{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3U552DSILBKCLGHQBIN3AVKPX5","short_pith_number":"pith:3U552DSI","canonical_record":{"source":{"id":"2302.02299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T04:44:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7209fab48fe00a3f6bca224ee95a274b329af9e1bf7dd7d1b9545790123be8a5","abstract_canon_sha256":"e07f13ce3dc2ee3f58b0679bdeec02dd8eda80fb5acb361f94d3318abfb23975"},"schema_version":"1.0"},"canonical_sha256":"dd3bdd0e4858542598f00a1bb0554fbf7adb1387b0901394969b34c9fd67067d","source":{"kind":"arxiv","id":"2302.02299","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02299","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02299v1","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02299","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"pith_short_12","alias_value":"3U552DSILBKC","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"pith_short_16","alias_value":"3U552DSILBKCLGHQ","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"pith_short_8","alias_value":"3U552DSI","created_at":"2026-07-05T05:38:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3U552DSILBKCLGHQBIN3AVKPX5","target":"record","payload":{"canonical_record":{"source":{"id":"2302.02299","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T04:44:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7209fab48fe00a3f6bca224ee95a274b329af9e1bf7dd7d1b9545790123be8a5","abstract_canon_sha256":"e07f13ce3dc2ee3f58b0679bdeec02dd8eda80fb5acb361f94d3318abfb23975"},"schema_version":"1.0"},"canonical_sha256":"dd3bdd0e4858542598f00a1bb0554fbf7adb1387b0901394969b34c9fd67067d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:51.763104Z","signature_b64":"8vnovjMsuJdxkmoB7BhwG4CFLsw3CT5hCL7cEgv8VXBZ3+wjGlRZSN1OORkVhkrV7ExMARPSRNkaTT7FWdAzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd3bdd0e4858542598f00a1bb0554fbf7adb1387b0901394969b34c9fd67067d","last_reissued_at":"2026-07-05T05:38:51.762586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:51.762586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.02299","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:38:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bdKdsfPYTXosEE1gPAxgHap1NggYMb2dHNc+S/V7be7xoM6pO9jV13xFrdZZGnxUKZL8FoRJ86eMiiQgaD/BDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:48:28.822194Z"},"content_sha256":"351017577f5d870ba70f608c14687e6d12cbe15f1d6b31788ae516a262f355e5","schema_version":"1.0","event_id":"sha256:351017577f5d870ba70f608c14687e6d12cbe15f1d6b31788ae516a262f355e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3U552DSILBKCLGHQBIN3AVKPX5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Deheng Ye, Mingfei Sun, Qiang Fu, Wei Liu, Wei Yang, Xiapeng Wu, Zichuan Lin","submitted_at":"2023-02-05T04:44:35Z","abstract_excerpt":"Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse. In this paper, we show that the use of importance sampling could introduce high variance in the objective estimate. Specifically, we show in a principled way that the variance of importance sampling estimate grows quadratically with importance ratios and the large ratios could consequently jeopardize the effectiveness of surrogate objective optimization. We then propose a technique called sample dropout "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02299","kind":"arxiv","version":1},"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/2302.02299/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":"2026-07-05T05:38:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BW9a+hJzlwBlSwz1Rkdf8L/Yv8PFR/t4/E0YEDiAsJB871JpUvVe1sRGGlMsQ0WrT5QMLCDNhYrdlILR2FB2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:48:28.822739Z"},"content_sha256":"2b7943476f1d93c18e35fde0f4750a977a81ea5740baae0522d5adeef87ee006","schema_version":"1.0","event_id":"sha256:2b7943476f1d93c18e35fde0f4750a977a81ea5740baae0522d5adeef87ee006"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3U552DSILBKCLGHQBIN3AVKPX5/bundle.json","state_url":"https://pith.science/pith/3U552DSILBKCLGHQBIN3AVKPX5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3U552DSILBKCLGHQBIN3AVKPX5/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":"2026-08-06T15:48:28Z","links":{"resolver":"https://pith.science/pith/3U552DSILBKCLGHQBIN3AVKPX5","bundle":"https://pith.science/pith/3U552DSILBKCLGHQBIN3AVKPX5/bundle.json","state":"https://pith.science/pith/3U552DSILBKCLGHQBIN3AVKPX5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3U552DSILBKCLGHQBIN3AVKPX5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3U552DSILBKCLGHQBIN3AVKPX5","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":"e07f13ce3dc2ee3f58b0679bdeec02dd8eda80fb5acb361f94d3318abfb23975","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T04:44:35Z","title_canon_sha256":"7209fab48fe00a3f6bca224ee95a274b329af9e1bf7dd7d1b9545790123be8a5"},"schema_version":"1.0","source":{"id":"2302.02299","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02299","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02299v1","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02299","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"pith_short_12","alias_value":"3U552DSILBKC","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"pith_short_16","alias_value":"3U552DSILBKCLGHQ","created_at":"2026-07-05T05:38:51Z"},{"alias_kind":"pith_short_8","alias_value":"3U552DSI","created_at":"2026-07-05T05:38:51Z"}],"graph_snapshots":[{"event_id":"sha256:2b7943476f1d93c18e35fde0f4750a977a81ea5740baae0522d5adeef87ee006","target":"graph","created_at":"2026-07-05T05:38:51Z","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/2302.02299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse. In this paper, we show that the use of importance sampling could introduce high variance in the objective estimate. Specifically, we show in a principled way that the variance of importance sampling estimate grows quadratically with importance ratios and the large ratios could consequently jeopardize the effectiveness of surrogate objective optimization. We then propose a technique called sample dropout ","authors_text":"Deheng Ye, Mingfei Sun, Qiang Fu, Wei Liu, Wei Yang, Xiapeng Wu, Zichuan Lin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T04:44:35Z","title":"Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02299","kind":"arxiv","version":1},"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":"sha256:351017577f5d870ba70f608c14687e6d12cbe15f1d6b31788ae516a262f355e5","target":"record","created_at":"2026-07-05T05:38:51Z","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":"e07f13ce3dc2ee3f58b0679bdeec02dd8eda80fb5acb361f94d3318abfb23975","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T04:44:35Z","title_canon_sha256":"7209fab48fe00a3f6bca224ee95a274b329af9e1bf7dd7d1b9545790123be8a5"},"schema_version":"1.0","source":{"id":"2302.02299","kind":"arxiv","version":1}},"canonical_sha256":"dd3bdd0e4858542598f00a1bb0554fbf7adb1387b0901394969b34c9fd67067d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd3bdd0e4858542598f00a1bb0554fbf7adb1387b0901394969b34c9fd67067d","first_computed_at":"2026-07-05T05:38:51.762586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:51.762586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8vnovjMsuJdxkmoB7BhwG4CFLsw3CT5hCL7cEgv8VXBZ3+wjGlRZSN1OORkVhkrV7ExMARPSRNkaTT7FWdAzCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:51.763104Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.02299","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:351017577f5d870ba70f608c14687e6d12cbe15f1d6b31788ae516a262f355e5","sha256:2b7943476f1d93c18e35fde0f4750a977a81ea5740baae0522d5adeef87ee006"],"state_sha256":"c2fbf1f1859360295e6625dbe24640082bae6ffc57076c945bb91f447e2b1d02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yaE9kdXry8X3IW3B/67hOxRMj42ceV//EBokzOnu4qrLJyehEirHNYFM+fdm0ikC65SmnNe6YT5okFDpbSVGDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:48:28.828255Z","bundle_sha256":"b06cd7fbce81635590ad9ac1c61687ba816663c605cb272b809cf63ab9af3781"}}