{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PNAEISQ4LRE4Z6WBODGW7OTHU4","short_pith_number":"pith:PNAEISQ4","canonical_record":{"source":{"id":"2003.04302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-09T17:59:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b52dd2d910a8279b93cf3b39cd00689e4c994002bf700c6b14af6c402391953f","abstract_canon_sha256":"d3e57597f92ae92eac85f7140fa2b49160817614c111339f6836c896e5599be2"},"schema_version":"1.0"},"canonical_sha256":"7b40444a1c5c49ccfac170cd6fba67a70dfdda90d4a1f5e082c0ea68f8cd1668","source":{"kind":"arxiv","id":"2003.04302","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.04302","created_at":"2026-07-05T00:46:41Z"},{"alias_kind":"arxiv_version","alias_value":"2003.04302v1","created_at":"2026-07-05T00:46:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04302","created_at":"2026-07-05T00:46:41Z"},{"alias_kind":"pith_short_12","alias_value":"PNAEISQ4LRE4","created_at":"2026-07-05T00:46:41Z"},{"alias_kind":"pith_short_16","alias_value":"PNAEISQ4LRE4Z6WB","created_at":"2026-07-05T00:46:41Z"},{"alias_kind":"pith_short_8","alias_value":"PNAEISQ4","created_at":"2026-07-05T00:46:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PNAEISQ4LRE4Z6WBODGW7OTHU4","target":"record","payload":{"canonical_record":{"source":{"id":"2003.04302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-09T17:59:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b52dd2d910a8279b93cf3b39cd00689e4c994002bf700c6b14af6c402391953f","abstract_canon_sha256":"d3e57597f92ae92eac85f7140fa2b49160817614c111339f6836c896e5599be2"},"schema_version":"1.0"},"canonical_sha256":"7b40444a1c5c49ccfac170cd6fba67a70dfdda90d4a1f5e082c0ea68f8cd1668","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:46:41.308583Z","signature_b64":"NEr1M/Sfvwbyh18zyuzHOQLM9iz115qfUSr4zCNOW1BRwLyumPxeGnH/CU3bZzZElij5D/nBeQATShFVgiFdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b40444a1c5c49ccfac170cd6fba67a70dfdda90d4a1f5e082c0ea68f8cd1668","last_reissued_at":"2026-07-05T00:46:41.308213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:46:41.308213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.04302","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":"2026-07-05T00:46:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rjGPds3opAgRTQmdj3LnrAShzxnceT7K7k7+YXE6AzDQccY2NxZRiXPYzJx1ei+JQ8UFociJtctSyQ5mYQe+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:41:14.702067Z"},"content_sha256":"38fc74a0aeacdd6a0635fa6b450e11eb2e64a23bb5683d58e41f046e0def562b","schema_version":"1.0","event_id":"sha256:38fc74a0aeacdd6a0635fa6b450e11eb2e64a23bb5683d58e41f046e0def562b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PNAEISQ4LRE4Z6WBODGW7OTHU4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Recursive Momentum for Policy Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Huizhuo Yuan, Ji Liu, Xiangru Lian, Yuren Zhou","submitted_at":"2020-03-09T17:59:03Z","abstract_excerpt":"In this paper, we propose a novel algorithm named STOchastic Recursive Momentum for Policy Gradient (STORM-PG), which operates a SARAH-type stochastic recursive variance-reduced policy gradient in an exponential moving average fashion. STORM-PG enjoys a provably sharp $O(1/\\epsilon^3)$ sample complexity bound for STORM-PG, matching the best-known convergence rate for policy gradient algorithm. In the mean time, STORM-PG avoids the alternations between large batches and small batches which persists in comparable variance-reduced policy gradient methods, allowing considerably simpler parameter t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04302","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/2003.04302/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":"2026-07-05T00:46:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vcqIZbreqoxfRfPerHAGvWfFMCeuOn3+6oSYq0DTs6E+DZOXBK1UIKtKoCdu6XzqPYR53anEZ7xP6l85GMrGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:41:14.702939Z"},"content_sha256":"8e937d8ecfac31ef201021d1f7f6830fe8ed4dc8288d0c7aa12c7d96c1ce6741","schema_version":"1.0","event_id":"sha256:8e937d8ecfac31ef201021d1f7f6830fe8ed4dc8288d0c7aa12c7d96c1ce6741"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PNAEISQ4LRE4Z6WBODGW7OTHU4/bundle.json","state_url":"https://pith.science/pith/PNAEISQ4LRE4Z6WBODGW7OTHU4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PNAEISQ4LRE4Z6WBODGW7OTHU4/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":"2026-08-09T21:41:14Z","links":{"resolver":"https://pith.science/pith/PNAEISQ4LRE4Z6WBODGW7OTHU4","bundle":"https://pith.science/pith/PNAEISQ4LRE4Z6WBODGW7OTHU4/bundle.json","state":"https://pith.science/pith/PNAEISQ4LRE4Z6WBODGW7OTHU4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PNAEISQ4LRE4Z6WBODGW7OTHU4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PNAEISQ4LRE4Z6WBODGW7OTHU4","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":"d3e57597f92ae92eac85f7140fa2b49160817614c111339f6836c896e5599be2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-09T17:59:03Z","title_canon_sha256":"b52dd2d910a8279b93cf3b39cd00689e4c994002bf700c6b14af6c402391953f"},"schema_version":"1.0","source":{"id":"2003.04302","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.04302","created_at":"2026-07-05T00:46:41Z"},{"alias_kind":"arxiv_version","alias_value":"2003.04302v1","created_at":"2026-07-05T00:46:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04302","created_at":"2026-07-05T00:46:41Z"},{"alias_kind":"pith_short_12","alias_value":"PNAEISQ4LRE4","created_at":"2026-07-05T00:46:41Z"},{"alias_kind":"pith_short_16","alias_value":"PNAEISQ4LRE4Z6WB","created_at":"2026-07-05T00:46:41Z"},{"alias_kind":"pith_short_8","alias_value":"PNAEISQ4","created_at":"2026-07-05T00:46:41Z"}],"graph_snapshots":[{"event_id":"sha256:8e937d8ecfac31ef201021d1f7f6830fe8ed4dc8288d0c7aa12c7d96c1ce6741","target":"graph","created_at":"2026-07-05T00:46:41Z","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/2003.04302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a novel algorithm named STOchastic Recursive Momentum for Policy Gradient (STORM-PG), which operates a SARAH-type stochastic recursive variance-reduced policy gradient in an exponential moving average fashion. STORM-PG enjoys a provably sharp $O(1/\\epsilon^3)$ sample complexity bound for STORM-PG, matching the best-known convergence rate for policy gradient algorithm. In the mean time, STORM-PG avoids the alternations between large batches and small batches which persists in comparable variance-reduced policy gradient methods, allowing considerably simpler parameter t","authors_text":"Huizhuo Yuan, Ji Liu, Xiangru Lian, Yuren Zhou","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-09T17:59:03Z","title":"Stochastic Recursive Momentum for Policy Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04302","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":"sha256:38fc74a0aeacdd6a0635fa6b450e11eb2e64a23bb5683d58e41f046e0def562b","target":"record","created_at":"2026-07-05T00:46:41Z","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":"d3e57597f92ae92eac85f7140fa2b49160817614c111339f6836c896e5599be2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-09T17:59:03Z","title_canon_sha256":"b52dd2d910a8279b93cf3b39cd00689e4c994002bf700c6b14af6c402391953f"},"schema_version":"1.0","source":{"id":"2003.04302","kind":"arxiv","version":1}},"canonical_sha256":"7b40444a1c5c49ccfac170cd6fba67a70dfdda90d4a1f5e082c0ea68f8cd1668","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b40444a1c5c49ccfac170cd6fba67a70dfdda90d4a1f5e082c0ea68f8cd1668","first_computed_at":"2026-07-05T00:46:41.308213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:46:41.308213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NEr1M/Sfvwbyh18zyuzHOQLM9iz115qfUSr4zCNOW1BRwLyumPxeGnH/CU3bZzZElij5D/nBeQATShFVgiFdBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:46:41.308583Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.04302","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38fc74a0aeacdd6a0635fa6b450e11eb2e64a23bb5683d58e41f046e0def562b","sha256:8e937d8ecfac31ef201021d1f7f6830fe8ed4dc8288d0c7aa12c7d96c1ce6741"],"state_sha256":"a6bfff5260acb7914bd4dc2574fd21ac250428adce8ce23f83d6aefb12443fce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wRGL0nZVudsapUG+vvdEBGn25gVYEsHLdGJaEOhRYNpnBA5MMEsQWLJm2rrso0jSfUUCcJzQwpJjVfOHQJvPAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:41:14.708944Z","bundle_sha256":"67139069573f5c12b3c6a9b3cb26d52bff530bc2214298181822835db84ec6e2"}}