{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2YZ2Y47EZ5IRI76INE3CVJF3H4","short_pith_number":"pith:2YZ2Y47E","canonical_record":{"source":{"id":"2408.09495","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-18T14:25:44Z","cross_cats_sorted":[],"title_canon_sha256":"470b8579aa743ff9272955249ac66a6556b960d1abb266f50f267cb57903a8af","abstract_canon_sha256":"fad164356e4c025cb3e033fe8793f876d0c89811edb4ee7deb9666a982b7bbd9"},"schema_version":"1.0"},"canonical_sha256":"d633ac73e4cf51147fc869362aa4bb3f336cde7d3e0bda077a6335468e23a6b9","source":{"kind":"arxiv","id":"2408.09495","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09495","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09495v2","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09495","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_12","alias_value":"2YZ2Y47EZ5IR","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_16","alias_value":"2YZ2Y47EZ5IRI76I","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_8","alias_value":"2YZ2Y47E","created_at":"2026-07-05T11:18:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2YZ2Y47EZ5IRI76INE3CVJF3H4","target":"record","payload":{"canonical_record":{"source":{"id":"2408.09495","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-18T14:25:44Z","cross_cats_sorted":[],"title_canon_sha256":"470b8579aa743ff9272955249ac66a6556b960d1abb266f50f267cb57903a8af","abstract_canon_sha256":"fad164356e4c025cb3e033fe8793f876d0c89811edb4ee7deb9666a982b7bbd9"},"schema_version":"1.0"},"canonical_sha256":"d633ac73e4cf51147fc869362aa4bb3f336cde7d3e0bda077a6335468e23a6b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:39.405715Z","signature_b64":"MS7z1azMqtv/zZuHpn+tJsmx8Fr+wDuMSEwGO//6Hy4QQcqYVz8zz3P1h8L/qyTUxovr7M1VCjBU9wKfs8wRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d633ac73e4cf51147fc869362aa4bb3f336cde7d3e0bda077a6335468e23a6b9","last_reissued_at":"2026-07-05T11:18:39.405203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:39.405203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.09495","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":"2026-07-05T11:18:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EfNqX56k7AahJoNLrvQS68/VzowBX0cGHaG0QItnBi64fRB2HUiZ4zp0s8SxYHITFiXU6Zvrrdp5Y4jw4uIXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:33:27.356129Z"},"content_sha256":"d138261e616b6a774add0c44a64b47d13f55131d6fd318def0b32c9d84eafa42","schema_version":"1.0","event_id":"sha256:d138261e616b6a774add0c44a64b47d13f55131d6fd318def0b32c9d84eafa42"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2YZ2Y47EZ5IRI76INE3CVJF3H4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Directed Exploration in Reinforcement Learning from Linear Temporal Logic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Georg Martius, Marco Bagatella","submitted_at":"2024-08-18T14:25:44Z","abstract_excerpt":"Linear temporal logic (LTL) is a powerful language for task specification in reinforcement learning, as it allows describing objectives beyond the expressivity of conventional discounted return formulations. Nonetheless, recent works have shown that LTL formulas can be translated into a variable rewarding and discounting scheme, whose optimization produces a policy maximizing a lower bound on the probability of formula satisfaction. However, the synthesized reward signal remains fundamentally sparse, making exploration challenging. We aim to overcome this limitation, which can prevent current "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09495","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/2408.09495/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":"2026-07-05T11:18:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/nS4DZ/Zka1BvDHFQA95NswWdRbySdzg5ucBIVJBmCGp+P7/MqnMRtFzfru2DqD8ic/xce1VK83q04wUwravDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:33:27.356838Z"},"content_sha256":"a9ba3cb27f414751e10c71a7132ec20de9535e2f874c19040736b7e9a1a60562","schema_version":"1.0","event_id":"sha256:a9ba3cb27f414751e10c71a7132ec20de9535e2f874c19040736b7e9a1a60562"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2YZ2Y47EZ5IRI76INE3CVJF3H4/bundle.json","state_url":"https://pith.science/pith/2YZ2Y47EZ5IRI76INE3CVJF3H4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2YZ2Y47EZ5IRI76INE3CVJF3H4/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":"2026-07-07T06:33:27Z","links":{"resolver":"https://pith.science/pith/2YZ2Y47EZ5IRI76INE3CVJF3H4","bundle":"https://pith.science/pith/2YZ2Y47EZ5IRI76INE3CVJF3H4/bundle.json","state":"https://pith.science/pith/2YZ2Y47EZ5IRI76INE3CVJF3H4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2YZ2Y47EZ5IRI76INE3CVJF3H4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2YZ2Y47EZ5IRI76INE3CVJF3H4","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":"fad164356e4c025cb3e033fe8793f876d0c89811edb4ee7deb9666a982b7bbd9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-18T14:25:44Z","title_canon_sha256":"470b8579aa743ff9272955249ac66a6556b960d1abb266f50f267cb57903a8af"},"schema_version":"1.0","source":{"id":"2408.09495","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09495","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09495v2","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09495","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_12","alias_value":"2YZ2Y47EZ5IR","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_16","alias_value":"2YZ2Y47EZ5IRI76I","created_at":"2026-07-05T11:18:39Z"},{"alias_kind":"pith_short_8","alias_value":"2YZ2Y47E","created_at":"2026-07-05T11:18:39Z"}],"graph_snapshots":[{"event_id":"sha256:a9ba3cb27f414751e10c71a7132ec20de9535e2f874c19040736b7e9a1a60562","target":"graph","created_at":"2026-07-05T11:18:39Z","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/2408.09495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Linear temporal logic (LTL) is a powerful language for task specification in reinforcement learning, as it allows describing objectives beyond the expressivity of conventional discounted return formulations. Nonetheless, recent works have shown that LTL formulas can be translated into a variable rewarding and discounting scheme, whose optimization produces a policy maximizing a lower bound on the probability of formula satisfaction. However, the synthesized reward signal remains fundamentally sparse, making exploration challenging. We aim to overcome this limitation, which can prevent current ","authors_text":"Andreas Krause, Georg Martius, Marco Bagatella","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-18T14:25:44Z","title":"Directed Exploration in Reinforcement Learning from Linear Temporal Logic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09495","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:d138261e616b6a774add0c44a64b47d13f55131d6fd318def0b32c9d84eafa42","target":"record","created_at":"2026-07-05T11:18:39Z","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":"fad164356e4c025cb3e033fe8793f876d0c89811edb4ee7deb9666a982b7bbd9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-18T14:25:44Z","title_canon_sha256":"470b8579aa743ff9272955249ac66a6556b960d1abb266f50f267cb57903a8af"},"schema_version":"1.0","source":{"id":"2408.09495","kind":"arxiv","version":2}},"canonical_sha256":"d633ac73e4cf51147fc869362aa4bb3f336cde7d3e0bda077a6335468e23a6b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d633ac73e4cf51147fc869362aa4bb3f336cde7d3e0bda077a6335468e23a6b9","first_computed_at":"2026-07-05T11:18:39.405203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:39.405203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MS7z1azMqtv/zZuHpn+tJsmx8Fr+wDuMSEwGO//6Hy4QQcqYVz8zz3P1h8L/qyTUxovr7M1VCjBU9wKfs8wRBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:39.405715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.09495","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d138261e616b6a774add0c44a64b47d13f55131d6fd318def0b32c9d84eafa42","sha256:a9ba3cb27f414751e10c71a7132ec20de9535e2f874c19040736b7e9a1a60562"],"state_sha256":"3e3a8d306ea0b97f4b93d043b97275bb8636e5aabb7a3b05a1d8d2ba24b29122"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YH88QCGRslCrTCJ+FXgUTx67Aty7bHbWJZWkFIXc3Uy3su2zXvGNb4GKiWQTfrsBFtSXckXyhMdqvvVB0IOJDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:33:27.360155Z","bundle_sha256":"9e91bc59a7547a4cea1bd3737e426176e4b4f2b3dc1642b074528a92ce299cd0"}}