{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:O4VOL625YSCLBB6V53K7YEOL6Y","short_pith_number":"pith:O4VOL625","canonical_record":{"source":{"id":"2003.01008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2020-03-02T16:36:16Z","cross_cats_sorted":[],"title_canon_sha256":"464ce242bf453d62f20ca248f102c55db82461d7c3677a2daa456fde539a1f6b","abstract_canon_sha256":"3ec93f534a4ba4e098f1bed6bd6232252a64a7dccebfe50a5442d64bf61b7d95"},"schema_version":"1.0"},"canonical_sha256":"772ae5fb5dc484b087d5eed5fc11cbf6153681d49615e46361df61959b52200e","source":{"kind":"arxiv","id":"2003.01008","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.01008","created_at":"2026-07-05T00:44:59Z"},{"alias_kind":"arxiv_version","alias_value":"2003.01008v1","created_at":"2026-07-05T00:44:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.01008","created_at":"2026-07-05T00:44:59Z"},{"alias_kind":"pith_short_12","alias_value":"O4VOL625YSCL","created_at":"2026-07-05T00:44:59Z"},{"alias_kind":"pith_short_16","alias_value":"O4VOL625YSCLBB6V","created_at":"2026-07-05T00:44:59Z"},{"alias_kind":"pith_short_8","alias_value":"O4VOL625","created_at":"2026-07-05T00:44:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:O4VOL625YSCLBB6V53K7YEOL6Y","target":"record","payload":{"canonical_record":{"source":{"id":"2003.01008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2020-03-02T16:36:16Z","cross_cats_sorted":[],"title_canon_sha256":"464ce242bf453d62f20ca248f102c55db82461d7c3677a2daa456fde539a1f6b","abstract_canon_sha256":"3ec93f534a4ba4e098f1bed6bd6232252a64a7dccebfe50a5442d64bf61b7d95"},"schema_version":"1.0"},"canonical_sha256":"772ae5fb5dc484b087d5eed5fc11cbf6153681d49615e46361df61959b52200e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:59.991373Z","signature_b64":"YO3xIyYRWGz0MtSTfYlNRqUu4rJO07IsqOrpSifDfd/7too6cvG01mOgJ2nyP9NkbdP25gyyHaObO9hk8hzTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"772ae5fb5dc484b087d5eed5fc11cbf6153681d49615e46361df61959b52200e","last_reissued_at":"2026-07-05T00:44:59.990906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:59.990906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.01008","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:44:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2hQGTfoJ/ukb2+bDw5bVzp8hvXq4qeSJeabF3FFj2hiy5Ym90dJTviWAPY1USKSJKpPpOMOBAU22APi38UnCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T14:48:55.516823Z"},"content_sha256":"1ec46cf92ad24cfbc65e0fe6e6b120fc7f9bbad8013157d218a36798cb830ad8","schema_version":"1.0","event_id":"sha256:1ec46cf92ad24cfbc65e0fe6e6b120fc7f9bbad8013157d218a36798cb830ad8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:O4VOL625YSCLBB6V53K7YEOL6Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning and Solving Regular Decision Processes","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Eden Abadi, Ronen I. Brafman","submitted_at":"2020-03-02T16:36:16Z","abstract_excerpt":"Regular Decision Processes (RDPs) are a recently introduced model that extends MDPs with non-Markovian dynamics and rewards. The non-Markovian behavior is restricted to depend on regular properties of the history. These can be specified using regular expressions or formulas in linear dynamic logic over finite traces. Fully specified RDPs can be solved by compiling them into an appropriate MDP. Learning RDPs from data is a challenging problem that has yet to be addressed, on which we focus in this paper. Our approach rests on a new representation for RDPs using Mealy Machines that emit a distri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.01008","kind":"arxiv","version":1},"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/2003.01008/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":"2026-07-05T00:44:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ArEa6BUfFPBCCjZ/YrbojNv12sdFEBH5M/NmqgP/yhHesorwXGheO96VLynyHHs1UNBcJ1zQCsorvLydLYnmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T14:48:55.517620Z"},"content_sha256":"8d1510bd2ac19d5b0ea6d861c576614c2864a095b5691c1e55c13a00f2cac88a","schema_version":"1.0","event_id":"sha256:8d1510bd2ac19d5b0ea6d861c576614c2864a095b5691c1e55c13a00f2cac88a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O4VOL625YSCLBB6V53K7YEOL6Y/bundle.json","state_url":"https://pith.science/pith/O4VOL625YSCLBB6V53K7YEOL6Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O4VOL625YSCLBB6V53K7YEOL6Y/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":"2026-08-22T14:48:55Z","links":{"resolver":"https://pith.science/pith/O4VOL625YSCLBB6V53K7YEOL6Y","bundle":"https://pith.science/pith/O4VOL625YSCLBB6V53K7YEOL6Y/bundle.json","state":"https://pith.science/pith/O4VOL625YSCLBB6V53K7YEOL6Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O4VOL625YSCLBB6V53K7YEOL6Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:O4VOL625YSCLBB6V53K7YEOL6Y","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":"3ec93f534a4ba4e098f1bed6bd6232252a64a7dccebfe50a5442d64bf61b7d95","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2020-03-02T16:36:16Z","title_canon_sha256":"464ce242bf453d62f20ca248f102c55db82461d7c3677a2daa456fde539a1f6b"},"schema_version":"1.0","source":{"id":"2003.01008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.01008","created_at":"2026-07-05T00:44:59Z"},{"alias_kind":"arxiv_version","alias_value":"2003.01008v1","created_at":"2026-07-05T00:44:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.01008","created_at":"2026-07-05T00:44:59Z"},{"alias_kind":"pith_short_12","alias_value":"O4VOL625YSCL","created_at":"2026-07-05T00:44:59Z"},{"alias_kind":"pith_short_16","alias_value":"O4VOL625YSCLBB6V","created_at":"2026-07-05T00:44:59Z"},{"alias_kind":"pith_short_8","alias_value":"O4VOL625","created_at":"2026-07-05T00:44:59Z"}],"graph_snapshots":[{"event_id":"sha256:8d1510bd2ac19d5b0ea6d861c576614c2864a095b5691c1e55c13a00f2cac88a","target":"graph","created_at":"2026-07-05T00:44:59Z","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/2003.01008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Regular Decision Processes (RDPs) are a recently introduced model that extends MDPs with non-Markovian dynamics and rewards. The non-Markovian behavior is restricted to depend on regular properties of the history. These can be specified using regular expressions or formulas in linear dynamic logic over finite traces. Fully specified RDPs can be solved by compiling them into an appropriate MDP. Learning RDPs from data is a challenging problem that has yet to be addressed, on which we focus in this paper. Our approach rests on a new representation for RDPs using Mealy Machines that emit a distri","authors_text":"Eden Abadi, Ronen I. Brafman","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2020-03-02T16:36:16Z","title":"Learning and Solving Regular Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.01008","kind":"arxiv","version":1},"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":"sha256:1ec46cf92ad24cfbc65e0fe6e6b120fc7f9bbad8013157d218a36798cb830ad8","target":"record","created_at":"2026-07-05T00:44:59Z","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":"3ec93f534a4ba4e098f1bed6bd6232252a64a7dccebfe50a5442d64bf61b7d95","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2020-03-02T16:36:16Z","title_canon_sha256":"464ce242bf453d62f20ca248f102c55db82461d7c3677a2daa456fde539a1f6b"},"schema_version":"1.0","source":{"id":"2003.01008","kind":"arxiv","version":1}},"canonical_sha256":"772ae5fb5dc484b087d5eed5fc11cbf6153681d49615e46361df61959b52200e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"772ae5fb5dc484b087d5eed5fc11cbf6153681d49615e46361df61959b52200e","first_computed_at":"2026-07-05T00:44:59.990906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:59.990906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YO3xIyYRWGz0MtSTfYlNRqUu4rJO07IsqOrpSifDfd/7too6cvG01mOgJ2nyP9NkbdP25gyyHaObO9hk8hzTAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:59.991373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.01008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ec46cf92ad24cfbc65e0fe6e6b120fc7f9bbad8013157d218a36798cb830ad8","sha256:8d1510bd2ac19d5b0ea6d861c576614c2864a095b5691c1e55c13a00f2cac88a"],"state_sha256":"53d0c56f67595c921a26997d13227f358c4c9b73d7e346d212a72c9f50d225f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gnShj1IlZwAuvfaKQK1tnN0iBVdHcQKQytnTdoBLfSAAdeFyd2ppZy54IqmDcMMgfCnkx6VVh0GsGe51Y6yXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T14:48:55.523522Z","bundle_sha256":"cd2c42d88938d3704ac2b3dc5da03f31e2fedeedea2a34c0f4819d42110e5265"}}