{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FDF5G4ZL5T7AJDGRMVB6UNDCFB","short_pith_number":"pith:FDF5G4ZL","canonical_record":{"source":{"id":"1906.03704","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T20:59:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e204126324d98815e2b9287aabe0af1398c8d54d87e2335d34aa03842e91fb5f","abstract_canon_sha256":"86b66bc9d80321ace79cb2311c43d1cd4dec27c5a81c202ee4a505e524a0987a"},"schema_version":"1.0"},"canonical_sha256":"28cbd3732becfe048cd16543ea3462287eb584bd5139f741db9bc68292490721","source":{"kind":"arxiv","id":"1906.03704","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03704","created_at":"2026-07-05T01:11:33Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03704v2","created_at":"2026-07-05T01:11:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03704","created_at":"2026-07-05T01:11:33Z"},{"alias_kind":"pith_short_12","alias_value":"FDF5G4ZL5T7A","created_at":"2026-07-05T01:11:33Z"},{"alias_kind":"pith_short_16","alias_value":"FDF5G4ZL5T7AJDGR","created_at":"2026-07-05T01:11:33Z"},{"alias_kind":"pith_short_8","alias_value":"FDF5G4ZL","created_at":"2026-07-05T01:11:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FDF5G4ZL5T7AJDGRMVB6UNDCFB","target":"record","payload":{"canonical_record":{"source":{"id":"1906.03704","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T20:59:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e204126324d98815e2b9287aabe0af1398c8d54d87e2335d34aa03842e91fb5f","abstract_canon_sha256":"86b66bc9d80321ace79cb2311c43d1cd4dec27c5a81c202ee4a505e524a0987a"},"schema_version":"1.0"},"canonical_sha256":"28cbd3732becfe048cd16543ea3462287eb584bd5139f741db9bc68292490721","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:33.100993Z","signature_b64":"Jnzh2oZtN8ie+7rNO+riP4VkclHm8pyCYbfQe9PeXdhXu6Nl5npzyfdPQOVJn1egWn2OxJbou3VhC+0L8XSWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28cbd3732becfe048cd16543ea3462287eb584bd5139f741db9bc68292490721","last_reissued_at":"2026-07-05T01:11:33.100594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:33.100594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.03704","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:11:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"73xklKkvdNDr2h3vd5XL36/ptVkEnOePVXzBNPj8eVwUGWF3wFUORRhJ7Qt8mYPm6IFyWvO2yah5bSCWr56GAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:05:34.662645Z"},"content_sha256":"d89a14e75793de82287728c4a802687da8d38a685e4acc4ad1f7206a0715502d","schema_version":"1.0","event_id":"sha256:d89a14e75793de82287728c4a802687da8d38a685e4acc4ad1f7206a0715502d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FDF5G4ZL5T7AJDGRMVB6UNDCFB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SVRG for Policy Evaluation with Fewer Gradient Evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed Touati, Doina Precup, Pascal Vincent, Zilun Peng","submitted_at":"2019-06-09T20:59:02Z","abstract_excerpt":"Stochastic variance-reduced gradient (SVRG) is an optimization method originally designed for tackling machine learning problems with a finite sum structure. SVRG was later shown to work for policy evaluation, a problem in reinforcement learning in which one aims to estimate the value function of a given policy. SVRG makes use of gradient estimates at two scales. At the slower scale, SVRG computes a full gradient over the whole dataset, which could lead to prohibitive computation costs. In this work, we show that two variants of SVRG for policy evaluation could significantly diminish the numbe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03704","kind":"arxiv","version":2},"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/1906.03704/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":"2026-07-05T01:11:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0/B7cMt2dU4YSjsjz/RJVzsj9U4WhKUTLbm7+/gBO5feP+pHufxeMwmqU/2C2f9a4FWyAgEYLJ2hW398jfzqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T17:05:34.663301Z"},"content_sha256":"ec602d12a4d37188d40492845dd762e312187b56ba82001bd96b2ba7c073d380","schema_version":"1.0","event_id":"sha256:ec602d12a4d37188d40492845dd762e312187b56ba82001bd96b2ba7c073d380"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FDF5G4ZL5T7AJDGRMVB6UNDCFB/bundle.json","state_url":"https://pith.science/pith/FDF5G4ZL5T7AJDGRMVB6UNDCFB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FDF5G4ZL5T7AJDGRMVB6UNDCFB/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":"2026-08-06T17:05:34Z","links":{"resolver":"https://pith.science/pith/FDF5G4ZL5T7AJDGRMVB6UNDCFB","bundle":"https://pith.science/pith/FDF5G4ZL5T7AJDGRMVB6UNDCFB/bundle.json","state":"https://pith.science/pith/FDF5G4ZL5T7AJDGRMVB6UNDCFB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FDF5G4ZL5T7AJDGRMVB6UNDCFB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FDF5G4ZL5T7AJDGRMVB6UNDCFB","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":"86b66bc9d80321ace79cb2311c43d1cd4dec27c5a81c202ee4a505e524a0987a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T20:59:02Z","title_canon_sha256":"e204126324d98815e2b9287aabe0af1398c8d54d87e2335d34aa03842e91fb5f"},"schema_version":"1.0","source":{"id":"1906.03704","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03704","created_at":"2026-07-05T01:11:33Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03704v2","created_at":"2026-07-05T01:11:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03704","created_at":"2026-07-05T01:11:33Z"},{"alias_kind":"pith_short_12","alias_value":"FDF5G4ZL5T7A","created_at":"2026-07-05T01:11:33Z"},{"alias_kind":"pith_short_16","alias_value":"FDF5G4ZL5T7AJDGR","created_at":"2026-07-05T01:11:33Z"},{"alias_kind":"pith_short_8","alias_value":"FDF5G4ZL","created_at":"2026-07-05T01:11:33Z"}],"graph_snapshots":[{"event_id":"sha256:ec602d12a4d37188d40492845dd762e312187b56ba82001bd96b2ba7c073d380","target":"graph","created_at":"2026-07-05T01:11:33Z","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/1906.03704/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic variance-reduced gradient (SVRG) is an optimization method originally designed for tackling machine learning problems with a finite sum structure. SVRG was later shown to work for policy evaluation, a problem in reinforcement learning in which one aims to estimate the value function of a given policy. SVRG makes use of gradient estimates at two scales. At the slower scale, SVRG computes a full gradient over the whole dataset, which could lead to prohibitive computation costs. In this work, we show that two variants of SVRG for policy evaluation could significantly diminish the numbe","authors_text":"Ahmed Touati, Doina Precup, Pascal Vincent, Zilun Peng","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T20:59:02Z","title":"SVRG for Policy Evaluation with Fewer Gradient Evaluations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03704","kind":"arxiv","version":2},"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:d89a14e75793de82287728c4a802687da8d38a685e4acc4ad1f7206a0715502d","target":"record","created_at":"2026-07-05T01:11:33Z","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":"86b66bc9d80321ace79cb2311c43d1cd4dec27c5a81c202ee4a505e524a0987a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-09T20:59:02Z","title_canon_sha256":"e204126324d98815e2b9287aabe0af1398c8d54d87e2335d34aa03842e91fb5f"},"schema_version":"1.0","source":{"id":"1906.03704","kind":"arxiv","version":2}},"canonical_sha256":"28cbd3732becfe048cd16543ea3462287eb584bd5139f741db9bc68292490721","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28cbd3732becfe048cd16543ea3462287eb584bd5139f741db9bc68292490721","first_computed_at":"2026-07-05T01:11:33.100594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:33.100594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jnzh2oZtN8ie+7rNO+riP4VkclHm8pyCYbfQe9PeXdhXu6Nl5npzyfdPQOVJn1egWn2OxJbou3VhC+0L8XSWAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:33.100993Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03704","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d89a14e75793de82287728c4a802687da8d38a685e4acc4ad1f7206a0715502d","sha256:ec602d12a4d37188d40492845dd762e312187b56ba82001bd96b2ba7c073d380"],"state_sha256":"f074560227fc7e837d2a325c8c8b3e31841a149ce16b339dbdd45f305da72e01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9reH9+5lbkUoKMBbC/985zupDbhgsflrRmjHWdOitLEfoOmgz460g9Tym6pyZwFd6H+Ho6GVlj5Ud8eiegqBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T17:05:34.668466Z","bundle_sha256":"75c9376690eebf9e7fef088c1cae37d7fc9af6bc081447ead6fee766b700ab5f"}}