{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:V7FQN5EBSKNI23BPQBC5XUCA3C","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":"7307b624a19cf5eb665be443e30d6a8d896a9d776d6eb8b95eff7d68c4c1a8fe","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-01-13T01:55:50Z","title_canon_sha256":"0f560068d88804224c2407d2871588c5f9730c486f140ff0427c96fe1c37f5db"},"schema_version":"1.0","source":{"id":"2001.04032","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.04032","created_at":"2026-07-05T00:51:38Z"},{"alias_kind":"arxiv_version","alias_value":"2001.04032v2","created_at":"2026-07-05T00:51:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.04032","created_at":"2026-07-05T00:51:38Z"},{"alias_kind":"pith_short_12","alias_value":"V7FQN5EBSKNI","created_at":"2026-07-05T00:51:38Z"},{"alias_kind":"pith_short_16","alias_value":"V7FQN5EBSKNI23BP","created_at":"2026-07-05T00:51:38Z"},{"alias_kind":"pith_short_8","alias_value":"V7FQN5EB","created_at":"2026-07-05T00:51:38Z"}],"graph_snapshots":[{"event_id":"sha256:c1f2b5f511d215053f4f8bd3c41284421e1e90950a4d7a476e32c158e5460a3e","target":"graph","created_at":"2026-07-05T00:51:38Z","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/2001.04032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many medical decision-making tasks can be framed as partially observed Markov decision processes (POMDPs). However, prevailing two-stage approaches that first learn a POMDP and then solve it often fail because the model that best fits the data may not be well suited for planning. We introduce a new optimization objective that (a) produces both high-performing policies and high-quality generative models, even when some observations are irrelevant for planning, and (b) does so in batch off-policy settings that are typical in healthcare, when only retrospective data is available. We demonstrate o","authors_text":"Finale Doshi-Velez, Joseph Futoma, Michael C. Hughes","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-01-13T01:55:50Z","title":"POPCORN: Partially Observed Prediction COnstrained ReiNforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.04032","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":"sha256:7f6511cd409b6520dce42ba959a9033e53cc34ed7d9e78b820ca59bc9a20de3c","target":"record","created_at":"2026-07-05T00:51:38Z","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":"7307b624a19cf5eb665be443e30d6a8d896a9d776d6eb8b95eff7d68c4c1a8fe","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-01-13T01:55:50Z","title_canon_sha256":"0f560068d88804224c2407d2871588c5f9730c486f140ff0427c96fe1c37f5db"},"schema_version":"1.0","source":{"id":"2001.04032","kind":"arxiv","version":2}},"canonical_sha256":"afcb06f481929a8d6c2f8045dbd040d89314e6ca3c80d93562ae734646ed1ba5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afcb06f481929a8d6c2f8045dbd040d89314e6ca3c80d93562ae734646ed1ba5","first_computed_at":"2026-07-05T00:51:38.115014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:51:38.115014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S4e3KoO34bdvvwShRn3S6qkU8Vr6Km1QZr+AbJ6gVWqx42enV/dQu8sy5xPYrkj4f3EpYqZBrBX+0FUo4s+yBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:51:38.115500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.04032","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f6511cd409b6520dce42ba959a9033e53cc34ed7d9e78b820ca59bc9a20de3c","sha256:c1f2b5f511d215053f4f8bd3c41284421e1e90950a4d7a476e32c158e5460a3e"],"state_sha256":"d03f3bc71e8ddc05f45f0d2a9a38412accf7d288b36f887b71d7406082003e5b"}