{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EW3LGFK467IT6QEFKCJMY46QFE","short_pith_number":"pith:EW3LGFK4","canonical_record":{"source":{"id":"1812.01478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:15:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ef76c7fb42ba3081f0c64f65df7056ecd4946b1132cfc740db9e6ed6a4b2f5ae","abstract_canon_sha256":"5ccbe9d25b6f3da57be35a4d31d684db983540c55fb2109f74f2892ebeb0e7af"},"schema_version":"1.0"},"canonical_sha256":"25b6b3155cf7d13f40855092cc73d0291ff61f050f8decf064276212f430fff4","source":{"kind":"arxiv","id":"1812.01478","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.01478","created_at":"2026-05-17T23:59:12Z"},{"alias_kind":"arxiv_version","alias_value":"1812.01478v1","created_at":"2026-05-17T23:59:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01478","created_at":"2026-05-17T23:59:12Z"},{"alias_kind":"pith_short_12","alias_value":"EW3LGFK467IT","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EW3LGFK467IT6QEF","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EW3LGFK4","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EW3LGFK467IT6QEFKCJMY46QFE","target":"record","payload":{"canonical_record":{"source":{"id":"1812.01478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:15:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ef76c7fb42ba3081f0c64f65df7056ecd4946b1132cfc740db9e6ed6a4b2f5ae","abstract_canon_sha256":"5ccbe9d25b6f3da57be35a4d31d684db983540c55fb2109f74f2892ebeb0e7af"},"schema_version":"1.0"},"canonical_sha256":"25b6b3155cf7d13f40855092cc73d0291ff61f050f8decf064276212f430fff4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:12.356771Z","signature_b64":"wgTN6aOgGR1rhZQWTq+TBf4dgVcURdyjPX6MN+v969B/gfGVZg08ZNOcTZKLTQm636POT4DS8A6ug7u4b788AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25b6b3155cf7d13f40855092cc73d0291ff61f050f8decf064276212f430fff4","last_reissued_at":"2026-05-17T23:59:12.356173Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:12.356173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.01478","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":"2026-05-17T23:59:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YCqmZmqUzPG8FlcSANlINQoCUvgVWPk/Y+kersh+6SGAd8Y7wAZ6cvQVeGNgGEwnzub0wGaomaXqkaNvqxjVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:54:19.073310Z"},"content_sha256":"3703dd0efaf34c70b6713138db1f58078d7873ac40459dcc6d74ac064f6309a1","schema_version":"1.0","event_id":"sha256:3703dd0efaf34c70b6713138db1f58078d7873ac40459dcc6d74ac064f6309a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EW3LGFK467IT6QEFKCJMY46QFE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Matrix Factorization via Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Duc Minh Nguyen, Evaggelia Tsiligianni, Nikos Deligiannis","submitted_at":"2018-12-04T15:15:23Z","abstract_excerpt":"Matrix completion is one of the key problems in signal processing and machine learning. In recent years, deep-learning-based models have achieved state-of-the-art results in matrix completion. Nevertheless, they suffer from two drawbacks: (i) they can not be extended easily to rows or columns unseen during training; and (ii) their results are often degraded in case discrete predictions are required. This paper addresses these two drawbacks by presenting a deep matrix factorization model and a generic method to allow joint training of the factorization model and the discretization operator. Exp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01478","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":"2026-05-17T23:59:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8iUzLdlNehY2x5JEY9UhoZSs4/Cejf9SA9qgG70a7tGY8XffKCDnqo5H2eLkZlZC0CYs2u7DAeSDDVpUybkfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T22:54:19.073840Z"},"content_sha256":"81752867b14b801ae7eb95c43d5255c7a62dc84b2c5a0fb2143c1571e303c4df","schema_version":"1.0","event_id":"sha256:81752867b14b801ae7eb95c43d5255c7a62dc84b2c5a0fb2143c1571e303c4df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EW3LGFK467IT6QEFKCJMY46QFE/bundle.json","state_url":"https://pith.science/pith/EW3LGFK467IT6QEFKCJMY46QFE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EW3LGFK467IT6QEFKCJMY46QFE/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":"2026-06-11T22:54:19Z","links":{"resolver":"https://pith.science/pith/EW3LGFK467IT6QEFKCJMY46QFE","bundle":"https://pith.science/pith/EW3LGFK467IT6QEFKCJMY46QFE/bundle.json","state":"https://pith.science/pith/EW3LGFK467IT6QEFKCJMY46QFE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EW3LGFK467IT6QEFKCJMY46QFE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EW3LGFK467IT6QEFKCJMY46QFE","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":"5ccbe9d25b6f3da57be35a4d31d684db983540c55fb2109f74f2892ebeb0e7af","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:15:23Z","title_canon_sha256":"ef76c7fb42ba3081f0c64f65df7056ecd4946b1132cfc740db9e6ed6a4b2f5ae"},"schema_version":"1.0","source":{"id":"1812.01478","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.01478","created_at":"2026-05-17T23:59:12Z"},{"alias_kind":"arxiv_version","alias_value":"1812.01478v1","created_at":"2026-05-17T23:59:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01478","created_at":"2026-05-17T23:59:12Z"},{"alias_kind":"pith_short_12","alias_value":"EW3LGFK467IT","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EW3LGFK467IT6QEF","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EW3LGFK4","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:81752867b14b801ae7eb95c43d5255c7a62dc84b2c5a0fb2143c1571e303c4df","target":"graph","created_at":"2026-05-17T23:59:12Z","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":"Matrix completion is one of the key problems in signal processing and machine learning. In recent years, deep-learning-based models have achieved state-of-the-art results in matrix completion. Nevertheless, they suffer from two drawbacks: (i) they can not be extended easily to rows or columns unseen during training; and (ii) their results are often degraded in case discrete predictions are required. This paper addresses these two drawbacks by presenting a deep matrix factorization model and a generic method to allow joint training of the factorization model and the discretization operator. Exp","authors_text":"Duc Minh Nguyen, Evaggelia Tsiligianni, Nikos Deligiannis","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:15:23Z","title":"Matrix Factorization via Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01478","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":"sha256:3703dd0efaf34c70b6713138db1f58078d7873ac40459dcc6d74ac064f6309a1","target":"record","created_at":"2026-05-17T23:59:12Z","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":"5ccbe9d25b6f3da57be35a4d31d684db983540c55fb2109f74f2892ebeb0e7af","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:15:23Z","title_canon_sha256":"ef76c7fb42ba3081f0c64f65df7056ecd4946b1132cfc740db9e6ed6a4b2f5ae"},"schema_version":"1.0","source":{"id":"1812.01478","kind":"arxiv","version":1}},"canonical_sha256":"25b6b3155cf7d13f40855092cc73d0291ff61f050f8decf064276212f430fff4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25b6b3155cf7d13f40855092cc73d0291ff61f050f8decf064276212f430fff4","first_computed_at":"2026-05-17T23:59:12.356173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:12.356173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wgTN6aOgGR1rhZQWTq+TBf4dgVcURdyjPX6MN+v969B/gfGVZg08ZNOcTZKLTQm636POT4DS8A6ug7u4b788AA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:12.356771Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.01478","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3703dd0efaf34c70b6713138db1f58078d7873ac40459dcc6d74ac064f6309a1","sha256:81752867b14b801ae7eb95c43d5255c7a62dc84b2c5a0fb2143c1571e303c4df"],"state_sha256":"c70b5e7c08a7bbd84185dd06a598015cabf0d3df41586e7bf636083ca2f04bad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R58XVS5fvUKggpx0CzClBT3LQV9Pc+ytO3O9nP/xdj04sf8usGUTljFJdxk4FeUtJdM3MYgo+Sy4k8PL2Kc2CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T22:54:19.076238Z","bundle_sha256":"a0742c4b3f9eb2041eb77ddfc6347b5d01ffd3c82f2de13e33718651ed732e0a"}}