{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KKGH2MXAYCLOJK5XFLZVGHOELD","short_pith_number":"pith:KKGH2MXA","canonical_record":{"source":{"id":"2507.15532","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-21T12:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"6c57621d524bd73e66112c0ef26ff30128049916b38c666b121aac2854ab0ab5","abstract_canon_sha256":"7fdb0522b46e11316ff952eea924142e23076b935bcd12cad244e8301cb24503"},"schema_version":"1.0"},"canonical_sha256":"528c7d32e0c096e4abb72af3531dc458f5ac92185cd27c19220a516d1961fa73","source":{"kind":"arxiv","id":"2507.15532","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15532","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15532v2","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15532","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_12","alias_value":"KKGH2MXAYCLO","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_16","alias_value":"KKGH2MXAYCLOJK5X","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_8","alias_value":"KKGH2MXA","created_at":"2026-07-05T11:55:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KKGH2MXAYCLOJK5XFLZVGHOELD","target":"record","payload":{"canonical_record":{"source":{"id":"2507.15532","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-21T12:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"6c57621d524bd73e66112c0ef26ff30128049916b38c666b121aac2854ab0ab5","abstract_canon_sha256":"7fdb0522b46e11316ff952eea924142e23076b935bcd12cad244e8301cb24503"},"schema_version":"1.0"},"canonical_sha256":"528c7d32e0c096e4abb72af3531dc458f5ac92185cd27c19220a516d1961fa73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:41.447338Z","signature_b64":"NZ3F9PvwCmNEKhvOOHejGHzJcmzZzXLml9WHI568BLkhYpGxhQVa6rLO7fqDFPCcc4nmaBNNGMyqH8FdP4rKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"528c7d32e0c096e4abb72af3531dc458f5ac92185cd27c19220a516d1961fa73","last_reissued_at":"2026-07-05T11:55:41.446779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:41.446779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.15532","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":"2026-07-05T11:55:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a+mpHqweqcPc47itBxyB+KHtHG5qDdfBYIsuJnVRjWcWAiz7qQdVnu4kOHEx6kLSzR1v6MvQOxjgkuAFqAT8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:07:11.939737Z"},"content_sha256":"9e1ef4e1530daa35dc64d1ba81d158d96388135cbe78a2ef6cd6e52fadb084dd","schema_version":"1.0","event_id":"sha256:9e1ef4e1530daa35dc64d1ba81d158d96388135cbe78a2ef6cd6e52fadb084dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KKGH2MXAYCLOJK5XFLZVGHOELD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-Efficient Safe Policy Improvement Using Parametric Structure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guillermo A. P\\'erez, Kasper Engelen, Marnix Suilen","submitted_at":"2025-07-21T12:00:03Z","abstract_excerpt":"Safe policy improvement (SPI) is an offline reinforcement learning problem in which a new policy that reliably outperforms the behavior policy with high confidence needs to be computed using only a dataset and the behavior policy. Markov decision processes (MDPs) are the standard formalism for modeling environments in SPI. In many applications, additional information in the form of parametric dependencies between distributions in the transition dynamics is available. We make SPI more data-efficient by leveraging these dependencies through three contributions: (1) a parametric SPI algorithm tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15532","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/2507.15532/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":"2026-07-05T11:55:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AsUkXzrP1x2ym1sWDp9ialZI/X8Hvc7w+VEQFiz1I5rjnTG6v+hy3pn2qurj6gaxrN3nZI0P5fLcGRWRyVR7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:07:11.940366Z"},"content_sha256":"70c7db2c2efde36b2139efba2fa7500afed21d0b90aeba0a63078aa8398841ad","schema_version":"1.0","event_id":"sha256:70c7db2c2efde36b2139efba2fa7500afed21d0b90aeba0a63078aa8398841ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KKGH2MXAYCLOJK5XFLZVGHOELD/bundle.json","state_url":"https://pith.science/pith/KKGH2MXAYCLOJK5XFLZVGHOELD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KKGH2MXAYCLOJK5XFLZVGHOELD/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":"2026-08-11T19:07:11Z","links":{"resolver":"https://pith.science/pith/KKGH2MXAYCLOJK5XFLZVGHOELD","bundle":"https://pith.science/pith/KKGH2MXAYCLOJK5XFLZVGHOELD/bundle.json","state":"https://pith.science/pith/KKGH2MXAYCLOJK5XFLZVGHOELD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KKGH2MXAYCLOJK5XFLZVGHOELD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KKGH2MXAYCLOJK5XFLZVGHOELD","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":"7fdb0522b46e11316ff952eea924142e23076b935bcd12cad244e8301cb24503","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-21T12:00:03Z","title_canon_sha256":"6c57621d524bd73e66112c0ef26ff30128049916b38c666b121aac2854ab0ab5"},"schema_version":"1.0","source":{"id":"2507.15532","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15532","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15532v2","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15532","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_12","alias_value":"KKGH2MXAYCLO","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_16","alias_value":"KKGH2MXAYCLOJK5X","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_8","alias_value":"KKGH2MXA","created_at":"2026-07-05T11:55:41Z"}],"graph_snapshots":[{"event_id":"sha256:70c7db2c2efde36b2139efba2fa7500afed21d0b90aeba0a63078aa8398841ad","target":"graph","created_at":"2026-07-05T11:55:41Z","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/2507.15532/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe policy improvement (SPI) is an offline reinforcement learning problem in which a new policy that reliably outperforms the behavior policy with high confidence needs to be computed using only a dataset and the behavior policy. Markov decision processes (MDPs) are the standard formalism for modeling environments in SPI. In many applications, additional information in the form of parametric dependencies between distributions in the transition dynamics is available. We make SPI more data-efficient by leveraging these dependencies through three contributions: (1) a parametric SPI algorithm tha","authors_text":"Guillermo A. P\\'erez, Kasper Engelen, Marnix Suilen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-21T12:00:03Z","title":"Data-Efficient Safe Policy Improvement Using Parametric Structure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15532","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":"sha256:9e1ef4e1530daa35dc64d1ba81d158d96388135cbe78a2ef6cd6e52fadb084dd","target":"record","created_at":"2026-07-05T11:55:41Z","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":"7fdb0522b46e11316ff952eea924142e23076b935bcd12cad244e8301cb24503","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-21T12:00:03Z","title_canon_sha256":"6c57621d524bd73e66112c0ef26ff30128049916b38c666b121aac2854ab0ab5"},"schema_version":"1.0","source":{"id":"2507.15532","kind":"arxiv","version":2}},"canonical_sha256":"528c7d32e0c096e4abb72af3531dc458f5ac92185cd27c19220a516d1961fa73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"528c7d32e0c096e4abb72af3531dc458f5ac92185cd27c19220a516d1961fa73","first_computed_at":"2026-07-05T11:55:41.446779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:41.446779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NZ3F9PvwCmNEKhvOOHejGHzJcmzZzXLml9WHI568BLkhYpGxhQVa6rLO7fqDFPCcc4nmaBNNGMyqH8FdP4rKAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:41.447338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15532","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e1ef4e1530daa35dc64d1ba81d158d96388135cbe78a2ef6cd6e52fadb084dd","sha256:70c7db2c2efde36b2139efba2fa7500afed21d0b90aeba0a63078aa8398841ad"],"state_sha256":"8ba55e802c90c2eb58a7f42596644877965d12c246cc5da406d8ebc0faacec07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EuNmQh/KNPXKPg1UaayYZdZCRCptnHUf9lkTu9ZsHi38lXD4Vub2k8ND9YvyCVCjVhFUVJTxkkPUx9oCSk3TCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:07:11.945718Z","bundle_sha256":"830a24fa60cf47e61d548e581737867be4aaad4740cd0ce55129a042a6ee3e20"}}