{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:345MTHRLPUUMU3XBVHSEAUVWJU","short_pith_number":"pith:345MTHRL","canonical_record":{"source":{"id":"1505.02417","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-05-10T18:10:07Z","cross_cats_sorted":["cs.LG","stat.CO","stat.ML"],"title_canon_sha256":"5a37197d5dcdb0d42030e4c63b6d4cdfed43f021e0229b0a41c5ca5880450f4e","abstract_canon_sha256":"a4939f5701a25103019a0904ca41c06dda1b0f0259a3b8eab15b1a828850236d"},"schema_version":"1.0"},"canonical_sha256":"df3ac99e2b7d28ca6ee1a9e44052b64d28d9b66aaf1b2812889b29ab89e42eb8","source":{"kind":"arxiv","id":"1505.02417","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.02417","created_at":"2026-05-18T01:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"1505.02417v4","created_at":"2026-05-18T01:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.02417","created_at":"2026-05-18T01:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"345MTHRLPUUM","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"345MTHRLPUUMU3XB","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"345MTHRL","created_at":"2026-05-18T12:29:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:345MTHRLPUUMU3XBVHSEAUVWJU","target":"record","payload":{"canonical_record":{"source":{"id":"1505.02417","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-05-10T18:10:07Z","cross_cats_sorted":["cs.LG","stat.CO","stat.ML"],"title_canon_sha256":"5a37197d5dcdb0d42030e4c63b6d4cdfed43f021e0229b0a41c5ca5880450f4e","abstract_canon_sha256":"a4939f5701a25103019a0904ca41c06dda1b0f0259a3b8eab15b1a828850236d"},"schema_version":"1.0"},"canonical_sha256":"df3ac99e2b7d28ca6ee1a9e44052b64d28d9b66aaf1b2812889b29ab89e42eb8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:49.915954Z","signature_b64":"2v7tsUYBKLvdRXpG2i/Es1myc5Yb+/KaR+Mw53DWhdh7PP9smmtjBCUjZWa35yh9Ywx8pYBuG2adPdmYUX3wDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df3ac99e2b7d28ca6ee1a9e44052b64d28d9b66aaf1b2812889b29ab89e42eb8","last_reissued_at":"2026-05-18T01:12:49.915599Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:49.915599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1505.02417","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lFvix1jTaOo6dwt3PwKKavExwDSbdEvjncpS0PNcriY/JyC4v7OHr82GB9Wn2iTvmw9perpqwnG7oeT58U/mBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T10:08:31.235250Z"},"content_sha256":"dc902919604f9e6e6d464eeaad032ee1b413c9392c44ad87969820f3ed9913e1","schema_version":"1.0","event_id":"sha256:dc902919604f9e6e6d464eeaad032ee1b413c9392c44ad87969820f3ed9913e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:345MTHRLPUUMU3XBVHSEAUVWJU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards stability and optimality in stochastic gradient descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.CO","stat.ML"],"primary_cat":"stat.ME","authors_text":"Dustin Tran, Edoardo M. Airoldi, Panos Toulis","submitted_at":"2015-05-10T18:10:07Z","abstract_excerpt":"Iterative procedures for parameter estimation based on stochastic gradient descent allow the estimation to scale to massive data sets. However, in both theory and practice, they suffer from numerical instability. Moreover, they are statistically inefficient as estimators of the true parameter value. To address these two issues, we propose a new iterative procedure termed averaged implicit SGD (AI-SGD). For statistical efficiency, AI-SGD employs averaging of the iterates, which achieves the optimal Cram\\'{e}r-Rao bound under strong convexity, i.e., it is an optimal unbiased estimator of the tru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.02417","kind":"arxiv","version":4},"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":"2026-05-18T01:12:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t0o4NuiDTagBnG5u2Q7IqPozN3NiroDXDtUNS0wDUygNm/SQNUO49cW0mhgvwTw8mrsAGTgEwx3G52oFXSkxDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T10:08:31.235911Z"},"content_sha256":"b095a82187fab87fdcd49f63f7bff53a7592dcc7b89c8046d0e74377911c0f9b","schema_version":"1.0","event_id":"sha256:b095a82187fab87fdcd49f63f7bff53a7592dcc7b89c8046d0e74377911c0f9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/345MTHRLPUUMU3XBVHSEAUVWJU/bundle.json","state_url":"https://pith.science/pith/345MTHRLPUUMU3XBVHSEAUVWJU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/345MTHRLPUUMU3XBVHSEAUVWJU/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":"2026-06-07T10:08:31Z","links":{"resolver":"https://pith.science/pith/345MTHRLPUUMU3XBVHSEAUVWJU","bundle":"https://pith.science/pith/345MTHRLPUUMU3XBVHSEAUVWJU/bundle.json","state":"https://pith.science/pith/345MTHRLPUUMU3XBVHSEAUVWJU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/345MTHRLPUUMU3XBVHSEAUVWJU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:345MTHRLPUUMU3XBVHSEAUVWJU","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":"a4939f5701a25103019a0904ca41c06dda1b0f0259a3b8eab15b1a828850236d","cross_cats_sorted":["cs.LG","stat.CO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-05-10T18:10:07Z","title_canon_sha256":"5a37197d5dcdb0d42030e4c63b6d4cdfed43f021e0229b0a41c5ca5880450f4e"},"schema_version":"1.0","source":{"id":"1505.02417","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.02417","created_at":"2026-05-18T01:12:49Z"},{"alias_kind":"arxiv_version","alias_value":"1505.02417v4","created_at":"2026-05-18T01:12:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.02417","created_at":"2026-05-18T01:12:49Z"},{"alias_kind":"pith_short_12","alias_value":"345MTHRLPUUM","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"345MTHRLPUUMU3XB","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"345MTHRL","created_at":"2026-05-18T12:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:b095a82187fab87fdcd49f63f7bff53a7592dcc7b89c8046d0e74377911c0f9b","target":"graph","created_at":"2026-05-18T01:12:49Z","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":"Iterative procedures for parameter estimation based on stochastic gradient descent allow the estimation to scale to massive data sets. However, in both theory and practice, they suffer from numerical instability. Moreover, they are statistically inefficient as estimators of the true parameter value. To address these two issues, we propose a new iterative procedure termed averaged implicit SGD (AI-SGD). For statistical efficiency, AI-SGD employs averaging of the iterates, which achieves the optimal Cram\\'{e}r-Rao bound under strong convexity, i.e., it is an optimal unbiased estimator of the tru","authors_text":"Dustin Tran, Edoardo M. Airoldi, Panos Toulis","cross_cats":["cs.LG","stat.CO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-05-10T18:10:07Z","title":"Towards stability and optimality in stochastic gradient descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.02417","kind":"arxiv","version":4},"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:dc902919604f9e6e6d464eeaad032ee1b413c9392c44ad87969820f3ed9913e1","target":"record","created_at":"2026-05-18T01:12:49Z","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":"a4939f5701a25103019a0904ca41c06dda1b0f0259a3b8eab15b1a828850236d","cross_cats_sorted":["cs.LG","stat.CO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2015-05-10T18:10:07Z","title_canon_sha256":"5a37197d5dcdb0d42030e4c63b6d4cdfed43f021e0229b0a41c5ca5880450f4e"},"schema_version":"1.0","source":{"id":"1505.02417","kind":"arxiv","version":4}},"canonical_sha256":"df3ac99e2b7d28ca6ee1a9e44052b64d28d9b66aaf1b2812889b29ab89e42eb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df3ac99e2b7d28ca6ee1a9e44052b64d28d9b66aaf1b2812889b29ab89e42eb8","first_computed_at":"2026-05-18T01:12:49.915599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:49.915599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2v7tsUYBKLvdRXpG2i/Es1myc5Yb+/KaR+Mw53DWhdh7PP9smmtjBCUjZWa35yh9Ywx8pYBuG2adPdmYUX3wDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:49.915954Z","signed_message":"canonical_sha256_bytes"},"source_id":"1505.02417","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc902919604f9e6e6d464eeaad032ee1b413c9392c44ad87969820f3ed9913e1","sha256:b095a82187fab87fdcd49f63f7bff53a7592dcc7b89c8046d0e74377911c0f9b"],"state_sha256":"591ffbc71d97aa47c76258942325514802e39d0ea5094786baf7f313f7aec438"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rS2IYDmU0VD/4IRfWILgIuU7UyKfWrFtSWVGz5FIzb52OOfeIu34VRhSflQRHxfJfNP8v2M6Q2I85eKKo+87BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T10:08:31.239245Z","bundle_sha256":"32847f83e0d1ff45ffc73369fc74c9fd5c8e052c1a52597d52f2e79ba3d887e7"}}