{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UDTVJDNJQ5EPUYUQXO5GWEXRRC","short_pith_number":"pith:UDTVJDNJ","canonical_record":{"source":{"id":"1809.07823","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T19:52:06Z","cross_cats_sorted":["cs.FL","cs.LO","stat.ML"],"title_canon_sha256":"460b158b9f356a5d11af1a0af3506e843859a89f066dd5a7af1152cacb158d21","abstract_canon_sha256":"ce2e01491a00d7ac04abdadd7e4e7e35ea58f5a6e4033760427d8bd47d982472"},"schema_version":"1.0"},"canonical_sha256":"a0e7548da98748fa6290bbba6b12f188bfba2c665242b64127cdf85964764e8b","source":{"kind":"arxiv","id":"1809.07823","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.07823","created_at":"2026-05-17T23:51:19Z"},{"alias_kind":"arxiv_version","alias_value":"1809.07823v4","created_at":"2026-05-17T23:51:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.07823","created_at":"2026-05-17T23:51:19Z"},{"alias_kind":"pith_short_12","alias_value":"UDTVJDNJQ5EP","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UDTVJDNJQ5EPUYUQ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UDTVJDNJ","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UDTVJDNJQ5EPUYUQXO5GWEXRRC","target":"record","payload":{"canonical_record":{"source":{"id":"1809.07823","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T19:52:06Z","cross_cats_sorted":["cs.FL","cs.LO","stat.ML"],"title_canon_sha256":"460b158b9f356a5d11af1a0af3506e843859a89f066dd5a7af1152cacb158d21","abstract_canon_sha256":"ce2e01491a00d7ac04abdadd7e4e7e35ea58f5a6e4033760427d8bd47d982472"},"schema_version":"1.0"},"canonical_sha256":"a0e7548da98748fa6290bbba6b12f188bfba2c665242b64127cdf85964764e8b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:19.521560Z","signature_b64":"//mKhjzZvPouzux2Bk2CYOPT6Ye2spUHLGC4EZ92QjY0IrdeckTYwr8M5XyqE+8NpbV6uWIAYbFir/Zi9o9FBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0e7548da98748fa6290bbba6b12f188bfba2c665242b64127cdf85964764e8b","last_reissued_at":"2026-05-17T23:51:19.521092Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:19.521092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.07823","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VhRvbPVKNw7SwSLlmpNkzSrvxr0lxoIvcXqh2bAS7E33BhzAToW17lkYjO3lcVMBDM3zSkaVEma000Q+kpeeAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T18:02:56.097960Z"},"content_sha256":"99d40c06699d082afc678485717579b3d91573d77f12a91bd6d4d43f79b3dbe5","schema_version":"1.0","event_id":"sha256:99d40c06699d082afc678485717579b3d91573d77f12a91bd6d4d43f79b3dbe5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UDTVJDNJQ5EPUYUQXO5GWEXRRC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Logically-Constrained Neural Fitted Q-Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.FL","cs.LO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Abate, Daniel Kroening, Mohammadhosein Hasanbeig","submitted_at":"2018-09-20T19:52:06Z","abstract_excerpt":"We propose a method for efficient training of Q-functions for continuous-state Markov Decision Processes (MDPs) such that the traces of the resulting policies satisfy a given Linear Temporal Logic (LTL) property. LTL, a modal logic, can express a wide range of time-dependent logical properties (including \"safety\") that are quite similar to patterns in natural language. We convert the LTL property into a limit deterministic Buchi automaton and construct an on-the-fly synchronised product MDP. The control policy is then synthesised by defining an adaptive reward function and by applying a modifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.07823","kind":"arxiv","version":4},"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":"2026-05-17T23:51:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aSgW00DfAT009AVDF3EbpnuryOGqVHfjn2dLgcfpvtnhB+UPeEHKcbW40TsOk41wV0rMbi6dc2/OnSF9nDXLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T18:02:56.098358Z"},"content_sha256":"7836287416db8d7adb6bcb6638fa0c42ca996617edd05aef5a0ffa53c8b1e532","schema_version":"1.0","event_id":"sha256:7836287416db8d7adb6bcb6638fa0c42ca996617edd05aef5a0ffa53c8b1e532"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UDTVJDNJQ5EPUYUQXO5GWEXRRC/bundle.json","state_url":"https://pith.science/pith/UDTVJDNJQ5EPUYUQXO5GWEXRRC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UDTVJDNJQ5EPUYUQXO5GWEXRRC/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":"2026-06-02T18:02:56Z","links":{"resolver":"https://pith.science/pith/UDTVJDNJQ5EPUYUQXO5GWEXRRC","bundle":"https://pith.science/pith/UDTVJDNJQ5EPUYUQXO5GWEXRRC/bundle.json","state":"https://pith.science/pith/UDTVJDNJQ5EPUYUQXO5GWEXRRC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UDTVJDNJQ5EPUYUQXO5GWEXRRC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UDTVJDNJQ5EPUYUQXO5GWEXRRC","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":"ce2e01491a00d7ac04abdadd7e4e7e35ea58f5a6e4033760427d8bd47d982472","cross_cats_sorted":["cs.FL","cs.LO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T19:52:06Z","title_canon_sha256":"460b158b9f356a5d11af1a0af3506e843859a89f066dd5a7af1152cacb158d21"},"schema_version":"1.0","source":{"id":"1809.07823","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.07823","created_at":"2026-05-17T23:51:19Z"},{"alias_kind":"arxiv_version","alias_value":"1809.07823v4","created_at":"2026-05-17T23:51:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.07823","created_at":"2026-05-17T23:51:19Z"},{"alias_kind":"pith_short_12","alias_value":"UDTVJDNJQ5EP","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UDTVJDNJQ5EPUYUQ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UDTVJDNJ","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:7836287416db8d7adb6bcb6638fa0c42ca996617edd05aef5a0ffa53c8b1e532","target":"graph","created_at":"2026-05-17T23:51:19Z","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 propose a method for efficient training of Q-functions for continuous-state Markov Decision Processes (MDPs) such that the traces of the resulting policies satisfy a given Linear Temporal Logic (LTL) property. LTL, a modal logic, can express a wide range of time-dependent logical properties (including \"safety\") that are quite similar to patterns in natural language. We convert the LTL property into a limit deterministic Buchi automaton and construct an on-the-fly synchronised product MDP. The control policy is then synthesised by defining an adaptive reward function and by applying a modifi","authors_text":"Alessandro Abate, Daniel Kroening, Mohammadhosein Hasanbeig","cross_cats":["cs.FL","cs.LO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T19:52:06Z","title":"Logically-Constrained Neural Fitted Q-Iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.07823","kind":"arxiv","version":4},"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":"sha256:99d40c06699d082afc678485717579b3d91573d77f12a91bd6d4d43f79b3dbe5","target":"record","created_at":"2026-05-17T23:51:19Z","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":"ce2e01491a00d7ac04abdadd7e4e7e35ea58f5a6e4033760427d8bd47d982472","cross_cats_sorted":["cs.FL","cs.LO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T19:52:06Z","title_canon_sha256":"460b158b9f356a5d11af1a0af3506e843859a89f066dd5a7af1152cacb158d21"},"schema_version":"1.0","source":{"id":"1809.07823","kind":"arxiv","version":4}},"canonical_sha256":"a0e7548da98748fa6290bbba6b12f188bfba2c665242b64127cdf85964764e8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0e7548da98748fa6290bbba6b12f188bfba2c665242b64127cdf85964764e8b","first_computed_at":"2026-05-17T23:51:19.521092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:19.521092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"//mKhjzZvPouzux2Bk2CYOPT6Ye2spUHLGC4EZ92QjY0IrdeckTYwr8M5XyqE+8NpbV6uWIAYbFir/Zi9o9FBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:19.521560Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.07823","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99d40c06699d082afc678485717579b3d91573d77f12a91bd6d4d43f79b3dbe5","sha256:7836287416db8d7adb6bcb6638fa0c42ca996617edd05aef5a0ffa53c8b1e532"],"state_sha256":"909418eb98c2b75832ca87424d6a90c1860655d89ede6d2dac33823f7cfed9ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vstLhdhQWh1rLR7w/YhqaJ7lrt6ifdGMIJuro53YYKM3UUNBHu3B6D3CdQOeGDt0hn4IKP2lTgihKyRtWXOADw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T18:02:56.100362Z","bundle_sha256":"ddc4ba342c571face307f69464c9265894b3a126ee16ea84f03e6cb4e8872d3a"}}