{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:H4BFERBZPYYIDZDCNJMVVA4M34","short_pith_number":"pith:H4BFERBZ","canonical_record":{"source":{"id":"2104.06175","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-04-13T13:27:33Z","cross_cats_sorted":[],"title_canon_sha256":"f931d5f2e13941d5dc4ed4f7df6014f8f305b0f60be039c180325dac57b36b53","abstract_canon_sha256":"ce399a00266270ca0dd68b5a38dd3a69bf3eb09a13c01f637ffb7c2c5dfec132"},"schema_version":"1.0"},"canonical_sha256":"3f025244397e3081e4626a595a838cdf3072e30f1fdf9619e9b95c4e28396638","source":{"kind":"arxiv","id":"2104.06175","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.06175","created_at":"2026-07-05T03:35:09Z"},{"alias_kind":"arxiv_version","alias_value":"2104.06175v3","created_at":"2026-07-05T03:35:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06175","created_at":"2026-07-05T03:35:09Z"},{"alias_kind":"pith_short_12","alias_value":"H4BFERBZPYYI","created_at":"2026-07-05T03:35:09Z"},{"alias_kind":"pith_short_16","alias_value":"H4BFERBZPYYIDZDC","created_at":"2026-07-05T03:35:09Z"},{"alias_kind":"pith_short_8","alias_value":"H4BFERBZ","created_at":"2026-07-05T03:35:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:H4BFERBZPYYIDZDCNJMVVA4M34","target":"record","payload":{"canonical_record":{"source":{"id":"2104.06175","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-04-13T13:27:33Z","cross_cats_sorted":[],"title_canon_sha256":"f931d5f2e13941d5dc4ed4f7df6014f8f305b0f60be039c180325dac57b36b53","abstract_canon_sha256":"ce399a00266270ca0dd68b5a38dd3a69bf3eb09a13c01f637ffb7c2c5dfec132"},"schema_version":"1.0"},"canonical_sha256":"3f025244397e3081e4626a595a838cdf3072e30f1fdf9619e9b95c4e28396638","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:09.348729Z","signature_b64":"zYRymyEWD41XoKIUeDDZZKJFK8mdPXq7vI2E/I06X1Jrp94Pt6jis5jHSuaOCi6oVCyy/MVa8PlGZteSm1plBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f025244397e3081e4626a595a838cdf3072e30f1fdf9619e9b95c4e28396638","last_reissued_at":"2026-07-05T03:35:09.348328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:09.348328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.06175","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:35:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A1bUUpWgnp+bowUMu6dCm/CLplSe92iAduGdahMW4tq7QqFzXPd6TINza9zMP5AdsEVkIlKoFtwoC3qfbsQsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T03:52:37.985226Z"},"content_sha256":"3672fc86e5b85c6b614fac5f5eb37fa72bf8fe5a977a68595328ab2390ba294d","schema_version":"1.0","event_id":"sha256:3672fc86e5b85c6b614fac5f5eb37fa72bf8fe5a977a68595328ab2390ba294d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:H4BFERBZPYYIDZDCNJMVVA4M34","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy-based optimization: single-step policy gradient method seen as an evolution strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Alexander Kuhnle, Elie Hachem, Jonathan Viquerat, Philippe Meliga, R\\'egis Duvigneau","submitted_at":"2021-04-13T13:27:33Z","abstract_excerpt":"This research reports on the recent development of a black-box optimization method based on single-step deep reinforcement learning (DRL), and on its conceptual proximity to evolution strategy (ES) techniques. In the fashion of policy gradient (PG) methods, the policy-based optimization (PBO) algorithm relies on the update of a policy network to describe the density function of its next generation of individuals. The method is described in details, and its similarities to both ES and PG methods are pointed out. The relevance of the approach is then evaluated on the minimization of standard ana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06175","kind":"arxiv","version":3},"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/2104.06175/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:35:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XyTbPrb9pizoWZ88gQWB3Zgq/2HYh6YVu9sSI3MKQnm8CbopnuYhFDoS2FFGxdQ4St5v5UX4IBCfkQsKDjW6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T03:52:37.985606Z"},"content_sha256":"32236fccbd31206b82223ebbe8adf3e5023fb8f96b4f61fa713ceb5e23e2a9bc","schema_version":"1.0","event_id":"sha256:32236fccbd31206b82223ebbe8adf3e5023fb8f96b4f61fa713ceb5e23e2a9bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H4BFERBZPYYIDZDCNJMVVA4M34/bundle.json","state_url":"https://pith.science/pith/H4BFERBZPYYIDZDCNJMVVA4M34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H4BFERBZPYYIDZDCNJMVVA4M34/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-12T03:52:37Z","links":{"resolver":"https://pith.science/pith/H4BFERBZPYYIDZDCNJMVVA4M34","bundle":"https://pith.science/pith/H4BFERBZPYYIDZDCNJMVVA4M34/bundle.json","state":"https://pith.science/pith/H4BFERBZPYYIDZDCNJMVVA4M34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H4BFERBZPYYIDZDCNJMVVA4M34/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:H4BFERBZPYYIDZDCNJMVVA4M34","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":"ce399a00266270ca0dd68b5a38dd3a69bf3eb09a13c01f637ffb7c2c5dfec132","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-04-13T13:27:33Z","title_canon_sha256":"f931d5f2e13941d5dc4ed4f7df6014f8f305b0f60be039c180325dac57b36b53"},"schema_version":"1.0","source":{"id":"2104.06175","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.06175","created_at":"2026-07-05T03:35:09Z"},{"alias_kind":"arxiv_version","alias_value":"2104.06175v3","created_at":"2026-07-05T03:35:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06175","created_at":"2026-07-05T03:35:09Z"},{"alias_kind":"pith_short_12","alias_value":"H4BFERBZPYYI","created_at":"2026-07-05T03:35:09Z"},{"alias_kind":"pith_short_16","alias_value":"H4BFERBZPYYIDZDC","created_at":"2026-07-05T03:35:09Z"},{"alias_kind":"pith_short_8","alias_value":"H4BFERBZ","created_at":"2026-07-05T03:35:09Z"}],"graph_snapshots":[{"event_id":"sha256:32236fccbd31206b82223ebbe8adf3e5023fb8f96b4f61fa713ceb5e23e2a9bc","target":"graph","created_at":"2026-07-05T03:35:09Z","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/2104.06175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This research reports on the recent development of a black-box optimization method based on single-step deep reinforcement learning (DRL), and on its conceptual proximity to evolution strategy (ES) techniques. In the fashion of policy gradient (PG) methods, the policy-based optimization (PBO) algorithm relies on the update of a policy network to describe the density function of its next generation of individuals. The method is described in details, and its similarities to both ES and PG methods are pointed out. The relevance of the approach is then evaluated on the minimization of standard ana","authors_text":"Alexander Kuhnle, Elie Hachem, Jonathan Viquerat, Philippe Meliga, R\\'egis Duvigneau","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-04-13T13:27:33Z","title":"Policy-based optimization: single-step policy gradient method seen as an evolution strategy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06175","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":"sha256:3672fc86e5b85c6b614fac5f5eb37fa72bf8fe5a977a68595328ab2390ba294d","target":"record","created_at":"2026-07-05T03:35:09Z","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":"ce399a00266270ca0dd68b5a38dd3a69bf3eb09a13c01f637ffb7c2c5dfec132","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-04-13T13:27:33Z","title_canon_sha256":"f931d5f2e13941d5dc4ed4f7df6014f8f305b0f60be039c180325dac57b36b53"},"schema_version":"1.0","source":{"id":"2104.06175","kind":"arxiv","version":3}},"canonical_sha256":"3f025244397e3081e4626a595a838cdf3072e30f1fdf9619e9b95c4e28396638","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f025244397e3081e4626a595a838cdf3072e30f1fdf9619e9b95c4e28396638","first_computed_at":"2026-07-05T03:35:09.348328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:35:09.348328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zYRymyEWD41XoKIUeDDZZKJFK8mdPXq7vI2E/I06X1Jrp94Pt6jis5jHSuaOCi6oVCyy/MVa8PlGZteSm1plBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:35:09.348729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.06175","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3672fc86e5b85c6b614fac5f5eb37fa72bf8fe5a977a68595328ab2390ba294d","sha256:32236fccbd31206b82223ebbe8adf3e5023fb8f96b4f61fa713ceb5e23e2a9bc"],"state_sha256":"e83d26f647dc741e25c500619ba9aa06a6cd0c9d5523507837122a643c09f770"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k6qB+J61EO8mHrMxxuGyM7OyiQPK2Kx03I79KGBPgiSSD1kHBw5B8GCyNvJIRP+VaN334TzFWQ1JvRnx9QwtDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T03:52:37.987618Z","bundle_sha256":"591441dfe56852142d11441cd71eafc7e1ac55c583e7c7a865581a01b6a7d604"}}