{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4IW4HBPJJ3LQGR5RPAQIJXTR4Z","short_pith_number":"pith:4IW4HBPJ","canonical_record":{"source":{"id":"1707.00192","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-01T18:54:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"76ffc920f970ba2f5dd11603fa3693b7696c416876eba7b5fe4833ace12da891","abstract_canon_sha256":"f907bb9fe26e82bd3bdc62567841c77d0c9e5775da6d765c682ffc10c24b82c0"},"schema_version":"1.0"},"canonical_sha256":"e22dc385e94ed70347b1782084de71e65ec3192720eb30748320e0202227de49","source":{"kind":"arxiv","id":"1707.00192","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.00192","created_at":"2026-05-18T00:41:04Z"},{"alias_kind":"arxiv_version","alias_value":"1707.00192v1","created_at":"2026-05-18T00:41:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00192","created_at":"2026-05-18T00:41:04Z"},{"alias_kind":"pith_short_12","alias_value":"4IW4HBPJJ3LQ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4IW4HBPJJ3LQGR5R","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4IW4HBPJ","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4IW4HBPJJ3LQGR5RPAQIJXTR4Z","target":"record","payload":{"canonical_record":{"source":{"id":"1707.00192","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-01T18:54:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"76ffc920f970ba2f5dd11603fa3693b7696c416876eba7b5fe4833ace12da891","abstract_canon_sha256":"f907bb9fe26e82bd3bdc62567841c77d0c9e5775da6d765c682ffc10c24b82c0"},"schema_version":"1.0"},"canonical_sha256":"e22dc385e94ed70347b1782084de71e65ec3192720eb30748320e0202227de49","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:04.186282Z","signature_b64":"a704fmpSw2wpYRkIpWqQcNk6ubKOZYCMVuzAUn7/+Mde6E3thvuEJs1Z0sTqGcOx1u+81WUY5e+dARpqHbf1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e22dc385e94ed70347b1782084de71e65ec3192720eb30748320e0202227de49","last_reissued_at":"2026-05-18T00:41:04.185532Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:04.185532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.00192","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":"2026-05-18T00:41:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oxxwVXgPPH4oi9hvYKHZw1N2cjOIjhnXhxOz7RL1OTCG4CRos75yiH61Wui4L2ghFKiYKiRRJ2H89IwoYY5OBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:21:05.519512Z"},"content_sha256":"e9f08c4384218e05aba5892da3ceede2ad11adc1acac4cda7811fe5fdfdea3e8","schema_version":"1.0","event_id":"sha256:e9f08c4384218e05aba5892da3ceede2ad11adc1acac4cda7811fe5fdfdea3e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4IW4HBPJJ3LQGR5RPAQIJXTR4Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Scalable Inference with Stochastic Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jinfeng Xu, Lei Yang, Yixin Fang","submitted_at":"2017-07-01T18:54:34Z","abstract_excerpt":"In many applications involving large dataset or online updating, stochastic gradient descent (SGD) provides a scalable way to compute parameter estimates and has gained increasing popularity due to its numerical convenience and memory efficiency. While the asymptotic properties of SGD-based estimators have been established decades ago, statistical inference such as interval estimation remains much unexplored. The traditional resampling method such as the bootstrap is not computationally feasible since it requires to repeatedly draw independent samples from the entire dataset. The plug-in metho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00192","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":"2026-05-18T00:41:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SGzgmhmxMpJAsPBDMGKaXLohMRRpOmYqWIHtYXznYHCDvRuo4b1jDkXxCHU7IijGQDdOvz8RM1xCQVtLgIOQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:21:05.520187Z"},"content_sha256":"8a82b847e7247f18ac56aa9687a3149b6f8ee242996e742ac3b76ae33dd7fd36","schema_version":"1.0","event_id":"sha256:8a82b847e7247f18ac56aa9687a3149b6f8ee242996e742ac3b76ae33dd7fd36"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4IW4HBPJJ3LQGR5RPAQIJXTR4Z/bundle.json","state_url":"https://pith.science/pith/4IW4HBPJJ3LQGR5RPAQIJXTR4Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4IW4HBPJJ3LQGR5RPAQIJXTR4Z/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":"2026-05-27T05:21:05Z","links":{"resolver":"https://pith.science/pith/4IW4HBPJJ3LQGR5RPAQIJXTR4Z","bundle":"https://pith.science/pith/4IW4HBPJJ3LQGR5RPAQIJXTR4Z/bundle.json","state":"https://pith.science/pith/4IW4HBPJJ3LQGR5RPAQIJXTR4Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4IW4HBPJJ3LQGR5RPAQIJXTR4Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4IW4HBPJJ3LQGR5RPAQIJXTR4Z","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":"f907bb9fe26e82bd3bdc62567841c77d0c9e5775da6d765c682ffc10c24b82c0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-01T18:54:34Z","title_canon_sha256":"76ffc920f970ba2f5dd11603fa3693b7696c416876eba7b5fe4833ace12da891"},"schema_version":"1.0","source":{"id":"1707.00192","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.00192","created_at":"2026-05-18T00:41:04Z"},{"alias_kind":"arxiv_version","alias_value":"1707.00192v1","created_at":"2026-05-18T00:41:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00192","created_at":"2026-05-18T00:41:04Z"},{"alias_kind":"pith_short_12","alias_value":"4IW4HBPJJ3LQ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4IW4HBPJJ3LQGR5R","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4IW4HBPJ","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:8a82b847e7247f18ac56aa9687a3149b6f8ee242996e742ac3b76ae33dd7fd36","target":"graph","created_at":"2026-05-18T00:41:04Z","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 many applications involving large dataset or online updating, stochastic gradient descent (SGD) provides a scalable way to compute parameter estimates and has gained increasing popularity due to its numerical convenience and memory efficiency. While the asymptotic properties of SGD-based estimators have been established decades ago, statistical inference such as interval estimation remains much unexplored. The traditional resampling method such as the bootstrap is not computationally feasible since it requires to repeatedly draw independent samples from the entire dataset. The plug-in metho","authors_text":"Jinfeng Xu, Lei Yang, Yixin Fang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-01T18:54:34Z","title":"On Scalable Inference with Stochastic Gradient Descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00192","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:e9f08c4384218e05aba5892da3ceede2ad11adc1acac4cda7811fe5fdfdea3e8","target":"record","created_at":"2026-05-18T00:41:04Z","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":"f907bb9fe26e82bd3bdc62567841c77d0c9e5775da6d765c682ffc10c24b82c0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-01T18:54:34Z","title_canon_sha256":"76ffc920f970ba2f5dd11603fa3693b7696c416876eba7b5fe4833ace12da891"},"schema_version":"1.0","source":{"id":"1707.00192","kind":"arxiv","version":1}},"canonical_sha256":"e22dc385e94ed70347b1782084de71e65ec3192720eb30748320e0202227de49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e22dc385e94ed70347b1782084de71e65ec3192720eb30748320e0202227de49","first_computed_at":"2026-05-18T00:41:04.185532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:41:04.185532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a704fmpSw2wpYRkIpWqQcNk6ubKOZYCMVuzAUn7/+Mde6E3thvuEJs1Z0sTqGcOx1u+81WUY5e+dARpqHbf1CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:41:04.186282Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.00192","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9f08c4384218e05aba5892da3ceede2ad11adc1acac4cda7811fe5fdfdea3e8","sha256:8a82b847e7247f18ac56aa9687a3149b6f8ee242996e742ac3b76ae33dd7fd36"],"state_sha256":"aa6d0ddd8d56f51c4ab46b2c15bde60bbc1fe5ed5138402ae69db966bdd5590a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"03sO6u90j6I1+Ah+OWywQOWxqUrbvodaOZjojgLXn3PQmQP3FJxK7KS/4iPFRjFMPQGoYgbYDFTGFV/d3rD7CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T05:21:05.524073Z","bundle_sha256":"14e07ce5ec6b3a3d49d34e5891202f1f7ed25fa4f944dcfa38300a214e36166b"}}