{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:3MDJSM7TJJSFUYXLKRORO3Y4PD","short_pith_number":"pith:3MDJSM7T","schema_version":"1.0","canonical_sha256":"db069933f34a645a62eb545d176f1c78e0b3c3e314d9b44bcdd71c790d87475d","source":{"kind":"arxiv","id":"1507.04635","version":4},"attestation_state":"computed","paper":{"title":"Black-Box Policy Search with Probabilistic Programs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"stat.ML","authors_text":"Brooks Paige, David Tolpin, Frank Wood, Jan-Willem van de Meent","submitted_at":"2015-07-16T16:18:44Z","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"},"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":"1507.04635","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-16T16:18:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"71989bb2e971d2b0707415a4d102d09648891706237ed47a7fde6e5c276b91b6","abstract_canon_sha256":"c819b73aed3755d590feedce981f2014f94a3dba5e1c5b20db65ce6b7006b696"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:55.239657Z","signature_b64":"qi6SZ2JPz9tFWvGT4VWUQpb54kQqHppA6WwHb9sy58VRk7lwm5l/FMpys1ALTUho1hAQpfpnx+D361oFqeSuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db069933f34a645a62eb545d176f1c78e0b3c3e314d9b44bcdd71c790d87475d","last_reissued_at":"2026-05-18T01:09:55.239060Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:55.239060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Black-Box Policy Search with Probabilistic Programs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"stat.ML","authors_text":"Brooks Paige, David Tolpin, Frank Wood, Jan-Willem van de Meent","submitted_at":"2015-07-16T16:18:44Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.04635","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1507.04635","created_at":"2026-05-18T01:09:55.239163+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.04635v4","created_at":"2026-05-18T01:09:55.239163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.04635","created_at":"2026-05-18T01:09:55.239163+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MDJSM7TJJSF","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MDJSM7TJJSFUYXL","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MDJSM7T","created_at":"2026-05-18T12:29:02.477457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3MDJSM7TJJSFUYXLKRORO3Y4PD","json":"https://pith.science/pith/3MDJSM7TJJSFUYXLKRORO3Y4PD.json","graph_json":"https://pith.science/api/pith-number/3MDJSM7TJJSFUYXLKRORO3Y4PD/graph.json","events_json":"https://pith.science/api/pith-number/3MDJSM7TJJSFUYXLKRORO3Y4PD/events.json","paper":"https://pith.science/paper/3MDJSM7T"},"agent_actions":{"view_html":"https://pith.science/pith/3MDJSM7TJJSFUYXLKRORO3Y4PD","download_json":"https://pith.science/pith/3MDJSM7TJJSFUYXLKRORO3Y4PD.json","view_paper":"https://pith.science/paper/3MDJSM7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.04635&json=true","fetch_graph":"https://pith.science/api/pith-number/3MDJSM7TJJSFUYXLKRORO3Y4PD/graph.json","fetch_events":"https://pith.science/api/pith-number/3MDJSM7TJJSFUYXLKRORO3Y4PD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MDJSM7TJJSFUYXLKRORO3Y4PD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MDJSM7TJJSFUYXLKRORO3Y4PD/action/storage_attestation","attest_author":"https://pith.science/pith/3MDJSM7TJJSFUYXLKRORO3Y4PD/action/author_attestation","sign_citation":"https://pith.science/pith/3MDJSM7TJJSFUYXLKRORO3Y4PD/action/citation_signature","submit_replication":"https://pith.science/pith/3MDJSM7TJJSFUYXLKRORO3Y4PD/action/replication_record"}},"created_at":"2026-05-18T01:09:55.239163+00:00","updated_at":"2026-05-18T01:09:55.239163+00:00"}