{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:S4E5MCF73JJOJY6LFOQP3UZ7I7","short_pith_number":"pith:S4E5MCF7","canonical_record":{"source":{"id":"1706.08934","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-27T16:43:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"983be0944b7ac502fe2f5262170e8759583d68c47cf1c609175d9bb60385d82f","abstract_canon_sha256":"169c4207d1cb731c5a0f42d8ffb6da020e447e05509da71cb8b338ebf1fd2775"},"schema_version":"1.0"},"canonical_sha256":"9709d608bfda52e4e3cb2ba0fdd33f47c938c9f844373ad5da88ebbeae58e83e","source":{"kind":"arxiv","id":"1706.08934","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.08934","created_at":"2026-05-18T00:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"1706.08934v3","created_at":"2026-05-18T00:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.08934","created_at":"2026-05-18T00:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"S4E5MCF73JJO","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"S4E5MCF73JJOJY6L","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"S4E5MCF7","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:S4E5MCF73JJOJY6LFOQP3UZ7I7","target":"record","payload":{"canonical_record":{"source":{"id":"1706.08934","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-27T16:43:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"983be0944b7ac502fe2f5262170e8759583d68c47cf1c609175d9bb60385d82f","abstract_canon_sha256":"169c4207d1cb731c5a0f42d8ffb6da020e447e05509da71cb8b338ebf1fd2775"},"schema_version":"1.0"},"canonical_sha256":"9709d608bfda52e4e3cb2ba0fdd33f47c938c9f844373ad5da88ebbeae58e83e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:12.022496Z","signature_b64":"LVxqEDtYFGQVVfke2YE+5S/qD60oI202vlMfvSAydVJF/GzCI4MgILHa58u1S07hLiKwmfejplD/qw81DoLtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9709d608bfda52e4e3cb2ba0fdd33f47c938c9f844373ad5da88ebbeae58e83e","last_reissued_at":"2026-05-18T00:39:12.021791Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:12.021791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.08934","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6RmCGHChIo1Oi+AatQhlreAzSMS9Oh++2kIe7wNin4dwlYRFHAT4tF/yjsjzNNmHHp0dwWvGpDbUr5OuIpN4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:27:21.468573Z"},"content_sha256":"ef63d13563382f6e6f7823694a654c0991ea6108d7ae6206f44157745bf09e16","schema_version":"1.0","event_id":"sha256:ef63d13563382f6e6f7823694a654c0991ea6108d7ae6206f44157745bf09e16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:S4E5MCF73JJOJY6LFOQP3UZ7I7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reexamining Low Rank Matrix Factorization for Trace Norm Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carlo Ciliberto, Dimitris Stamos, Massimiliano Pontil","submitted_at":"2017-06-27T16:43:31Z","abstract_excerpt":"Trace norm regularization is a widely used approach for learning low rank matrices. A standard optimization strategy is based on formulating the problem as one of low rank matrix factorization which, however, leads to a non-convex problem. In practice this approach works well, and it is often computationally faster than standard convex solvers such as proximal gradient methods. Nevertheless, it is not guaranteed to converge to a global optimum, and the optimization can be trapped at poor stationary points. In this paper we show that it is possible to characterize all critical points of the non"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.08934","kind":"arxiv","version":3},"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":"2026-05-18T00:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"73hzds/xy1vB8c0Ts4JM9BesXz6wCGdem61FD31JuE0i/K9NccwAcIeFMRSBGgFoKOAqb3r574DBcU+DOg0sBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:27:21.469027Z"},"content_sha256":"ae809e2002b1cd957e3aea5f308ec830b755780629cde500bf3dd0944aa4cb28","schema_version":"1.0","event_id":"sha256:ae809e2002b1cd957e3aea5f308ec830b755780629cde500bf3dd0944aa4cb28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S4E5MCF73JJOJY6LFOQP3UZ7I7/bundle.json","state_url":"https://pith.science/pith/S4E5MCF73JJOJY6LFOQP3UZ7I7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S4E5MCF73JJOJY6LFOQP3UZ7I7/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":"2026-05-31T09:27:21Z","links":{"resolver":"https://pith.science/pith/S4E5MCF73JJOJY6LFOQP3UZ7I7","bundle":"https://pith.science/pith/S4E5MCF73JJOJY6LFOQP3UZ7I7/bundle.json","state":"https://pith.science/pith/S4E5MCF73JJOJY6LFOQP3UZ7I7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S4E5MCF73JJOJY6LFOQP3UZ7I7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:S4E5MCF73JJOJY6LFOQP3UZ7I7","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":"169c4207d1cb731c5a0f42d8ffb6da020e447e05509da71cb8b338ebf1fd2775","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-27T16:43:31Z","title_canon_sha256":"983be0944b7ac502fe2f5262170e8759583d68c47cf1c609175d9bb60385d82f"},"schema_version":"1.0","source":{"id":"1706.08934","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.08934","created_at":"2026-05-18T00:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"1706.08934v3","created_at":"2026-05-18T00:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.08934","created_at":"2026-05-18T00:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"S4E5MCF73JJO","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"S4E5MCF73JJOJY6L","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"S4E5MCF7","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:ae809e2002b1cd957e3aea5f308ec830b755780629cde500bf3dd0944aa4cb28","target":"graph","created_at":"2026-05-18T00:39:12Z","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":"Trace norm regularization is a widely used approach for learning low rank matrices. A standard optimization strategy is based on formulating the problem as one of low rank matrix factorization which, however, leads to a non-convex problem. In practice this approach works well, and it is often computationally faster than standard convex solvers such as proximal gradient methods. Nevertheless, it is not guaranteed to converge to a global optimum, and the optimization can be trapped at poor stationary points. In this paper we show that it is possible to characterize all critical points of the non","authors_text":"Carlo Ciliberto, Dimitris Stamos, Massimiliano Pontil","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-27T16:43:31Z","title":"Reexamining Low Rank Matrix Factorization for Trace Norm Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.08934","kind":"arxiv","version":3},"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:ef63d13563382f6e6f7823694a654c0991ea6108d7ae6206f44157745bf09e16","target":"record","created_at":"2026-05-18T00:39:12Z","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":"169c4207d1cb731c5a0f42d8ffb6da020e447e05509da71cb8b338ebf1fd2775","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-27T16:43:31Z","title_canon_sha256":"983be0944b7ac502fe2f5262170e8759583d68c47cf1c609175d9bb60385d82f"},"schema_version":"1.0","source":{"id":"1706.08934","kind":"arxiv","version":3}},"canonical_sha256":"9709d608bfda52e4e3cb2ba0fdd33f47c938c9f844373ad5da88ebbeae58e83e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9709d608bfda52e4e3cb2ba0fdd33f47c938c9f844373ad5da88ebbeae58e83e","first_computed_at":"2026-05-18T00:39:12.021791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:12.021791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LVxqEDtYFGQVVfke2YE+5S/qD60oI202vlMfvSAydVJF/GzCI4MgILHa58u1S07hLiKwmfejplD/qw81DoLtDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:12.022496Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.08934","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef63d13563382f6e6f7823694a654c0991ea6108d7ae6206f44157745bf09e16","sha256:ae809e2002b1cd957e3aea5f308ec830b755780629cde500bf3dd0944aa4cb28"],"state_sha256":"8f968f423f6466bc4ce89958e70ad78518d783afdaafc89e126133e4cabb98e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FZekaQNpfNc4Oe6cHf3DQ2yyGX5631dmpy/W9nGVgYYthtDDohRBO2+MFLu0/iis1EpdUJ2VOf7paQc1dnjCCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T09:27:21.472489Z","bundle_sha256":"f90899ac63699df649fc89443fe372da47ba3bc89c555a58030c4b9381aed9c4"}}