{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JJLBU6HCZOEDTSL2NUGWHPTP3M","short_pith_number":"pith:JJLBU6HC","canonical_record":{"source":{"id":"2202.03535","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T21:53:51Z","cross_cats_sorted":[],"title_canon_sha256":"03032c3426bf37485e8c58926d4f6aa5f4ad2a6713d20107b7e2312bcae3ed0f","abstract_canon_sha256":"de178c93da40854a96147dbd16782bf8f84bc48068b38cf12fb713d2a302561c"},"schema_version":"1.0"},"canonical_sha256":"4a561a78e2cb8839c97a6d0d63be6fdb0889c41a0fea1c221f9384f3885e100d","source":{"kind":"arxiv","id":"2202.03535","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03535","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03535v1","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03535","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"JJLBU6HCZOED","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"JJLBU6HCZOEDTSL2","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"JJLBU6HC","created_at":"2026-07-05T03:54:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JJLBU6HCZOEDTSL2NUGWHPTP3M","target":"record","payload":{"canonical_record":{"source":{"id":"2202.03535","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T21:53:51Z","cross_cats_sorted":[],"title_canon_sha256":"03032c3426bf37485e8c58926d4f6aa5f4ad2a6713d20107b7e2312bcae3ed0f","abstract_canon_sha256":"de178c93da40854a96147dbd16782bf8f84bc48068b38cf12fb713d2a302561c"},"schema_version":"1.0"},"canonical_sha256":"4a561a78e2cb8839c97a6d0d63be6fdb0889c41a0fea1c221f9384f3885e100d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:45.298876Z","signature_b64":"NrWxvCXgWC153qVl/DDTXzqx035lx7EWaYwc/VRFlCZ9czU5FgeZqiElbr2IxTnKJ4z9PJa0uAOuHt8JnHUJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a561a78e2cb8839c97a6d0d63be6fdb0889c41a0fea1c221f9384f3885e100d","last_reissued_at":"2026-07-05T03:54:45.298480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:45.298480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.03535","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":"2026-07-05T03:54:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HIecojKQmIx0ZXyOb/69jjpnfSw3qzw7c4OfsP8F7L2RSFY99EYkZtckSEGGU7n52ZRvsilTeFc9rzh+VBz9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:35:47.087548Z"},"content_sha256":"b61065848c33329902916f364afcf58301510bad30ee595866e3e26dfaeb4712","schema_version":"1.0","event_id":"sha256:b61065848c33329902916f364afcf58301510bad30ee595866e3e26dfaeb4712"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JJLBU6HCZOEDTSL2NUGWHPTP3M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Enlu Zhou, Tianyi Liu, Tuo Zhao, Yan Li","submitted_at":"2022-02-07T21:53:51Z","abstract_excerpt":"We investigate the role of noise in optimization algorithms for learning over-parameterized models. Specifically, we consider the recovery of a rank one matrix $Y^*\\in R^{d\\times d}$ from a noisy observation $Y$ using an over-parameterization model. We parameterize the rank one matrix $Y^*$ by $XX^\\top$, where $X\\in R^{d\\times d}$. We then show that under mild conditions, the estimator, obtained by the randomly perturbed gradient descent algorithm using the square loss function, attains a mean square error of $O(\\sigma^2/d)$, where $\\sigma^2$ is the variance of the observational noise. In cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03535","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.03535/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T03:54:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b7YY0ajarutIlMwXFWeqWcsEKNVrVxB6L9rOo2fwPSPuSOL9qF4odfGflhbk8/tTC5X/u1MD4YugMZRf5zQnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:35:47.087918Z"},"content_sha256":"92072b3fac5bc04594c190193e4816458952ccb1e466a4c7afd71c433ed14478","schema_version":"1.0","event_id":"sha256:92072b3fac5bc04594c190193e4816458952ccb1e466a4c7afd71c433ed14478"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JJLBU6HCZOEDTSL2NUGWHPTP3M/bundle.json","state_url":"https://pith.science/pith/JJLBU6HCZOEDTSL2NUGWHPTP3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JJLBU6HCZOEDTSL2NUGWHPTP3M/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":"2026-07-09T03:35:47Z","links":{"resolver":"https://pith.science/pith/JJLBU6HCZOEDTSL2NUGWHPTP3M","bundle":"https://pith.science/pith/JJLBU6HCZOEDTSL2NUGWHPTP3M/bundle.json","state":"https://pith.science/pith/JJLBU6HCZOEDTSL2NUGWHPTP3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JJLBU6HCZOEDTSL2NUGWHPTP3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JJLBU6HCZOEDTSL2NUGWHPTP3M","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":"de178c93da40854a96147dbd16782bf8f84bc48068b38cf12fb713d2a302561c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T21:53:51Z","title_canon_sha256":"03032c3426bf37485e8c58926d4f6aa5f4ad2a6713d20107b7e2312bcae3ed0f"},"schema_version":"1.0","source":{"id":"2202.03535","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03535","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03535v1","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03535","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"JJLBU6HCZOED","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"JJLBU6HCZOEDTSL2","created_at":"2026-07-05T03:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"JJLBU6HC","created_at":"2026-07-05T03:54:45Z"}],"graph_snapshots":[{"event_id":"sha256:92072b3fac5bc04594c190193e4816458952ccb1e466a4c7afd71c433ed14478","target":"graph","created_at":"2026-07-05T03:54:45Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2202.03535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the role of noise in optimization algorithms for learning over-parameterized models. Specifically, we consider the recovery of a rank one matrix $Y^*\\in R^{d\\times d}$ from a noisy observation $Y$ using an over-parameterization model. We parameterize the rank one matrix $Y^*$ by $XX^\\top$, where $X\\in R^{d\\times d}$. We then show that under mild conditions, the estimator, obtained by the randomly perturbed gradient descent algorithm using the square loss function, attains a mean square error of $O(\\sigma^2/d)$, where $\\sigma^2$ is the variance of the observational noise. In cont","authors_text":"Enlu Zhou, Tianyi Liu, Tuo Zhao, Yan Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T21:53:51Z","title":"Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03535","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:b61065848c33329902916f364afcf58301510bad30ee595866e3e26dfaeb4712","target":"record","created_at":"2026-07-05T03:54:45Z","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":"de178c93da40854a96147dbd16782bf8f84bc48068b38cf12fb713d2a302561c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-07T21:53:51Z","title_canon_sha256":"03032c3426bf37485e8c58926d4f6aa5f4ad2a6713d20107b7e2312bcae3ed0f"},"schema_version":"1.0","source":{"id":"2202.03535","kind":"arxiv","version":1}},"canonical_sha256":"4a561a78e2cb8839c97a6d0d63be6fdb0889c41a0fea1c221f9384f3885e100d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a561a78e2cb8839c97a6d0d63be6fdb0889c41a0fea1c221f9384f3885e100d","first_computed_at":"2026-07-05T03:54:45.298480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:54:45.298480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NrWxvCXgWC153qVl/DDTXzqx035lx7EWaYwc/VRFlCZ9czU5FgeZqiElbr2IxTnKJ4z9PJa0uAOuHt8JnHUJDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:54:45.298876Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.03535","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b61065848c33329902916f364afcf58301510bad30ee595866e3e26dfaeb4712","sha256:92072b3fac5bc04594c190193e4816458952ccb1e466a4c7afd71c433ed14478"],"state_sha256":"34679ed6a0fb427faedbffddb1832886f31ac737e4f9c34b360877c3bc05a166"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rHFmnSBVthbZpbXMhJEOU+rO7reiskm6w1eRtfAwydHdoQg9CjQXUU3X3tAPPXisiR/MEsdXHlfpth43YhsLCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:35:47.089835Z","bundle_sha256":"a61da40c298461295db6088f646fecea9822a033dec782937136b77f61c3a73d"}}