{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:B37KFEXO2QUYGIIPPD2OL2N4QB","short_pith_number":"pith:B37KFEXO","canonical_record":{"source":{"id":"1803.10846","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-28T20:46:27Z","cross_cats_sorted":["cs.DS","math.OC","stat.ML"],"title_canon_sha256":"a4cebbf4da928515adf7c1ae3b81a58da7aeaebbbc0fd0a24643c208284bb107","abstract_canon_sha256":"42d2f1e15adf0137c1a7acedd4d7b354488f3bd0f7f5c42ef3f7d89471383b91"},"schema_version":"1.0"},"canonical_sha256":"0efea292eed42983210f78f4e5e9bc80601f49a5efdf2bd0cd4b8ea3842aefef","source":{"kind":"arxiv","id":"1803.10846","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.10846","created_at":"2026-05-18T00:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"1803.10846v2","created_at":"2026-05-18T00:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10846","created_at":"2026-05-18T00:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"B37KFEXO2QUY","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"B37KFEXO2QUYGIIP","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"B37KFEXO","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:B37KFEXO2QUYGIIPPD2OL2N4QB","target":"record","payload":{"canonical_record":{"source":{"id":"1803.10846","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-28T20:46:27Z","cross_cats_sorted":["cs.DS","math.OC","stat.ML"],"title_canon_sha256":"a4cebbf4da928515adf7c1ae3b81a58da7aeaebbbc0fd0a24643c208284bb107","abstract_canon_sha256":"42d2f1e15adf0137c1a7acedd4d7b354488f3bd0f7f5c42ef3f7d89471383b91"},"schema_version":"1.0"},"canonical_sha256":"0efea292eed42983210f78f4e5e9bc80601f49a5efdf2bd0cd4b8ea3842aefef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:16.095805Z","signature_b64":"Ng+BvSlWv2pDuxW5JtiNShGCp0s5FVvdxbXUPX6NDKlf6+QG2sqyP6mHokOhVH6EKNncF1dreWXobvYJuf2vDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0efea292eed42983210f78f4e5e9bc80601f49a5efdf2bd0cd4b8ea3842aefef","last_reissued_at":"2026-05-18T00:06:16.095204Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:16.095204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.10846","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":"2026-05-18T00:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cdXAN4l14GZRmzFM3tANDtwAQ/GLSAUgyk4sRPngfs5TdO61kl+XEFPFwGiaS+rJfAu4qE/3T+R3zWQNSbDuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:05:30.198626Z"},"content_sha256":"ea58961cc47417ce54dd1753cc0df2bc3a426a9d57ee8497790e2c87d10e3530","schema_version":"1.0","event_id":"sha256:ea58961cc47417ce54dd1753cc0df2bc3a426a9d57ee8497790e2c87d10e3530"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:B37KFEXO2QUYGIIPPD2OL2N4QB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Non-Convex Matrix Completion Against a Semi-Random Adversary","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rong Ge, Yu Cheng","submitted_at":"2018-03-28T20:46:27Z","abstract_excerpt":"Matrix completion is a well-studied problem with many machine learning applications. In practice, the problem is often solved by non-convex optimization algorithms. However, the current theoretical analysis for non-convex algorithms relies heavily on the assumption that every entry is observed with exactly the same probability $p$, which is not realistic in practice.\n  In this paper, we investigate a more realistic semi-random model, where the probability of observing each entry is at least $p$. Even with this mild semi-random perturbation, we can construct counter-examples where existing non-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10846","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":"2026-05-18T00:06:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xFogwqxCFS+FOy3oILSr5ikUmU/f9y6CBrZgPBtA2JFcm+X5S7nXbvDjXADqyJ+rkMYxAWJ0T1HTHeMyFLtYAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:05:30.198986Z"},"content_sha256":"6cbde7e2c96eaaf455566a02087435c1109e4cde879ce91266b3fb92c931cb37","schema_version":"1.0","event_id":"sha256:6cbde7e2c96eaaf455566a02087435c1109e4cde879ce91266b3fb92c931cb37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B37KFEXO2QUYGIIPPD2OL2N4QB/bundle.json","state_url":"https://pith.science/pith/B37KFEXO2QUYGIIPPD2OL2N4QB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B37KFEXO2QUYGIIPPD2OL2N4QB/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":"2026-05-28T14:05:30Z","links":{"resolver":"https://pith.science/pith/B37KFEXO2QUYGIIPPD2OL2N4QB","bundle":"https://pith.science/pith/B37KFEXO2QUYGIIPPD2OL2N4QB/bundle.json","state":"https://pith.science/pith/B37KFEXO2QUYGIIPPD2OL2N4QB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B37KFEXO2QUYGIIPPD2OL2N4QB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:B37KFEXO2QUYGIIPPD2OL2N4QB","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":"42d2f1e15adf0137c1a7acedd4d7b354488f3bd0f7f5c42ef3f7d89471383b91","cross_cats_sorted":["cs.DS","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-28T20:46:27Z","title_canon_sha256":"a4cebbf4da928515adf7c1ae3b81a58da7aeaebbbc0fd0a24643c208284bb107"},"schema_version":"1.0","source":{"id":"1803.10846","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.10846","created_at":"2026-05-18T00:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"1803.10846v2","created_at":"2026-05-18T00:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10846","created_at":"2026-05-18T00:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"B37KFEXO2QUY","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"B37KFEXO2QUYGIIP","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"B37KFEXO","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:6cbde7e2c96eaaf455566a02087435c1109e4cde879ce91266b3fb92c931cb37","target":"graph","created_at":"2026-05-18T00:06:16Z","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":"Matrix completion is a well-studied problem with many machine learning applications. In practice, the problem is often solved by non-convex optimization algorithms. However, the current theoretical analysis for non-convex algorithms relies heavily on the assumption that every entry is observed with exactly the same probability $p$, which is not realistic in practice.\n  In this paper, we investigate a more realistic semi-random model, where the probability of observing each entry is at least $p$. Even with this mild semi-random perturbation, we can construct counter-examples where existing non-","authors_text":"Rong Ge, Yu Cheng","cross_cats":["cs.DS","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-28T20:46:27Z","title":"Non-Convex Matrix Completion Against a Semi-Random Adversary"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10846","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:ea58961cc47417ce54dd1753cc0df2bc3a426a9d57ee8497790e2c87d10e3530","target":"record","created_at":"2026-05-18T00:06:16Z","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":"42d2f1e15adf0137c1a7acedd4d7b354488f3bd0f7f5c42ef3f7d89471383b91","cross_cats_sorted":["cs.DS","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-28T20:46:27Z","title_canon_sha256":"a4cebbf4da928515adf7c1ae3b81a58da7aeaebbbc0fd0a24643c208284bb107"},"schema_version":"1.0","source":{"id":"1803.10846","kind":"arxiv","version":2}},"canonical_sha256":"0efea292eed42983210f78f4e5e9bc80601f49a5efdf2bd0cd4b8ea3842aefef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0efea292eed42983210f78f4e5e9bc80601f49a5efdf2bd0cd4b8ea3842aefef","first_computed_at":"2026-05-18T00:06:16.095204Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:16.095204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ng+BvSlWv2pDuxW5JtiNShGCp0s5FVvdxbXUPX6NDKlf6+QG2sqyP6mHokOhVH6EKNncF1dreWXobvYJuf2vDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:16.095805Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.10846","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea58961cc47417ce54dd1753cc0df2bc3a426a9d57ee8497790e2c87d10e3530","sha256:6cbde7e2c96eaaf455566a02087435c1109e4cde879ce91266b3fb92c931cb37"],"state_sha256":"2f1aa34dbe2beada872b581240f33433fffe83ef9e174f45ceaf67a5b280653b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wL1xmy16gYdCUw2D3Rku2Pke2QehtOELdB+soG8ZFvlM6352jOBlUq1A8hlEPD59kbyTOfBVmAbWhenn7h4QBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T14:05:30.201089Z","bundle_sha256":"a1e1bcb4389a07f123f5156d4fd29564b6ec450836d58932fe6d0088362cdd7f"}}