{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:VYY4N65TMPCJEZAZPEA4XY36KG","short_pith_number":"pith:VYY4N65T","canonical_record":{"source":{"id":"1905.05787","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T18:39:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"281c5677c725cbcab3046e6ab033e31d3825063179e5f2cd5f886327c8466463","abstract_canon_sha256":"79585be76a2a46b20317792fed78fa13a7b62b9a7445365e754d145b5c186941"},"schema_version":"1.0"},"canonical_sha256":"ae31c6fbb363c49264197901cbe37e518af647b3efe6154b79f07a1e849ee07f","source":{"kind":"arxiv","id":"1905.05787","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05787","created_at":"2026-07-05T00:41:28Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05787v2","created_at":"2026-07-05T00:41:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05787","created_at":"2026-07-05T00:41:28Z"},{"alias_kind":"pith_short_12","alias_value":"VYY4N65TMPCJ","created_at":"2026-07-05T00:41:28Z"},{"alias_kind":"pith_short_16","alias_value":"VYY4N65TMPCJEZAZ","created_at":"2026-07-05T00:41:28Z"},{"alias_kind":"pith_short_8","alias_value":"VYY4N65T","created_at":"2026-07-05T00:41:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:VYY4N65TMPCJEZAZPEA4XY36KG","target":"record","payload":{"canonical_record":{"source":{"id":"1905.05787","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T18:39:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"281c5677c725cbcab3046e6ab033e31d3825063179e5f2cd5f886327c8466463","abstract_canon_sha256":"79585be76a2a46b20317792fed78fa13a7b62b9a7445365e754d145b5c186941"},"schema_version":"1.0"},"canonical_sha256":"ae31c6fbb363c49264197901cbe37e518af647b3efe6154b79f07a1e849ee07f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:41:28.238797Z","signature_b64":"q4omiTTP556iDgheG4aHtQcvh14y9tglTADcaLvhdsu+JLuDsKv1F6GhnIyyITLahTmOMefgD0nrkyLRY0yFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae31c6fbb363c49264197901cbe37e518af647b3efe6154b79f07a1e849ee07f","last_reissued_at":"2026-07-05T00:41:28.238331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:41:28.238331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.05787","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":"2026-07-05T00:41:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Z3D6xxb0lh7H3OJeBKW93oN/t5E11dlfh7VYc/Ac/sIswej9UEZUC/LU1IDEpvBDtXFMTNLLyVgaBlSYNTeDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T06:56:52.718900Z"},"content_sha256":"40488224d31346ae2a68d5022b65440231c808ccbcff3c540768831cdb9ef9e0","schema_version":"1.0","event_id":"sha256:40488224d31346ae2a68d5022b65440231c808ccbcff3c540768831cdb9ef9e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:VYY4N65TMPCJEZAZPEA4XY36KG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Combining Parametric and Nonparametric Models for Off-Policy Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Emma Brunskill, Finale Doshi-Velez, Omer Gottesman, Scott Sussex, Yao Liu","submitted_at":"2019-05-14T18:39:26Z","abstract_excerpt":"We consider a model-based approach to perform batch off-policy evaluation in reinforcement learning. Our method takes a mixture-of-experts approach to combine parametric and non-parametric models of the environment such that the final value estimate has the least expected error. We do so by first estimating the local accuracy of each model and then using a planner to select which model to use at every time step as to minimize the return error estimate along entire trajectories. Across a variety of domains, our mixture-based approach outperforms the individual models alone as well as state-of-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05787","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/1905.05787/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":"2026-07-05T00:41:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ercWvlZJaeAWnvDEeNih9RScuEkTLqSR3yL9IRhXo9/DbZVZ7UqDWWvkLsaT+bpGKMa579EAUUMYri6NV3DrAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T06:56:52.719400Z"},"content_sha256":"cd317ef29c68f4873549333cdd9f30724948c96f17e6828e524fbea2ae5c0f85","schema_version":"1.0","event_id":"sha256:cd317ef29c68f4873549333cdd9f30724948c96f17e6828e524fbea2ae5c0f85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VYY4N65TMPCJEZAZPEA4XY36KG/bundle.json","state_url":"https://pith.science/pith/VYY4N65TMPCJEZAZPEA4XY36KG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VYY4N65TMPCJEZAZPEA4XY36KG/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":"2026-08-11T06:56:52Z","links":{"resolver":"https://pith.science/pith/VYY4N65TMPCJEZAZPEA4XY36KG","bundle":"https://pith.science/pith/VYY4N65TMPCJEZAZPEA4XY36KG/bundle.json","state":"https://pith.science/pith/VYY4N65TMPCJEZAZPEA4XY36KG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VYY4N65TMPCJEZAZPEA4XY36KG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VYY4N65TMPCJEZAZPEA4XY36KG","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":"79585be76a2a46b20317792fed78fa13a7b62b9a7445365e754d145b5c186941","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T18:39:26Z","title_canon_sha256":"281c5677c725cbcab3046e6ab033e31d3825063179e5f2cd5f886327c8466463"},"schema_version":"1.0","source":{"id":"1905.05787","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05787","created_at":"2026-07-05T00:41:28Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05787v2","created_at":"2026-07-05T00:41:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05787","created_at":"2026-07-05T00:41:28Z"},{"alias_kind":"pith_short_12","alias_value":"VYY4N65TMPCJ","created_at":"2026-07-05T00:41:28Z"},{"alias_kind":"pith_short_16","alias_value":"VYY4N65TMPCJEZAZ","created_at":"2026-07-05T00:41:28Z"},{"alias_kind":"pith_short_8","alias_value":"VYY4N65T","created_at":"2026-07-05T00:41:28Z"}],"graph_snapshots":[{"event_id":"sha256:cd317ef29c68f4873549333cdd9f30724948c96f17e6828e524fbea2ae5c0f85","target":"graph","created_at":"2026-07-05T00:41:28Z","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/1905.05787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider a model-based approach to perform batch off-policy evaluation in reinforcement learning. Our method takes a mixture-of-experts approach to combine parametric and non-parametric models of the environment such that the final value estimate has the least expected error. We do so by first estimating the local accuracy of each model and then using a planner to select which model to use at every time step as to minimize the return error estimate along entire trajectories. Across a variety of domains, our mixture-based approach outperforms the individual models alone as well as state-of-t","authors_text":"Emma Brunskill, Finale Doshi-Velez, Omer Gottesman, Scott Sussex, Yao Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T18:39:26Z","title":"Combining Parametric and Nonparametric Models for Off-Policy Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05787","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":"sha256:40488224d31346ae2a68d5022b65440231c808ccbcff3c540768831cdb9ef9e0","target":"record","created_at":"2026-07-05T00:41:28Z","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":"79585be76a2a46b20317792fed78fa13a7b62b9a7445365e754d145b5c186941","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-14T18:39:26Z","title_canon_sha256":"281c5677c725cbcab3046e6ab033e31d3825063179e5f2cd5f886327c8466463"},"schema_version":"1.0","source":{"id":"1905.05787","kind":"arxiv","version":2}},"canonical_sha256":"ae31c6fbb363c49264197901cbe37e518af647b3efe6154b79f07a1e849ee07f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae31c6fbb363c49264197901cbe37e518af647b3efe6154b79f07a1e849ee07f","first_computed_at":"2026-07-05T00:41:28.238331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:41:28.238331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q4omiTTP556iDgheG4aHtQcvh14y9tglTADcaLvhdsu+JLuDsKv1F6GhnIyyITLahTmOMefgD0nrkyLRY0yFCA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:41:28.238797Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.05787","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40488224d31346ae2a68d5022b65440231c808ccbcff3c540768831cdb9ef9e0","sha256:cd317ef29c68f4873549333cdd9f30724948c96f17e6828e524fbea2ae5c0f85"],"state_sha256":"f0907096e8b3c4852ff869435ea20e2d8000d968bf814d6f3cbdb46267e4447c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nrAWS4AZFb8tGJEl2Wc3UF+NYe0RzhULlYThIlmH3XPO9yxcyxCsP2mHuWtyXWEVhqi7/30kvT6MZJ5IMSZmAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T06:56:52.723661Z","bundle_sha256":"ad460ff6ec92b53aa20bec8d3c4347a0b9135ed280c40b058e6a052e9bc7ebd8"}}