{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4BKZLI6ETBVXCCWO6DELBPC3OO","short_pith_number":"pith:4BKZLI6E","canonical_record":{"source":{"id":"2305.01381","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-02T12:57:05Z","cross_cats_sorted":["cs.AI","cs.FL","cs.RO"],"title_canon_sha256":"05e91177aa4cdcd051d37360b76dfd87df14777e60c831f3dfe85dffbffc7f37","abstract_canon_sha256":"a8aa84804405f3fd668c8ffc1d4767b157fc7487da63b2b3a3869b7ee84d96bc"},"schema_version":"1.0"},"canonical_sha256":"e05595a3c4986b710acef0c8b0bc5b73af4d381371ca57d48c5e9290edfb24fa","source":{"kind":"arxiv","id":"2305.01381","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.01381","created_at":"2026-07-05T07:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.01381v2","created_at":"2026-07-05T07:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01381","created_at":"2026-07-05T07:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"4BKZLI6ETBVX","created_at":"2026-07-05T07:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"4BKZLI6ETBVXCCWO","created_at":"2026-07-05T07:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"4BKZLI6E","created_at":"2026-07-05T07:04:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4BKZLI6ETBVXCCWO6DELBPC3OO","target":"record","payload":{"canonical_record":{"source":{"id":"2305.01381","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-02T12:57:05Z","cross_cats_sorted":["cs.AI","cs.FL","cs.RO"],"title_canon_sha256":"05e91177aa4cdcd051d37360b76dfd87df14777e60c831f3dfe85dffbffc7f37","abstract_canon_sha256":"a8aa84804405f3fd668c8ffc1d4767b157fc7487da63b2b3a3869b7ee84d96bc"},"schema_version":"1.0"},"canonical_sha256":"e05595a3c4986b710acef0c8b0bc5b73af4d381371ca57d48c5e9290edfb24fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:46.710732Z","signature_b64":"Musi1oamdiZCPo0rzPoItSLo2ytPwvKQIDaqlmeyLjFdt3MiM5pjqc7F9nx8VqNOLaBfvOp4JuHZIJSGR6y9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e05595a3c4986b710acef0c8b0bc5b73af4d381371ca57d48c5e9290edfb24fa","last_reissued_at":"2026-07-05T07:04:46.710185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:46.710185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.01381","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":"2026-07-05T07:04:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4gPyZ2MKOH38q0oc5LFQDMva29Xmi1J7gc/GyOyDyRqXESmigAPjwkUyepOIWKl5X43ymMApeeXWICuv5KYkBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:31:39.955737Z"},"content_sha256":"cde24069c09864f090657481a101149eb01e81ee09af3b7b32e329a30a53c4c8","schema_version":"1.0","event_id":"sha256:cde24069c09864f090657481a101149eb01e81ee09af3b7b32e329a30a53c4c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4BKZLI6ETBVXCCWO6DELBPC3OO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.FL","cs.RO"],"primary_cat":"cs.LG","authors_text":"Daqian Shao, Marta Kwiatkowska","submitted_at":"2023-05-02T12:57:05Z","abstract_excerpt":"Linear Temporal Logic (LTL) is widely used to specify high-level objectives for system policies, and it is highly desirable for autonomous systems to learn the optimal policy with respect to such specifications. However, learning the optimal policy from LTL specifications is not trivial. We present a model-free Reinforcement Learning (RL) approach that efficiently learns an optimal policy for an unknown stochastic system, modelled using Markov Decision Processes (MDPs). We propose a novel and more general product MDP, reward structure and discounting mechanism that, when applied in conjunction"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01381","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/2305.01381/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":"2026-07-05T07:04:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5GrvlOAy0hS2gymNKC0xBipzHoy59KJSUwv/+swzRaeg6843CwJbkV66L8Y0+eHZ8sRmJvT3vbcL9ZMpHWwADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:31:39.956122Z"},"content_sha256":"66af73b70919012f7f65219f532ce5362b0dd74b8c1dad796fb80cdd33306480","schema_version":"1.0","event_id":"sha256:66af73b70919012f7f65219f532ce5362b0dd74b8c1dad796fb80cdd33306480"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4BKZLI6ETBVXCCWO6DELBPC3OO/bundle.json","state_url":"https://pith.science/pith/4BKZLI6ETBVXCCWO6DELBPC3OO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4BKZLI6ETBVXCCWO6DELBPC3OO/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":"2026-07-07T11:31:39Z","links":{"resolver":"https://pith.science/pith/4BKZLI6ETBVXCCWO6DELBPC3OO","bundle":"https://pith.science/pith/4BKZLI6ETBVXCCWO6DELBPC3OO/bundle.json","state":"https://pith.science/pith/4BKZLI6ETBVXCCWO6DELBPC3OO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4BKZLI6ETBVXCCWO6DELBPC3OO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4BKZLI6ETBVXCCWO6DELBPC3OO","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":"a8aa84804405f3fd668c8ffc1d4767b157fc7487da63b2b3a3869b7ee84d96bc","cross_cats_sorted":["cs.AI","cs.FL","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-02T12:57:05Z","title_canon_sha256":"05e91177aa4cdcd051d37360b76dfd87df14777e60c831f3dfe85dffbffc7f37"},"schema_version":"1.0","source":{"id":"2305.01381","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.01381","created_at":"2026-07-05T07:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.01381v2","created_at":"2026-07-05T07:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01381","created_at":"2026-07-05T07:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"4BKZLI6ETBVX","created_at":"2026-07-05T07:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"4BKZLI6ETBVXCCWO","created_at":"2026-07-05T07:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"4BKZLI6E","created_at":"2026-07-05T07:04:46Z"}],"graph_snapshots":[{"event_id":"sha256:66af73b70919012f7f65219f532ce5362b0dd74b8c1dad796fb80cdd33306480","target":"graph","created_at":"2026-07-05T07:04:46Z","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/2305.01381/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Linear Temporal Logic (LTL) is widely used to specify high-level objectives for system policies, and it is highly desirable for autonomous systems to learn the optimal policy with respect to such specifications. However, learning the optimal policy from LTL specifications is not trivial. We present a model-free Reinforcement Learning (RL) approach that efficiently learns an optimal policy for an unknown stochastic system, modelled using Markov Decision Processes (MDPs). We propose a novel and more general product MDP, reward structure and discounting mechanism that, when applied in conjunction","authors_text":"Daqian Shao, Marta Kwiatkowska","cross_cats":["cs.AI","cs.FL","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-02T12:57:05Z","title":"Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01381","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:cde24069c09864f090657481a101149eb01e81ee09af3b7b32e329a30a53c4c8","target":"record","created_at":"2026-07-05T07:04:46Z","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":"a8aa84804405f3fd668c8ffc1d4767b157fc7487da63b2b3a3869b7ee84d96bc","cross_cats_sorted":["cs.AI","cs.FL","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-02T12:57:05Z","title_canon_sha256":"05e91177aa4cdcd051d37360b76dfd87df14777e60c831f3dfe85dffbffc7f37"},"schema_version":"1.0","source":{"id":"2305.01381","kind":"arxiv","version":2}},"canonical_sha256":"e05595a3c4986b710acef0c8b0bc5b73af4d381371ca57d48c5e9290edfb24fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e05595a3c4986b710acef0c8b0bc5b73af4d381371ca57d48c5e9290edfb24fa","first_computed_at":"2026-07-05T07:04:46.710185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:46.710185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Musi1oamdiZCPo0rzPoItSLo2ytPwvKQIDaqlmeyLjFdt3MiM5pjqc7F9nx8VqNOLaBfvOp4JuHZIJSGR6y9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:46.710732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.01381","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cde24069c09864f090657481a101149eb01e81ee09af3b7b32e329a30a53c4c8","sha256:66af73b70919012f7f65219f532ce5362b0dd74b8c1dad796fb80cdd33306480"],"state_sha256":"8a1375976ca3f5723fb7f52077e9f6890496c8662d08c2ca7a64be6b54959b52"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AoQsJwFoHuRRI1kqHoDpfRfLOb7F7tPwbQoV3J+CSihZ0zSGq1vcKniBcArXc7IMCAQGiArt9I/vFbH5ImbJCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:31:39.958182Z","bundle_sha256":"b610c64aa55a15dfa0d22b453b08f4884ce20758d3f43d3b047a3f0f9d08aed8"}}