{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:3MDJSM7TJJSFUYXLKRORO3Y4PD","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":"c819b73aed3755d590feedce981f2014f94a3dba5e1c5b20db65ce6b7006b696","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-16T16:18:44Z","title_canon_sha256":"71989bb2e971d2b0707415a4d102d09648891706237ed47a7fde6e5c276b91b6"},"schema_version":"1.0","source":{"id":"1507.04635","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.04635","created_at":"2026-05-18T01:09:55Z"},{"alias_kind":"arxiv_version","alias_value":"1507.04635v4","created_at":"2026-05-18T01:09:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.04635","created_at":"2026-05-18T01:09:55Z"},{"alias_kind":"pith_short_12","alias_value":"3MDJSM7TJJSF","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"3MDJSM7TJJSFUYXL","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"3MDJSM7T","created_at":"2026-05-18T12:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:93d54c90c4eeffe9d02a3627ba845e34b72b2e894bf847bd1357ad2c1ee795e1","target":"graph","created_at":"2026-05-18T01:09:55Z","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"},"paper":{"abstract_excerpt":"In this work, we explore how probabilistic programs can be used to represent policies in sequential decision problems. In this formulation, a probabilistic program is a black-box stochastic simulator for both the problem domain and the agent. We relate classic policy gradient techniques to recently introduced black-box variational methods which generalize to probabilistic program inference. We present case studies in the Canadian traveler problem, Rock Sample, and a benchmark for optimal diagnosis inspired by Guess Who. Each study illustrates how programs can efficiently represent policies usi","authors_text":"Brooks Paige, David Tolpin, Frank Wood, Jan-Willem van de Meent","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-16T16:18:44Z","title":"Black-Box Policy Search with Probabilistic Programs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.04635","kind":"arxiv","version":4},"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":"sha256:7ad5fb0fd2871faf94dfb06ccdad6ecd1c639d98a4577d792d5fbfdead7a95ba","target":"record","created_at":"2026-05-18T01:09:55Z","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":"c819b73aed3755d590feedce981f2014f94a3dba5e1c5b20db65ce6b7006b696","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-16T16:18:44Z","title_canon_sha256":"71989bb2e971d2b0707415a4d102d09648891706237ed47a7fde6e5c276b91b6"},"schema_version":"1.0","source":{"id":"1507.04635","kind":"arxiv","version":4}},"canonical_sha256":"db069933f34a645a62eb545d176f1c78e0b3c3e314d9b44bcdd71c790d87475d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db069933f34a645a62eb545d176f1c78e0b3c3e314d9b44bcdd71c790d87475d","first_computed_at":"2026-05-18T01:09:55.239060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:09:55.239060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qi6SZ2JPz9tFWvGT4VWUQpb54kQqHppA6WwHb9sy58VRk7lwm5l/FMpys1ALTUho1hAQpfpnx+D361oFqeSuAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:09:55.239657Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.04635","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ad5fb0fd2871faf94dfb06ccdad6ecd1c639d98a4577d792d5fbfdead7a95ba","sha256:93d54c90c4eeffe9d02a3627ba845e34b72b2e894bf847bd1357ad2c1ee795e1"],"state_sha256":"654cb89b7a037cd61d7de23e0604c9451c85ff6bb2f8c54291f3c61ffc2cb744"}