{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:EPNLAVKAK4HOKIZBVU6ZULL2YE","short_pith_number":"pith:EPNLAVKA","canonical_record":{"source":{"id":"1607.07329","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-07-25T15:56:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"127b70f8d7b9040ae830b7f950bd6194386c84910ef9ce702fa1bfb007e6ae8e","abstract_canon_sha256":"dfc8a06dcedc89d43dd9e84a2e1bc23f584500e77507ec3f0e4cd35145e8d116"},"schema_version":"1.0"},"canonical_sha256":"23dab05540570ee52321ad3d9a2d7ac13089fbbf7f5bf9b38f0b42acd2c27826","source":{"kind":"arxiv","id":"1607.07329","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.07329","created_at":"2026-05-18T01:10:34Z"},{"alias_kind":"arxiv_version","alias_value":"1607.07329v1","created_at":"2026-05-18T01:10:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.07329","created_at":"2026-05-18T01:10:34Z"},{"alias_kind":"pith_short_12","alias_value":"EPNLAVKAK4HO","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"EPNLAVKAK4HOKIZB","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"EPNLAVKA","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:EPNLAVKAK4HOKIZBVU6ZULL2YE","target":"record","payload":{"canonical_record":{"source":{"id":"1607.07329","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-07-25T15:56:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"127b70f8d7b9040ae830b7f950bd6194386c84910ef9ce702fa1bfb007e6ae8e","abstract_canon_sha256":"dfc8a06dcedc89d43dd9e84a2e1bc23f584500e77507ec3f0e4cd35145e8d116"},"schema_version":"1.0"},"canonical_sha256":"23dab05540570ee52321ad3d9a2d7ac13089fbbf7f5bf9b38f0b42acd2c27826","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:34.177953Z","signature_b64":"f4NzpBBNY1NCCS1Ir9nVzJBTW/bJPkjzqci9sbRyVG8muUy5wn0rVJtyXeKG5IciJM02CFnHYUcYzP2J9HIFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23dab05540570ee52321ad3d9a2d7ac13089fbbf7f5bf9b38f0b42acd2c27826","last_reissued_at":"2026-05-18T01:10:34.177172Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:34.177172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1607.07329","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":"2026-05-18T01:10:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S86VbC2v4yb2tzkz82TLf/RBRXX0O3cTbWvyccSm2p73WEVWl8F2fOo5Z9SFvMdbedMZeVA9RkUW7wg80LxoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T23:06:42.404475Z"},"content_sha256":"07941ff0c5bb52d6b8c968c9ad16f4b2f99c4f628bacbf811780d2feeb76932b","schema_version":"1.0","event_id":"sha256:07941ff0c5bb52d6b8c968c9ad16f4b2f99c4f628bacbf811780d2feeb76932b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:EPNLAVKAK4HOKIZBVU6ZULL2YE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating Stochastic Composition Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Ethan X. Fang, Ji Liu, Mengdi Wang","submitted_at":"2016-07-25T15:56:49Z","abstract_excerpt":"Consider the stochastic composition optimization problem where the objective is a composition of two expected-value functions. We propose a new stochastic first-order method, namely the accelerated stochastic compositional proximal gradient (ASC-PG) method, which updates based on queries to the sampling oracle using two different timescales. The ASC-PG is the first proximal gradient method for the stochastic composition problem that can deal with nonsmooth regularization penalty. We show that the ASC-PG exhibits faster convergence than the best known algorithms, and that it achieves the optima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.07329","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":""},"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":"2026-05-18T01:10:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ohUp7NHmQQgjIAexxnT9R+jRum1OlbrewdaCUhFBDYFBZ/zMHQKfn9xZst1QbIwgx7neyaA3JazpvYRd4Z8/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T23:06:42.405243Z"},"content_sha256":"ddba86f3fdbe814fe21fc0babfd4ca00d38faf70da39363d06a9eb160df4d58d","schema_version":"1.0","event_id":"sha256:ddba86f3fdbe814fe21fc0babfd4ca00d38faf70da39363d06a9eb160df4d58d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPNLAVKAK4HOKIZBVU6ZULL2YE/bundle.json","state_url":"https://pith.science/pith/EPNLAVKAK4HOKIZBVU6ZULL2YE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPNLAVKAK4HOKIZBVU6ZULL2YE/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":"2026-06-05T23:06:42Z","links":{"resolver":"https://pith.science/pith/EPNLAVKAK4HOKIZBVU6ZULL2YE","bundle":"https://pith.science/pith/EPNLAVKAK4HOKIZBVU6ZULL2YE/bundle.json","state":"https://pith.science/pith/EPNLAVKAK4HOKIZBVU6ZULL2YE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPNLAVKAK4HOKIZBVU6ZULL2YE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:EPNLAVKAK4HOKIZBVU6ZULL2YE","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":"dfc8a06dcedc89d43dd9e84a2e1bc23f584500e77507ec3f0e4cd35145e8d116","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-07-25T15:56:49Z","title_canon_sha256":"127b70f8d7b9040ae830b7f950bd6194386c84910ef9ce702fa1bfb007e6ae8e"},"schema_version":"1.0","source":{"id":"1607.07329","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.07329","created_at":"2026-05-18T01:10:34Z"},{"alias_kind":"arxiv_version","alias_value":"1607.07329v1","created_at":"2026-05-18T01:10:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.07329","created_at":"2026-05-18T01:10:34Z"},{"alias_kind":"pith_short_12","alias_value":"EPNLAVKAK4HO","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"EPNLAVKAK4HOKIZB","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"EPNLAVKA","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:ddba86f3fdbe814fe21fc0babfd4ca00d38faf70da39363d06a9eb160df4d58d","target":"graph","created_at":"2026-05-18T01:10:34Z","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"},"paper":{"abstract_excerpt":"Consider the stochastic composition optimization problem where the objective is a composition of two expected-value functions. We propose a new stochastic first-order method, namely the accelerated stochastic compositional proximal gradient (ASC-PG) method, which updates based on queries to the sampling oracle using two different timescales. The ASC-PG is the first proximal gradient method for the stochastic composition problem that can deal with nonsmooth regularization penalty. We show that the ASC-PG exhibits faster convergence than the best known algorithms, and that it achieves the optima","authors_text":"Ethan X. Fang, Ji Liu, Mengdi Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-07-25T15:56:49Z","title":"Accelerating Stochastic Composition Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.07329","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":"sha256:07941ff0c5bb52d6b8c968c9ad16f4b2f99c4f628bacbf811780d2feeb76932b","target":"record","created_at":"2026-05-18T01:10:34Z","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":"dfc8a06dcedc89d43dd9e84a2e1bc23f584500e77507ec3f0e4cd35145e8d116","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-07-25T15:56:49Z","title_canon_sha256":"127b70f8d7b9040ae830b7f950bd6194386c84910ef9ce702fa1bfb007e6ae8e"},"schema_version":"1.0","source":{"id":"1607.07329","kind":"arxiv","version":1}},"canonical_sha256":"23dab05540570ee52321ad3d9a2d7ac13089fbbf7f5bf9b38f0b42acd2c27826","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23dab05540570ee52321ad3d9a2d7ac13089fbbf7f5bf9b38f0b42acd2c27826","first_computed_at":"2026-05-18T01:10:34.177172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:10:34.177172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f4NzpBBNY1NCCS1Ir9nVzJBTW/bJPkjzqci9sbRyVG8muUy5wn0rVJtyXeKG5IciJM02CFnHYUcYzP2J9HIFCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:10:34.177953Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.07329","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07941ff0c5bb52d6b8c968c9ad16f4b2f99c4f628bacbf811780d2feeb76932b","sha256:ddba86f3fdbe814fe21fc0babfd4ca00d38faf70da39363d06a9eb160df4d58d"],"state_sha256":"55fbd7e22a72a50ef68ef1c3d7d9d8f9e93ef7373b7e38d6ebda6337c8d0d138"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qMRm4fA+dLjDKBb60ppeAYgrFGqxZTr9sRo+nnELw1OXPLEWQ5RorCYvjyX3KDq2zdBARbYZkpF7XSH6QwD6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T23:06:42.409849Z","bundle_sha256":"10ad8720b8304408ee191410fa2788fe470e2420158367731993025b8085036d"}}