{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:B2TXQTELMD3P3I6YDMCCJ3GG4H","short_pith_number":"pith:B2TXQTEL","canonical_record":{"source":{"id":"1611.03608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-11T08:23:30Z","cross_cats_sorted":[],"title_canon_sha256":"11e8d542c30833b615d2bde826f99a34026b7906c4e60257f9b2c754834a2f71","abstract_canon_sha256":"d0438bcac05f9ba44dd995da8725ca41dd3e0151e879a62ca86e396b08c4d65d"},"schema_version":"1.0"},"canonical_sha256":"0ea7784c8b60f6fda3d81b0424ecc6e1e5b01d1a42739ae0d225c05b64d0e922","source":{"kind":"arxiv","id":"1611.03608","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.03608","created_at":"2026-05-18T00:59:33Z"},{"alias_kind":"arxiv_version","alias_value":"1611.03608v1","created_at":"2026-05-18T00:59:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.03608","created_at":"2026-05-18T00:59:33Z"},{"alias_kind":"pith_short_12","alias_value":"B2TXQTELMD3P","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"B2TXQTELMD3P3I6Y","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"B2TXQTEL","created_at":"2026-05-18T12:30:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:B2TXQTELMD3P3I6YDMCCJ3GG4H","target":"record","payload":{"canonical_record":{"source":{"id":"1611.03608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-11T08:23:30Z","cross_cats_sorted":[],"title_canon_sha256":"11e8d542c30833b615d2bde826f99a34026b7906c4e60257f9b2c754834a2f71","abstract_canon_sha256":"d0438bcac05f9ba44dd995da8725ca41dd3e0151e879a62ca86e396b08c4d65d"},"schema_version":"1.0"},"canonical_sha256":"0ea7784c8b60f6fda3d81b0424ecc6e1e5b01d1a42739ae0d225c05b64d0e922","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:59:33.725013Z","signature_b64":"CrZktdH3eI+vo8+LBnF+vaUFb0KZe/EudqvGZzQGEobqxSRiF0DgG6QQUDd12j4Yb6c2xuZpWkNnxdboXJmqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ea7784c8b60f6fda3d81b0424ecc6e1e5b01d1a42739ae0d225c05b64d0e922","last_reissued_at":"2026-05-18T00:59:33.724526Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:59:33.724526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.03608","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":"2026-05-18T00:59:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Srgo+TUUvu3y7D0lVuPXaJ06m845iccbv22FSyHWjBFjz1F/owq5yR2hAakWM0O3Dcr6UW0MKKjXR9qEMefEAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:03:18.950207Z"},"content_sha256":"1f9011ae65c30afdf6fbec996b2260750dc38c37811a6f28ba0d59c9c19769b6","schema_version":"1.0","event_id":"sha256:1f9011ae65c30afdf6fbec996b2260750dc38c37811a6f28ba0d59c9c19769b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:B2TXQTELMD3P3I6YDMCCJ3GG4H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Greedy Step Averaging: A parameter-free stochastic optimization method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fan Yao, Xiatian Zhang, Yongjun Tian","submitted_at":"2016-11-11T08:23:30Z","abstract_excerpt":"In this paper we present the greedy step averaging(GSA) method, a parameter-free stochastic optimization algorithm for a variety of machine learning problems. As a gradient-based optimization method, GSA makes use of the information from the minimizer of a single sample's loss function, and takes average strategy to calculate reasonable learning rate sequence. While most existing gradient-based algorithms introduce an increasing number of hyper parameters or try to make a trade-off between computational cost and convergence rate, GSA avoids the manual tuning of learning rate and brings in no m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.03608","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":"2026-05-18T00:59:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a/0iLyhpRSJoRas8sHcIwskfHKQ1X5fw/laVhYoPgU7tEL5UaKCgK5XkKKg9+fluW/MrLeDono1Ej1UU43BtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T22:03:18.950567Z"},"content_sha256":"48f44c569313a3d1c75e87041be41925ec1c3f12d42db330b21e0bf281bdff93","schema_version":"1.0","event_id":"sha256:48f44c569313a3d1c75e87041be41925ec1c3f12d42db330b21e0bf281bdff93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B2TXQTELMD3P3I6YDMCCJ3GG4H/bundle.json","state_url":"https://pith.science/pith/B2TXQTELMD3P3I6YDMCCJ3GG4H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B2TXQTELMD3P3I6YDMCCJ3GG4H/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":"2026-06-02T22:03:18Z","links":{"resolver":"https://pith.science/pith/B2TXQTELMD3P3I6YDMCCJ3GG4H","bundle":"https://pith.science/pith/B2TXQTELMD3P3I6YDMCCJ3GG4H/bundle.json","state":"https://pith.science/pith/B2TXQTELMD3P3I6YDMCCJ3GG4H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B2TXQTELMD3P3I6YDMCCJ3GG4H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:B2TXQTELMD3P3I6YDMCCJ3GG4H","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":"d0438bcac05f9ba44dd995da8725ca41dd3e0151e879a62ca86e396b08c4d65d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-11T08:23:30Z","title_canon_sha256":"11e8d542c30833b615d2bde826f99a34026b7906c4e60257f9b2c754834a2f71"},"schema_version":"1.0","source":{"id":"1611.03608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.03608","created_at":"2026-05-18T00:59:33Z"},{"alias_kind":"arxiv_version","alias_value":"1611.03608v1","created_at":"2026-05-18T00:59:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.03608","created_at":"2026-05-18T00:59:33Z"},{"alias_kind":"pith_short_12","alias_value":"B2TXQTELMD3P","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"B2TXQTELMD3P3I6Y","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"B2TXQTEL","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:48f44c569313a3d1c75e87041be41925ec1c3f12d42db330b21e0bf281bdff93","target":"graph","created_at":"2026-05-18T00:59:33Z","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"},"paper":{"abstract_excerpt":"In this paper we present the greedy step averaging(GSA) method, a parameter-free stochastic optimization algorithm for a variety of machine learning problems. As a gradient-based optimization method, GSA makes use of the information from the minimizer of a single sample's loss function, and takes average strategy to calculate reasonable learning rate sequence. While most existing gradient-based algorithms introduce an increasing number of hyper parameters or try to make a trade-off between computational cost and convergence rate, GSA avoids the manual tuning of learning rate and brings in no m","authors_text":"Fan Yao, Xiatian Zhang, Yongjun Tian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-11T08:23:30Z","title":"Greedy Step Averaging: A parameter-free stochastic optimization method"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.03608","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":"sha256:1f9011ae65c30afdf6fbec996b2260750dc38c37811a6f28ba0d59c9c19769b6","target":"record","created_at":"2026-05-18T00:59:33Z","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":"d0438bcac05f9ba44dd995da8725ca41dd3e0151e879a62ca86e396b08c4d65d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-11T08:23:30Z","title_canon_sha256":"11e8d542c30833b615d2bde826f99a34026b7906c4e60257f9b2c754834a2f71"},"schema_version":"1.0","source":{"id":"1611.03608","kind":"arxiv","version":1}},"canonical_sha256":"0ea7784c8b60f6fda3d81b0424ecc6e1e5b01d1a42739ae0d225c05b64d0e922","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ea7784c8b60f6fda3d81b0424ecc6e1e5b01d1a42739ae0d225c05b64d0e922","first_computed_at":"2026-05-18T00:59:33.724526Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:59:33.724526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CrZktdH3eI+vo8+LBnF+vaUFb0KZe/EudqvGZzQGEobqxSRiF0DgG6QQUDd12j4Yb6c2xuZpWkNnxdboXJmqCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:59:33.725013Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.03608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f9011ae65c30afdf6fbec996b2260750dc38c37811a6f28ba0d59c9c19769b6","sha256:48f44c569313a3d1c75e87041be41925ec1c3f12d42db330b21e0bf281bdff93"],"state_sha256":"aa6fe1e573a1440a25110ebb453d7d171225da5a06d746b3c1c9eee05f7367aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TNtG9UnTwGc/sxuPwOPm63X8MUpuNXhcxFTHd9JSC7ipsdYdC5UOTIDxvoiUiOspmIgcqe1YYuzz1vqiCXMaCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T22:03:18.952490Z","bundle_sha256":"563e4e396034800a4528e97a9c590abbae0a8f912b255065ec0ea3a5410d14a9"}}