{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:YCVMA4DX4ZFYJLB5UYG6MNDIFQ","short_pith_number":"pith:YCVMA4DX","canonical_record":{"source":{"id":"1710.05092","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-13T22:47:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7fd636d16e643397fc47f60fd393d27aebdce4dca0b33506bd61589524080040","abstract_canon_sha256":"2800b8a538006d5bae184f56d3adcfa7831acb235b9be5a594fb9c2590bb83e4"},"schema_version":"1.0"},"canonical_sha256":"c0aac07077e64b84ac3da60de634682c36afd4089ae4b859ffc4ec37b626a54a","source":{"kind":"arxiv","id":"1710.05092","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.05092","created_at":"2026-05-18T00:32:54Z"},{"alias_kind":"arxiv_version","alias_value":"1710.05092v1","created_at":"2026-05-18T00:32:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.05092","created_at":"2026-05-18T00:32:54Z"},{"alias_kind":"pith_short_12","alias_value":"YCVMA4DX4ZFY","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YCVMA4DX4ZFYJLB5","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YCVMA4DX","created_at":"2026-05-18T12:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:YCVMA4DX4ZFYJLB5UYG6MNDIFQ","target":"record","payload":{"canonical_record":{"source":{"id":"1710.05092","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-13T22:47:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7fd636d16e643397fc47f60fd393d27aebdce4dca0b33506bd61589524080040","abstract_canon_sha256":"2800b8a538006d5bae184f56d3adcfa7831acb235b9be5a594fb9c2590bb83e4"},"schema_version":"1.0"},"canonical_sha256":"c0aac07077e64b84ac3da60de634682c36afd4089ae4b859ffc4ec37b626a54a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:54.431936Z","signature_b64":"q95qnbj0v6DGZ4TSUQ6W5wLRFmJwrf6VeRAEqagZiN1l7AzZKkaqqI3/yttSvFRC7MW0DPWqL2EpkQzExXNuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0aac07077e64b84ac3da60de634682c36afd4089ae4b859ffc4ec37b626a54a","last_reissued_at":"2026-05-18T00:32:54.431454Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:54.431454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.05092","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":"2026-05-18T00:32:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HbXS2/hgyKK/BUnewji+DYrNlNA0RC354P/0DtEU4D/sXdXB7rocWU+08L63zK+zMvSn814XbcKyORCbJ2/PBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T17:29:28.990673Z"},"content_sha256":"0ff33388e1d13034d5e2d5eadeceb2897c9e625a2c6e545041a199dfad9549be","schema_version":"1.0","event_id":"sha256:0ff33388e1d13034d5e2d5eadeceb2897c9e625a2c6e545041a199dfad9549be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:YCVMA4DX4ZFYJLB5UYG6MNDIFQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dropout as a Low-Rank Regularizer for Matrix Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Haeffele, Connor Lane, Jacopo Cavazza, Pietro Morerio, Rene Vidal, Vittorio Murino","submitted_at":"2017-10-13T22:47:19Z","abstract_excerpt":"Regularization for matrix factorization (MF) and approximation problems has been carried out in many different ways. Due to its popularity in deep learning, dropout has been applied also for this class of problems. Despite its solid empirical performance, the theoretical properties of dropout as a regularizer remain quite elusive for this class of problems. In this paper, we present a theoretical analysis of dropout for MF, where Bernoulli random variables are used to drop columns of the factors. We demonstrate the equivalence between dropout and a fully deterministic model for MF in which the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.05092","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":"2026-05-18T00:32:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uE4dOTwEc5I3FlLczso6YwKUATRv93p2mfV6WNxosO5bRYWiTM29qk+1I4PZ31l30tLlRg9qggYqqdbAOYjmBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T17:29:28.991009Z"},"content_sha256":"c5e691cb979a3c75500000907838e6b0cbe64045858b60da5fdbf5915d97c023","schema_version":"1.0","event_id":"sha256:c5e691cb979a3c75500000907838e6b0cbe64045858b60da5fdbf5915d97c023"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YCVMA4DX4ZFYJLB5UYG6MNDIFQ/bundle.json","state_url":"https://pith.science/pith/YCVMA4DX4ZFYJLB5UYG6MNDIFQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YCVMA4DX4ZFYJLB5UYG6MNDIFQ/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":"2026-07-04T17:29:28Z","links":{"resolver":"https://pith.science/pith/YCVMA4DX4ZFYJLB5UYG6MNDIFQ","bundle":"https://pith.science/pith/YCVMA4DX4ZFYJLB5UYG6MNDIFQ/bundle.json","state":"https://pith.science/pith/YCVMA4DX4ZFYJLB5UYG6MNDIFQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YCVMA4DX4ZFYJLB5UYG6MNDIFQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:YCVMA4DX4ZFYJLB5UYG6MNDIFQ","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":"2800b8a538006d5bae184f56d3adcfa7831acb235b9be5a594fb9c2590bb83e4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-13T22:47:19Z","title_canon_sha256":"7fd636d16e643397fc47f60fd393d27aebdce4dca0b33506bd61589524080040"},"schema_version":"1.0","source":{"id":"1710.05092","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.05092","created_at":"2026-05-18T00:32:54Z"},{"alias_kind":"arxiv_version","alias_value":"1710.05092v1","created_at":"2026-05-18T00:32:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.05092","created_at":"2026-05-18T00:32:54Z"},{"alias_kind":"pith_short_12","alias_value":"YCVMA4DX4ZFY","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YCVMA4DX4ZFYJLB5","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YCVMA4DX","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:c5e691cb979a3c75500000907838e6b0cbe64045858b60da5fdbf5915d97c023","target":"graph","created_at":"2026-05-18T00:32:54Z","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":"Regularization for matrix factorization (MF) and approximation problems has been carried out in many different ways. Due to its popularity in deep learning, dropout has been applied also for this class of problems. Despite its solid empirical performance, the theoretical properties of dropout as a regularizer remain quite elusive for this class of problems. In this paper, we present a theoretical analysis of dropout for MF, where Bernoulli random variables are used to drop columns of the factors. We demonstrate the equivalence between dropout and a fully deterministic model for MF in which the","authors_text":"Benjamin Haeffele, Connor Lane, Jacopo Cavazza, Pietro Morerio, Rene Vidal, Vittorio Murino","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-13T22:47:19Z","title":"Dropout as a Low-Rank Regularizer for Matrix Factorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.05092","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":"sha256:0ff33388e1d13034d5e2d5eadeceb2897c9e625a2c6e545041a199dfad9549be","target":"record","created_at":"2026-05-18T00:32:54Z","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":"2800b8a538006d5bae184f56d3adcfa7831acb235b9be5a594fb9c2590bb83e4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-13T22:47:19Z","title_canon_sha256":"7fd636d16e643397fc47f60fd393d27aebdce4dca0b33506bd61589524080040"},"schema_version":"1.0","source":{"id":"1710.05092","kind":"arxiv","version":1}},"canonical_sha256":"c0aac07077e64b84ac3da60de634682c36afd4089ae4b859ffc4ec37b626a54a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0aac07077e64b84ac3da60de634682c36afd4089ae4b859ffc4ec37b626a54a","first_computed_at":"2026-05-18T00:32:54.431454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:54.431454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q95qnbj0v6DGZ4TSUQ6W5wLRFmJwrf6VeRAEqagZiN1l7AzZKkaqqI3/yttSvFRC7MW0DPWqL2EpkQzExXNuAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:54.431936Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.05092","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ff33388e1d13034d5e2d5eadeceb2897c9e625a2c6e545041a199dfad9549be","sha256:c5e691cb979a3c75500000907838e6b0cbe64045858b60da5fdbf5915d97c023"],"state_sha256":"2c732ac516e4d6aa0d537c9fc7d5d49997c08ca9930b05bb13b8641b6ed2617f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PZgZ8lkaaMiPI/ZDbVV88zwr7OSrgSnaw7ddrdAsKfO3aNxNuid+EOlBfAXjtOe9ZMu/I3wZfcVQhKws3YdOCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T17:29:28.992879Z","bundle_sha256":"b979a3e187c0ec417959bd0bd59dec2833fe32d7295211b6cd00b7e2c7e2027e"}}