{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TBZZD7QH6HYRTBO5VRF7MZOKAU","short_pith_number":"pith:TBZZD7QH","canonical_record":{"source":{"id":"2110.15572","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-29T06:35:44Z","cross_cats_sorted":[],"title_canon_sha256":"b0dbb164bb0b06e36033a4df212f837d2e837943c10485d5770a398a5f003b45","abstract_canon_sha256":"442aea086bd446b9ef8fc3d4099765321bd80abc8ad93eb08f1119d55cad9697"},"schema_version":"1.0"},"canonical_sha256":"987391fe07f1f11985ddac4bf665ca051d2bb05997cdfc1c707766c658766340","source":{"kind":"arxiv","id":"2110.15572","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.15572","created_at":"2026-07-05T03:27:11Z"},{"alias_kind":"arxiv_version","alias_value":"2110.15572v1","created_at":"2026-07-05T03:27:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15572","created_at":"2026-07-05T03:27:11Z"},{"alias_kind":"pith_short_12","alias_value":"TBZZD7QH6HYR","created_at":"2026-07-05T03:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"TBZZD7QH6HYRTBO5","created_at":"2026-07-05T03:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"TBZZD7QH","created_at":"2026-07-05T03:27:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TBZZD7QH6HYRTBO5VRF7MZOKAU","target":"record","payload":{"canonical_record":{"source":{"id":"2110.15572","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-29T06:35:44Z","cross_cats_sorted":[],"title_canon_sha256":"b0dbb164bb0b06e36033a4df212f837d2e837943c10485d5770a398a5f003b45","abstract_canon_sha256":"442aea086bd446b9ef8fc3d4099765321bd80abc8ad93eb08f1119d55cad9697"},"schema_version":"1.0"},"canonical_sha256":"987391fe07f1f11985ddac4bf665ca051d2bb05997cdfc1c707766c658766340","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:11.353659Z","signature_b64":"kuUfEgICiBdOBSpbwKfs3fc1h4dMn56OCY3Jmk9rm0Zs4FWpxqDX5DtLqI9NJqxQVrj/yDNqtU4OjnYnTKA7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"987391fe07f1f11985ddac4bf665ca051d2bb05997cdfc1c707766c658766340","last_reissued_at":"2026-07-05T03:27:11.353216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:11.353216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.15572","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":"2026-07-05T03:27:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nYSL50e3tECS7fA6l6+Ozl1bA2ZVZRRCPnU+pycTOUspDWDP4NclSQTs6ywMnpYVceh3oenkC4YJaaDXJq22Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T07:31:33.941701Z"},"content_sha256":"932245c4be1d308323f6f75b854635dde11b3a17946598abf75c1e4b9d45c5dc","schema_version":"1.0","event_id":"sha256:932245c4be1d308323f6f75b854635dde11b3a17946598abf75c1e4b9d45c5dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TBZZD7QH6HYRTBO5VRF7MZOKAU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding the Effect of Stochasticity in Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Dai, Chenjun Xiao, Csaba Szepesvari, Dale Schuurmans, Jincheng Mei","submitted_at":"2021-10-29T06:35:44Z","abstract_excerpt":"We study the effect of stochasticity in on-policy policy optimization, and make the following four contributions. First, we show that the preferability of optimization methods depends critically on whether stochastic versus exact gradients are used. In particular, unlike the true gradient setting, geometric information cannot be easily exploited in the stochastic case for accelerating policy optimization without detrimental consequences or impractical assumptions. Second, to explain these findings we introduce the concept of committal rate for stochastic policy optimization, and show that this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15572","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/2110.15572/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":"2026-07-05T03:27:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Mzzd+aBfze/E5sGV3GxB99Qq1zd6RV0BKq191WDESqBc1cySPhgIASdV4ifvvNvZTFtE4A0bJLQBNzpxUd2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T07:31:33.942072Z"},"content_sha256":"14e9f8b33ddb0b1598815eaecc8efcd3a6bb95cae54bc2514cbf25a84ac889de","schema_version":"1.0","event_id":"sha256:14e9f8b33ddb0b1598815eaecc8efcd3a6bb95cae54bc2514cbf25a84ac889de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TBZZD7QH6HYRTBO5VRF7MZOKAU/bundle.json","state_url":"https://pith.science/pith/TBZZD7QH6HYRTBO5VRF7MZOKAU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TBZZD7QH6HYRTBO5VRF7MZOKAU/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":"2026-07-06T07:31:33Z","links":{"resolver":"https://pith.science/pith/TBZZD7QH6HYRTBO5VRF7MZOKAU","bundle":"https://pith.science/pith/TBZZD7QH6HYRTBO5VRF7MZOKAU/bundle.json","state":"https://pith.science/pith/TBZZD7QH6HYRTBO5VRF7MZOKAU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TBZZD7QH6HYRTBO5VRF7MZOKAU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TBZZD7QH6HYRTBO5VRF7MZOKAU","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":"442aea086bd446b9ef8fc3d4099765321bd80abc8ad93eb08f1119d55cad9697","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-29T06:35:44Z","title_canon_sha256":"b0dbb164bb0b06e36033a4df212f837d2e837943c10485d5770a398a5f003b45"},"schema_version":"1.0","source":{"id":"2110.15572","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.15572","created_at":"2026-07-05T03:27:11Z"},{"alias_kind":"arxiv_version","alias_value":"2110.15572v1","created_at":"2026-07-05T03:27:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15572","created_at":"2026-07-05T03:27:11Z"},{"alias_kind":"pith_short_12","alias_value":"TBZZD7QH6HYR","created_at":"2026-07-05T03:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"TBZZD7QH6HYRTBO5","created_at":"2026-07-05T03:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"TBZZD7QH","created_at":"2026-07-05T03:27:11Z"}],"graph_snapshots":[{"event_id":"sha256:14e9f8b33ddb0b1598815eaecc8efcd3a6bb95cae54bc2514cbf25a84ac889de","target":"graph","created_at":"2026-07-05T03:27:11Z","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/2110.15572/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the effect of stochasticity in on-policy policy optimization, and make the following four contributions. First, we show that the preferability of optimization methods depends critically on whether stochastic versus exact gradients are used. In particular, unlike the true gradient setting, geometric information cannot be easily exploited in the stochastic case for accelerating policy optimization without detrimental consequences or impractical assumptions. Second, to explain these findings we introduce the concept of committal rate for stochastic policy optimization, and show that this","authors_text":"Bo Dai, Chenjun Xiao, Csaba Szepesvari, Dale Schuurmans, Jincheng Mei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-29T06:35:44Z","title":"Understanding the Effect of Stochasticity in Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15572","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":"sha256:932245c4be1d308323f6f75b854635dde11b3a17946598abf75c1e4b9d45c5dc","target":"record","created_at":"2026-07-05T03:27:11Z","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":"442aea086bd446b9ef8fc3d4099765321bd80abc8ad93eb08f1119d55cad9697","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-29T06:35:44Z","title_canon_sha256":"b0dbb164bb0b06e36033a4df212f837d2e837943c10485d5770a398a5f003b45"},"schema_version":"1.0","source":{"id":"2110.15572","kind":"arxiv","version":1}},"canonical_sha256":"987391fe07f1f11985ddac4bf665ca051d2bb05997cdfc1c707766c658766340","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"987391fe07f1f11985ddac4bf665ca051d2bb05997cdfc1c707766c658766340","first_computed_at":"2026-07-05T03:27:11.353216Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:11.353216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kuUfEgICiBdOBSpbwKfs3fc1h4dMn56OCY3Jmk9rm0Zs4FWpxqDX5DtLqI9NJqxQVrj/yDNqtU4OjnYnTKA7Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:11.353659Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.15572","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:932245c4be1d308323f6f75b854635dde11b3a17946598abf75c1e4b9d45c5dc","sha256:14e9f8b33ddb0b1598815eaecc8efcd3a6bb95cae54bc2514cbf25a84ac889de"],"state_sha256":"bc0ab1befe2148d588aaae58a4e6d3d061709786240268aec54a68ee6bd56f50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jsXSmfnM7McgarEYSme5EUY3In+XpNNxF4cF1+DcZstNInBTI3ppVuiH9IDORE+mKSrPZiqrqQurrTNOr9DoCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T07:31:33.944039Z","bundle_sha256":"ad2349b3a791b395391eada6fefe2655afc6c068df9fa7692ad21c268cd5e966"}}