{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:DVH35Q4AKMVIQYXFU45GWPXT7S","short_pith_number":"pith:DVH35Q4A","canonical_record":{"source":{"id":"1304.5586","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2013-04-20T04:23:34Z","cross_cats_sorted":[],"title_canon_sha256":"f612c66526f4003d3a1e9c647a2069927a566bc576f05094592017d234a43f57","abstract_canon_sha256":"7cdfe4089a89cab574978aaa1ecc26b9a671407206131526cf664b748dbc2900"},"schema_version":"1.0"},"canonical_sha256":"1d4fbec380532a8862e5a73a6b3ef3fc917411fc1283ebee344a499dc090ddb2","source":{"kind":"arxiv","id":"1304.5586","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1304.5586","created_at":"2026-05-18T03:02:59Z"},{"alias_kind":"arxiv_version","alias_value":"1304.5586v2","created_at":"2026-05-18T03:02:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1304.5586","created_at":"2026-05-18T03:02:59Z"},{"alias_kind":"pith_short_12","alias_value":"DVH35Q4AKMVI","created_at":"2026-05-18T12:27:43Z"},{"alias_kind":"pith_short_16","alias_value":"DVH35Q4AKMVIQYXF","created_at":"2026-05-18T12:27:43Z"},{"alias_kind":"pith_short_8","alias_value":"DVH35Q4A","created_at":"2026-05-18T12:27:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:DVH35Q4AKMVIQYXFU45GWPXT7S","target":"record","payload":{"canonical_record":{"source":{"id":"1304.5586","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2013-04-20T04:23:34Z","cross_cats_sorted":[],"title_canon_sha256":"f612c66526f4003d3a1e9c647a2069927a566bc576f05094592017d234a43f57","abstract_canon_sha256":"7cdfe4089a89cab574978aaa1ecc26b9a671407206131526cf664b748dbc2900"},"schema_version":"1.0"},"canonical_sha256":"1d4fbec380532a8862e5a73a6b3ef3fc917411fc1283ebee344a499dc090ddb2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:02:59.487428Z","signature_b64":"Jlgk0rrHCKKSC4xPhZ82xk278AwwpY71dWWaukqcEpbmZSSi23eiJ7qaqrYQ4F95R5k+UR+C6L+Y6AMC18QfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d4fbec380532a8862e5a73a6b3ef3fc917411fc1283ebee344a499dc090ddb2","last_reissued_at":"2026-05-18T03:02:59.486699Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:02:59.486699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1304.5586","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:02:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kjtzk0L7nULav/GVkQtDCbiY5dS+ITPHsg/N3ZJkBxgd21cznxsSCpV9KFwRXj/KVWnFipH/K5/PVbHDlXmcBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T17:16:20.831005Z"},"content_sha256":"67350664187fef2fc8c3078f180c47c11b2086d1b850002d337a13632ee91fb6","schema_version":"1.0","event_id":"sha256:67350664187fef2fc8c3078f180c47c11b2086d1b850002d337a13632ee91fb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:DVH35Q4AKMVIQYXFU45GWPXT7S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tail bounds for stochastic approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Gabriel Goh, Michael P. Friedlander","submitted_at":"2013-04-20T04:23:34Z","abstract_excerpt":"Stochastic-approximation gradient methods are attractive for large-scale convex optimization because they offer inexpensive iterations. They are especially popular in data-fitting and machine-learning applications where the data arrives in a continuous stream, or it is necessary to minimize large sums of functions. It is known that by appropriately decreasing the variance of the error at each iteration, the expected rate of convergence matches that of the underlying deterministic gradient method. Conditions are given under which this happens with overwhelming probability."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1304.5586","kind":"arxiv","version":2},"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":"2026-05-18T03:02:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6nL8LgfzC9X3iIsWWFi/HLF7dGp9NHSam7AnjLPg21TtimSNkVhmtCJ8MBU7Zgp5wCisq0YkDpWe3aQimrOdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T17:16:20.831679Z"},"content_sha256":"acfda7e9f8e17b6df1e8f1bd3d20c8cde494e6dc9934e0ebd858170c2c93a922","schema_version":"1.0","event_id":"sha256:acfda7e9f8e17b6df1e8f1bd3d20c8cde494e6dc9934e0ebd858170c2c93a922"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DVH35Q4AKMVIQYXFU45GWPXT7S/bundle.json","state_url":"https://pith.science/pith/DVH35Q4AKMVIQYXFU45GWPXT7S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DVH35Q4AKMVIQYXFU45GWPXT7S/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":"2026-06-06T17:16:20Z","links":{"resolver":"https://pith.science/pith/DVH35Q4AKMVIQYXFU45GWPXT7S","bundle":"https://pith.science/pith/DVH35Q4AKMVIQYXFU45GWPXT7S/bundle.json","state":"https://pith.science/pith/DVH35Q4AKMVIQYXFU45GWPXT7S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DVH35Q4AKMVIQYXFU45GWPXT7S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:DVH35Q4AKMVIQYXFU45GWPXT7S","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":"7cdfe4089a89cab574978aaa1ecc26b9a671407206131526cf664b748dbc2900","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2013-04-20T04:23:34Z","title_canon_sha256":"f612c66526f4003d3a1e9c647a2069927a566bc576f05094592017d234a43f57"},"schema_version":"1.0","source":{"id":"1304.5586","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1304.5586","created_at":"2026-05-18T03:02:59Z"},{"alias_kind":"arxiv_version","alias_value":"1304.5586v2","created_at":"2026-05-18T03:02:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1304.5586","created_at":"2026-05-18T03:02:59Z"},{"alias_kind":"pith_short_12","alias_value":"DVH35Q4AKMVI","created_at":"2026-05-18T12:27:43Z"},{"alias_kind":"pith_short_16","alias_value":"DVH35Q4AKMVIQYXF","created_at":"2026-05-18T12:27:43Z"},{"alias_kind":"pith_short_8","alias_value":"DVH35Q4A","created_at":"2026-05-18T12:27:43Z"}],"graph_snapshots":[{"event_id":"sha256:acfda7e9f8e17b6df1e8f1bd3d20c8cde494e6dc9934e0ebd858170c2c93a922","target":"graph","created_at":"2026-05-18T03:02:59Z","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":"Stochastic-approximation gradient methods are attractive for large-scale convex optimization because they offer inexpensive iterations. They are especially popular in data-fitting and machine-learning applications where the data arrives in a continuous stream, or it is necessary to minimize large sums of functions. It is known that by appropriately decreasing the variance of the error at each iteration, the expected rate of convergence matches that of the underlying deterministic gradient method. Conditions are given under which this happens with overwhelming probability.","authors_text":"Gabriel Goh, Michael P. Friedlander","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2013-04-20T04:23:34Z","title":"Tail bounds for stochastic approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1304.5586","kind":"arxiv","version":2},"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":"sha256:67350664187fef2fc8c3078f180c47c11b2086d1b850002d337a13632ee91fb6","target":"record","created_at":"2026-05-18T03:02:59Z","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":"7cdfe4089a89cab574978aaa1ecc26b9a671407206131526cf664b748dbc2900","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2013-04-20T04:23:34Z","title_canon_sha256":"f612c66526f4003d3a1e9c647a2069927a566bc576f05094592017d234a43f57"},"schema_version":"1.0","source":{"id":"1304.5586","kind":"arxiv","version":2}},"canonical_sha256":"1d4fbec380532a8862e5a73a6b3ef3fc917411fc1283ebee344a499dc090ddb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d4fbec380532a8862e5a73a6b3ef3fc917411fc1283ebee344a499dc090ddb2","first_computed_at":"2026-05-18T03:02:59.486699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:02:59.486699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jlgk0rrHCKKSC4xPhZ82xk278AwwpY71dWWaukqcEpbmZSSi23eiJ7qaqrYQ4F95R5k+UR+C6L+Y6AMC18QfCg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:02:59.487428Z","signed_message":"canonical_sha256_bytes"},"source_id":"1304.5586","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67350664187fef2fc8c3078f180c47c11b2086d1b850002d337a13632ee91fb6","sha256:acfda7e9f8e17b6df1e8f1bd3d20c8cde494e6dc9934e0ebd858170c2c93a922"],"state_sha256":"25dbfe4ce104070717c3cde558b8298eaf668f51ea77e844218f4f02641450b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vDhhXDVpFoeD6taK+DN/qsOKCtt6aIEwtdLCcMvJRN0KU5dXzZNIIjVX8QzE3UoKR1hB95brP3+q2z44ZYpZAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T17:16:20.835784Z","bundle_sha256":"c91f992a964ebf98f53e96f049707006aefa6c2f25eb98291e25e537d0370424"}}