{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7AJEKIR3HZ3IMNT62OTG6BNWM3","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":"5811c47b23a6d6e76f052a74c3086954eed970f821d26cbc6ee20a605160449d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T18:02:57Z","title_canon_sha256":"ce126a46deff7834354601cda6d9fc08f69f0c08322eedad809019a20fe0a689"},"schema_version":"1.0","source":{"id":"2306.08044","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08044","created_at":"2026-07-05T09:19:51Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08044v3","created_at":"2026-07-05T09:19:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08044","created_at":"2026-07-05T09:19:51Z"},{"alias_kind":"pith_short_12","alias_value":"7AJEKIR3HZ3I","created_at":"2026-07-05T09:19:51Z"},{"alias_kind":"pith_short_16","alias_value":"7AJEKIR3HZ3IMNT6","created_at":"2026-07-05T09:19:51Z"},{"alias_kind":"pith_short_8","alias_value":"7AJEKIR3","created_at":"2026-07-05T09:19:51Z"}],"graph_snapshots":[{"event_id":"sha256:cc4038d3546195301afaa6260abcd2877cbe7224d31bb5c6a3d32b1e86affe3e","target":"graph","created_at":"2026-07-05T09:19:51Z","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/2306.08044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Medical treatments often involve a sequence of decisions, each informed by previous outcomes. This process closely aligns with reinforcement learning (RL), a framework for optimizing sequential decisions to maximize cumulative rewards under unknown dynamics. While RL shows promise for creating data-driven treatment plans, its application in medical contexts is challenging due to the frequent need to use sparse rewards, primarily defined based on mortality outcomes. This sparsity can reduce the stability of offline estimates, posing a significant hurdle in fully utilizing RL for medical decisio","authors_text":"Ahmed Alaa, Alexander Schubert, Ali Shirali","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T18:02:57Z","title":"Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08044","kind":"arxiv","version":3},"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:a03d2074703964725a9212507f7ed9ee285afce2e1c6c7185488fa418a0cee69","target":"record","created_at":"2026-07-05T09:19:51Z","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":"5811c47b23a6d6e76f052a74c3086954eed970f821d26cbc6ee20a605160449d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T18:02:57Z","title_canon_sha256":"ce126a46deff7834354601cda6d9fc08f69f0c08322eedad809019a20fe0a689"},"schema_version":"1.0","source":{"id":"2306.08044","kind":"arxiv","version":3}},"canonical_sha256":"f81245223b3e7686367ed3a66f05b666f2f8db2597e914285e127fde8384d0b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f81245223b3e7686367ed3a66f05b666f2f8db2597e914285e127fde8384d0b3","first_computed_at":"2026-07-05T09:19:51.285507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:51.285507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RczrCddoi9WYf/Eu1TqdhaLIbEgJTUTBpRO9xXMv8QRNXtpFP8b/67ZslIFQDde27bPruEikrYDdWu+6A+MDCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:51.285941Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08044","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a03d2074703964725a9212507f7ed9ee285afce2e1c6c7185488fa418a0cee69","sha256:cc4038d3546195301afaa6260abcd2877cbe7224d31bb5c6a3d32b1e86affe3e"],"state_sha256":"112edde52fff9b64ee051c6388d386dd8fafdeafc96b33235a223573ff072937"}