{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:VV5B3VNRPREUNWB4FJSB5BE3LH","short_pith_number":"pith:VV5B3VNR","canonical_record":{"source":{"id":"1508.07649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2015-08-30T23:53:48Z","cross_cats_sorted":[],"title_canon_sha256":"ec14c6edfafc5a28f5b9b44a857cc74a61be49d768dd062fd633c7396b77a55f","abstract_canon_sha256":"dbb4ffb93359ecc9710255e7eff99d86059d3fdb4e48b5517e747212d9649d63"},"schema_version":"1.0"},"canonical_sha256":"ad7a1dd5b17c4946d83c2a641e849b59c21bf9e93609c4dc726b4b60f8582b3f","source":{"kind":"arxiv","id":"1508.07649","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.07649","created_at":"2026-05-18T01:34:31Z"},{"alias_kind":"arxiv_version","alias_value":"1508.07649v1","created_at":"2026-05-18T01:34:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.07649","created_at":"2026-05-18T01:34:31Z"},{"alias_kind":"pith_short_12","alias_value":"VV5B3VNRPREU","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"VV5B3VNRPREUNWB4","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"VV5B3VNR","created_at":"2026-05-18T12:29:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:VV5B3VNRPREUNWB4FJSB5BE3LH","target":"record","payload":{"canonical_record":{"source":{"id":"1508.07649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2015-08-30T23:53:48Z","cross_cats_sorted":[],"title_canon_sha256":"ec14c6edfafc5a28f5b9b44a857cc74a61be49d768dd062fd633c7396b77a55f","abstract_canon_sha256":"dbb4ffb93359ecc9710255e7eff99d86059d3fdb4e48b5517e747212d9649d63"},"schema_version":"1.0"},"canonical_sha256":"ad7a1dd5b17c4946d83c2a641e849b59c21bf9e93609c4dc726b4b60f8582b3f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:34:31.767395Z","signature_b64":"62Hltuw2b7hPcVpwIddyyXfb3PFJEaNggkEjouu1veH0AjDGpb2HOcMbjlM1T+pBx6WoznxbOuombonV8UFIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad7a1dd5b17c4946d83c2a641e849b59c21bf9e93609c4dc726b4b60f8582b3f","last_reissued_at":"2026-05-18T01:34:31.766843Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:34:31.766843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1508.07649","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":"2026-05-18T01:34:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6cadipsNs3PBsp/ol+z3R49GDJsaT0Jj8fAszSDS0MfaZijriAqQK4cYjC0uwrzIWphqyWDhtjVxpVH0FP6QDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:36:44.631883Z"},"content_sha256":"523bbd266ebb112491d975a0eed974694ff83f89ea02ed31a5ebeb280dedcf14","schema_version":"1.0","event_id":"sha256:523bbd266ebb112491d975a0eed974694ff83f89ea02ed31a5ebeb280dedcf14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:VV5B3VNRPREUNWB4FJSB5BE3LH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Constrained and Preconditioned Stochastic Gradient Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.NA","authors_text":"Gang Huang, Hong Jiang, Liangkai Yu, Paul Wilford","submitted_at":"2015-08-30T23:53:48Z","abstract_excerpt":"We consider stochastic approximations which arise from such applications as data communications and image processing. We demonstrate why constraints are needed in a stochastic approximation and how a constrained approximation can be incorporated into a preconditioning technique to derive the pre-conditioned stochastic gradient method (PSGM). We perform convergence analysis to show that the PSGM converges to the theoretical best approximation under some simple assumptions on the preconditioner and on the independence of samples drawn from a stochastic process. Simulation results are presented t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.07649","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":"2026-05-18T01:34:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JY8ibp+nDFQquZj7u+mvLBch7LmH0OfipzlDXpPsK6iHbIRVAe1YK/PycgVbcTcG0EbKk0E/z06C3bhbJIqLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T21:36:44.632495Z"},"content_sha256":"e2aefe5831c28e6d5297c04fa03ca7a60f0890c03d35f23a1252b8b67a0101c0","schema_version":"1.0","event_id":"sha256:e2aefe5831c28e6d5297c04fa03ca7a60f0890c03d35f23a1252b8b67a0101c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VV5B3VNRPREUNWB4FJSB5BE3LH/bundle.json","state_url":"https://pith.science/pith/VV5B3VNRPREUNWB4FJSB5BE3LH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VV5B3VNRPREUNWB4FJSB5BE3LH/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":"2026-06-07T21:36:44Z","links":{"resolver":"https://pith.science/pith/VV5B3VNRPREUNWB4FJSB5BE3LH","bundle":"https://pith.science/pith/VV5B3VNRPREUNWB4FJSB5BE3LH/bundle.json","state":"https://pith.science/pith/VV5B3VNRPREUNWB4FJSB5BE3LH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VV5B3VNRPREUNWB4FJSB5BE3LH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:VV5B3VNRPREUNWB4FJSB5BE3LH","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":"dbb4ffb93359ecc9710255e7eff99d86059d3fdb4e48b5517e747212d9649d63","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2015-08-30T23:53:48Z","title_canon_sha256":"ec14c6edfafc5a28f5b9b44a857cc74a61be49d768dd062fd633c7396b77a55f"},"schema_version":"1.0","source":{"id":"1508.07649","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.07649","created_at":"2026-05-18T01:34:31Z"},{"alias_kind":"arxiv_version","alias_value":"1508.07649v1","created_at":"2026-05-18T01:34:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.07649","created_at":"2026-05-18T01:34:31Z"},{"alias_kind":"pith_short_12","alias_value":"VV5B3VNRPREU","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_16","alias_value":"VV5B3VNRPREUNWB4","created_at":"2026-05-18T12:29:47Z"},{"alias_kind":"pith_short_8","alias_value":"VV5B3VNR","created_at":"2026-05-18T12:29:47Z"}],"graph_snapshots":[{"event_id":"sha256:e2aefe5831c28e6d5297c04fa03ca7a60f0890c03d35f23a1252b8b67a0101c0","target":"graph","created_at":"2026-05-18T01:34:31Z","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":"We consider stochastic approximations which arise from such applications as data communications and image processing. We demonstrate why constraints are needed in a stochastic approximation and how a constrained approximation can be incorporated into a preconditioning technique to derive the pre-conditioned stochastic gradient method (PSGM). We perform convergence analysis to show that the PSGM converges to the theoretical best approximation under some simple assumptions on the preconditioner and on the independence of samples drawn from a stochastic process. Simulation results are presented t","authors_text":"Gang Huang, Hong Jiang, Liangkai Yu, Paul Wilford","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2015-08-30T23:53:48Z","title":"Constrained and Preconditioned Stochastic Gradient Method"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.07649","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":"sha256:523bbd266ebb112491d975a0eed974694ff83f89ea02ed31a5ebeb280dedcf14","target":"record","created_at":"2026-05-18T01:34:31Z","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":"dbb4ffb93359ecc9710255e7eff99d86059d3fdb4e48b5517e747212d9649d63","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.NA","submitted_at":"2015-08-30T23:53:48Z","title_canon_sha256":"ec14c6edfafc5a28f5b9b44a857cc74a61be49d768dd062fd633c7396b77a55f"},"schema_version":"1.0","source":{"id":"1508.07649","kind":"arxiv","version":1}},"canonical_sha256":"ad7a1dd5b17c4946d83c2a641e849b59c21bf9e93609c4dc726b4b60f8582b3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad7a1dd5b17c4946d83c2a641e849b59c21bf9e93609c4dc726b4b60f8582b3f","first_computed_at":"2026-05-18T01:34:31.766843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:34:31.766843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"62Hltuw2b7hPcVpwIddyyXfb3PFJEaNggkEjouu1veH0AjDGpb2HOcMbjlM1T+pBx6WoznxbOuombonV8UFIDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:34:31.767395Z","signed_message":"canonical_sha256_bytes"},"source_id":"1508.07649","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:523bbd266ebb112491d975a0eed974694ff83f89ea02ed31a5ebeb280dedcf14","sha256:e2aefe5831c28e6d5297c04fa03ca7a60f0890c03d35f23a1252b8b67a0101c0"],"state_sha256":"560da70d183bace9c38d187250e0b2b6504b0f1089283a5e3274cf7ab6e94052"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iLr70ShCDtGtsIfix9gjJCyp+QwjMd0VUCsA+g2auRbF6vrwRJetxcMb3kr/bw0PVCNgBwGDFQ71GWyI0v4RAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T21:36:44.637109Z","bundle_sha256":"5d7b66f3bc4ec0beb30c3fcb2d12d1220c352bf09f22074bf71804cedcad2170"}}