"e60707db5edf3b1351847e4055a1d7034676a9a481d3786053e7584f5e0d728d"},"schema_version":"1.0","source":{"id":"2411.12019","kind":"arxiv","version":2}},"canonical_sha256":"1266f5560337aa2e28394bc4a478c942ae67c85be6a1240eb24303ba751f6642","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1266f5560337aa2e28394bc4a478c942ae67c85be6a1240eb24303ba751f6642","first_computed_at":"2026-07-05T11:17:22.919078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:22.919078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0ItfYYZ2nMfLwtbi7/3tlvVnNcVNT6dkjhcYpOY3rmX3n3n+f5aw1F52e2wg9un+kMLLoeD+ZkzZOE5PDhgTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:22.919539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12019","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d3ac416f754e9dce3243d1edb424a56f27f2ea15a2683c0e348018ea914eacd6","sha256:4a4f1cd572ac7e5f271b291be374d13d7ee1ec18b89b027ccc7d9e88d6a4d896"],"state_sha256":"a81388dd39297c3d43a2d7d1748de507f9671f03c1fa55565583ecfec8ba857c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R1uf/bkwzCR1LMVV5mAduXep3JScsfekdG2ZXFkCxESOw8PW4NRQylb1M13pdM1ICJFxHPgB6IIMMtat0gs6BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T05:34:57.789201Z","bundle_sha256":"f11bf5ee6de9f787ae7a68edf0f23a32cfbd4745a02794095f1591b60ab7636c"}}