{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CWSZBWRVG2UBEN3UE7PP45ODSN","short_pith_number":"pith:CWSZBWRV","canonical_record":{"source":{"id":"2512.14617","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-16T17:26:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"502ad6fc66fd939022275f2762c329011ab1ce3848628a700e4b47053abc098e","abstract_canon_sha256":"14328e67a678e9dbd219f8be2ea947f8bdf04ea77c9d42f637259d3fd9b8457c"},"schema_version":"1.0"},"canonical_sha256":"15a590da3536a812377427defe75c393489fa3ad80aba566eb968766f0cab585","source":{"kind":"arxiv","id":"2512.14617","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.14617","created_at":"2026-06-10T01:08:30Z"},{"alias_kind":"arxiv_version","alias_value":"2512.14617v2","created_at":"2026-06-10T01:08:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.14617","created_at":"2026-06-10T01:08:30Z"},{"alias_kind":"pith_short_12","alias_value":"CWSZBWRVG2UB","created_at":"2026-06-10T01:08:30Z"},{"alias_kind":"pith_short_16","alias_value":"CWSZBWRVG2UBEN3U","created_at":"2026-06-10T01:08:30Z"},{"alias_kind":"pith_short_8","alias_value":"CWSZBWRV","created_at":"2026-06-10T01:08:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CWSZBWRVG2UBEN3UE7PP45ODSN","target":"record","payload":{"canonical_record":{"source":{"id":"2512.14617","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-16T17:26:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"502ad6fc66fd939022275f2762c329011ab1ce3848628a700e4b47053abc098e","abstract_canon_sha256":"14328e67a678e9dbd219f8be2ea947f8bdf04ea77c9d42f637259d3fd9b8457c"},"schema_version":"1.0"},"canonical_sha256":"15a590da3536a812377427defe75c393489fa3ad80aba566eb968766f0cab585","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:08:30.944065Z","signature_b64":"1vrOE6I96BTHNbVG4yNhOMkcv8JgFQOlkGEcXuI7Fg++mp0ves/zdzyiW4vPjZyq/UasPEEUhL6yxXfSndMuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15a590da3536a812377427defe75c393489fa3ad80aba566eb968766f0cab585","last_reissued_at":"2026-06-10T01:08:30.943144Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:08:30.943144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.14617","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":"2026-06-10T01:08:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P/w7HPEeAiafzYHDbuP4wdF/aczebEd2WZ1a9NkLk2fI5QnZzGb+wMaLhWXW0C/N0iOBePo/t3lXTBsVS+Y8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:17:48.435415Z"},"content_sha256":"acb14b3b63d6f0d21b2995bfe58e233ed8b5d7f11aa49de3b38981f90b89d54e","schema_version":"1.0","event_id":"sha256:acb14b3b63d6f0d21b2995bfe58e233ed8b5d7f11aa49de3b38981f90b89d54e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CWSZBWRVG2UBEN3UE7PP45ODSN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alessandro Trapasso, Fabio Patrizi, Luca Iocchi","submitted_at":"2025-12-16T17:26:24Z","abstract_excerpt":"Many practical decision-making problems involve tasks whose success depends on the entire system history, rather than on achieving a state with desired properties. Markovian Reinforcement Learning (RL) approaches are not suitable for such tasks, while RL with non-Markovian reward decision processes (NMRDPs) enables agents to tackle temporal-dependency tasks. This approach has long been known to lack formal guarantees on both (near-)optimality and sample efficiency. We contribute to solving both issues with QR-MAX, a novel model-based algorithm for discrete NMRDPs that factorizes Markovian tran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.14617","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/2512.14617/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":"2026-06-10T01:08:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bd84TeTROrSqRK3Nhs9bFFCy21lL+72tBHFccwLgIhafdWXNQZn+LEGUdo4tPRi107pGCPDcKI6aPpzkenWVCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:17:48.435969Z"},"content_sha256":"4fa0bd8813f336d37ac14aa7f0540fc03c92b56ae5880d52325d117c8b90f896","schema_version":"1.0","event_id":"sha256:4fa0bd8813f336d37ac14aa7f0540fc03c92b56ae5880d52325d117c8b90f896"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CWSZBWRVG2UBEN3UE7PP45ODSN/bundle.json","state_url":"https://pith.science/pith/CWSZBWRVG2UBEN3UE7PP45ODSN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CWSZBWRVG2UBEN3UE7PP45ODSN/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":"2026-08-16T22:17:48Z","links":{"resolver":"https://pith.science/pith/CWSZBWRVG2UBEN3UE7PP45ODSN","bundle":"https://pith.science/pith/CWSZBWRVG2UBEN3UE7PP45ODSN/bundle.json","state":"https://pith.science/pith/CWSZBWRVG2UBEN3UE7PP45ODSN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CWSZBWRVG2UBEN3UE7PP45ODSN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CWSZBWRVG2UBEN3UE7PP45ODSN","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":"14328e67a678e9dbd219f8be2ea947f8bdf04ea77c9d42f637259d3fd9b8457c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-16T17:26:24Z","title_canon_sha256":"502ad6fc66fd939022275f2762c329011ab1ce3848628a700e4b47053abc098e"},"schema_version":"1.0","source":{"id":"2512.14617","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.14617","created_at":"2026-06-10T01:08:30Z"},{"alias_kind":"arxiv_version","alias_value":"2512.14617v2","created_at":"2026-06-10T01:08:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.14617","created_at":"2026-06-10T01:08:30Z"},{"alias_kind":"pith_short_12","alias_value":"CWSZBWRVG2UB","created_at":"2026-06-10T01:08:30Z"},{"alias_kind":"pith_short_16","alias_value":"CWSZBWRVG2UBEN3U","created_at":"2026-06-10T01:08:30Z"},{"alias_kind":"pith_short_8","alias_value":"CWSZBWRV","created_at":"2026-06-10T01:08:30Z"}],"graph_snapshots":[{"event_id":"sha256:4fa0bd8813f336d37ac14aa7f0540fc03c92b56ae5880d52325d117c8b90f896","target":"graph","created_at":"2026-06-10T01:08:30Z","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/2512.14617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many practical decision-making problems involve tasks whose success depends on the entire system history, rather than on achieving a state with desired properties. Markovian Reinforcement Learning (RL) approaches are not suitable for such tasks, while RL with non-Markovian reward decision processes (NMRDPs) enables agents to tackle temporal-dependency tasks. This approach has long been known to lack formal guarantees on both (near-)optimality and sample efficiency. We contribute to solving both issues with QR-MAX, a novel model-based algorithm for discrete NMRDPs that factorizes Markovian tran","authors_text":"Alessandro Trapasso, Fabio Patrizi, Luca Iocchi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-16T17:26:24Z","title":"Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.14617","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:acb14b3b63d6f0d21b2995bfe58e233ed8b5d7f11aa49de3b38981f90b89d54e","target":"record","created_at":"2026-06-10T01:08:30Z","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":"14328e67a678e9dbd219f8be2ea947f8bdf04ea77c9d42f637259d3fd9b8457c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-12-16T17:26:24Z","title_canon_sha256":"502ad6fc66fd939022275f2762c329011ab1ce3848628a700e4b47053abc098e"},"schema_version":"1.0","source":{"id":"2512.14617","kind":"arxiv","version":2}},"canonical_sha256":"15a590da3536a812377427defe75c393489fa3ad80aba566eb968766f0cab585","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15a590da3536a812377427defe75c393489fa3ad80aba566eb968766f0cab585","first_computed_at":"2026-06-10T01:08:30.943144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:08:30.943144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1vrOE6I96BTHNbVG4yNhOMkcv8JgFQOlkGEcXuI7Fg++mp0ves/zdzyiW4vPjZyq/UasPEEUhL6yxXfSndMuDw==","signature_status":"signed_v1","signed_at":"2026-06-10T01:08:30.944065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.14617","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acb14b3b63d6f0d21b2995bfe58e233ed8b5d7f11aa49de3b38981f90b89d54e","sha256:4fa0bd8813f336d37ac14aa7f0540fc03c92b56ae5880d52325d117c8b90f896"],"state_sha256":"733c903e1b80ee87b23e5efb1c93a3b533112ebfc1517e792791e60affe62dfe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qTNI9lO+FAmjlQcM+dZxgqPACdZmiUOcIWtDC8OZRNun64fvS/mm0Ah1tcFUbFEz8J0fJ/m3PZmT7UTDObMdCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T22:17:48.439091Z","bundle_sha256":"e17d0856949f31f4afb4061e27dcadf752b4f9690ec2c08f119ed236b258bdd5"}}