{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FCBU67S6JT4UH5FRZJ4V4N5MZQ","short_pith_number":"pith:FCBU67S6","schema_version":"1.0","canonical_sha256":"28834f7e5e4cf943f4b1ca795e37accc248317af02050672ec74aaa409361976","source":{"kind":"arxiv","id":"2110.15335","version":2},"attestation_state":"computed","paper":{"title":"Bayesian Sequential Optimal Experimental Design for Nonlinear Models Using Policy Gradient Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Wanggang Shen, Xun Huan","submitted_at":"2021-10-28T17:47:31Z","abstract_excerpt":"We present a mathematical framework and computational methods to optimally design a finite number of sequential experiments. We formulate this sequential optimal experimental design (sOED) problem as a finite-horizon partially observable Markov decision process (POMDP) in a Bayesian setting and with information-theoretic utilities. It is built to accommodate continuous random variables, general non-Gaussian posteriors, and expensive nonlinear forward models. sOED then seeks an optimal design policy that incorporates elements of both feedback and lookahead, generalizing the suboptimal batch and"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2110.15335","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-28T17:47:31Z","cross_cats_sorted":["stat.CO","stat.ME","stat.ML"],"title_canon_sha256":"53059cffc3ddffc2486635e0f1632ac7fa6b89ffcf398b98e13aaca63ed4cde3","abstract_canon_sha256":"63755a2643fb256996ce7e111235f59fc42f893024e1de6ffb0cf84a5011b37f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:57.717896Z","signature_b64":"f/GvELdAgYtbyfnzDpl02SXPqvldOnAkG9tVjejjnVv49JvG+sGvTIwIW3CDXg0gvCyfgxVsX2l1/HYwsFptBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28834f7e5e4cf943f4b1ca795e37accc248317af02050672ec74aaa409361976","last_reissued_at":"2026-07-05T08:00:57.717375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:57.717375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Sequential Optimal Experimental Design for Nonlinear Models Using Policy Gradient Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.CO","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Wanggang Shen, Xun Huan","submitted_at":"2021-10-28T17:47:31Z","abstract_excerpt":"We present a mathematical framework and computational methods to optimally design a finite number of sequential experiments. We formulate this sequential optimal experimental design (sOED) problem as a finite-horizon partially observable Markov decision process (POMDP) in a Bayesian setting and with information-theoretic utilities. It is built to accommodate continuous random variables, general non-Gaussian posteriors, and expensive nonlinear forward models. sOED then seeks an optimal design policy that incorporates elements of both feedback and lookahead, generalizing the suboptimal batch and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15335","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/2110.15335/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.15335","created_at":"2026-07-05T08:00:57.717438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.15335v2","created_at":"2026-07-05T08:00:57.717438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15335","created_at":"2026-07-05T08:00:57.717438+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCBU67S6JT4U","created_at":"2026-07-05T08:00:57.717438+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCBU67S6JT4UH5FR","created_at":"2026-07-05T08:00:57.717438+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCBU67S6","created_at":"2026-07-05T08:00:57.717438+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23662","citing_title":"Action-BED: Task-Driven Bayesian Experimental Design with Singly Intractable Objectives","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2306.10430","citing_title":"Variational Sequential Optimal Experimental Design using Reinforcement Learning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2407.16212","citing_title":"Optimal experimental design: Formulations and computations","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25193","citing_title":"Adaptive Sensing beyond Non-Adaptive Information Limits: End-to-End Co-Design of Geometry, Policy, and Inference","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCBU67S6JT4UH5FRZJ4V4N5MZQ","json":"https://pith.science/pith/FCBU67S6JT4UH5FRZJ4V4N5MZQ.json","graph_json":"https://pith.science/api/pith-number/FCBU67S6JT4UH5FRZJ4V4N5MZQ/graph.json","events_json":"https://pith.science/api/pith-number/FCBU67S6JT4UH5FRZJ4V4N5MZQ/events.json","paper":"https://pith.science/paper/FCBU67S6"},"agent_actions":{"view_html":"https://pith.science/pith/FCBU67S6JT4UH5FRZJ4V4N5MZQ","download_json":"https://pith.science/pith/FCBU67S6JT4UH5FRZJ4V4N5MZQ.json","view_paper":"https://pith.science/paper/FCBU67S6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.15335&json=true","fetch_graph":"https://pith.science/api/pith-number/FCBU67S6JT4UH5FRZJ4V4N5MZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/FCBU67S6JT4UH5FRZJ4V4N5MZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCBU67S6JT4UH5FRZJ4V4N5MZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCBU67S6JT4UH5FRZJ4V4N5MZQ/action/storage_attestation","attest_author":"https://pith.science/pith/FCBU67S6JT4UH5FRZJ4V4N5MZQ/action/author_attestation","sign_citation":"https://pith.science/pith/FCBU67S6JT4UH5FRZJ4V4N5MZQ/action/citation_signature","submit_replication":"https://pith.science/pith/FCBU67S6JT4UH5FRZJ4V4N5MZQ/action/replication_record"}},"created_at":"2026-07-05T08:00:57.717438+00:00","updated_at":"2026-07-05T08:00:57.717438+00:00"}