{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZEUMAUNPOQR5QCU36MQPCQTTF7","short_pith_number":"pith:ZEUMAUNP","canonical_record":{"source":{"id":"1807.01798","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T21:54:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"98844c50b57c8ece836cc53416f317b2c6493d1c83ca66d9ba7eb068432e1f54","abstract_canon_sha256":"4e6fa12adde6c48a9e6834d21baf57e9487291dbdd0577e6ff34f8a542ee272b"},"schema_version":"1.0"},"canonical_sha256":"c928c051af7423d80a9bf320f142732fc43aa2ba20559188779ebd404e2d9489","source":{"kind":"arxiv","id":"1807.01798","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01798","created_at":"2026-05-18T00:11:28Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01798v1","created_at":"2026-05-18T00:11:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01798","created_at":"2026-05-18T00:11:28Z"},{"alias_kind":"pith_short_12","alias_value":"ZEUMAUNPOQR5","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZEUMAUNPOQR5QCU3","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZEUMAUNP","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZEUMAUNPOQR5QCU36MQPCQTTF7","target":"record","payload":{"canonical_record":{"source":{"id":"1807.01798","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T21:54:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"98844c50b57c8ece836cc53416f317b2c6493d1c83ca66d9ba7eb068432e1f54","abstract_canon_sha256":"4e6fa12adde6c48a9e6834d21baf57e9487291dbdd0577e6ff34f8a542ee272b"},"schema_version":"1.0"},"canonical_sha256":"c928c051af7423d80a9bf320f142732fc43aa2ba20559188779ebd404e2d9489","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:28.609642Z","signature_b64":"Zsjejhi/d/aE0qooffjPZRzi2sE6fJXI8gnytbJr14Spt+0czJvV1jzKuZ0JFcziPkn83O7yy1ulobfQOCP0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c928c051af7423d80a9bf320f142732fc43aa2ba20559188779ebd404e2d9489","last_reissued_at":"2026-05-18T00:11:28.609213Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:28.609213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.01798","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":"2026-05-18T00:11:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ErN39bA7grzRNS4PU/i49Nn1PKGD/10MGANwsF4yR4Z+OzpiOmgkj/5Vz66kPszEnEWLOjkpCOINkz5f38yCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T09:46:29.176509Z"},"content_sha256":"6b75acccb168d2317337a6834f5b8c38ae0420dc37461de9fac5ea0c7231ee2f","schema_version":"1.0","event_id":"sha256:6b75acccb168d2317337a6834f5b8c38ae0420dc37461de9fac5ea0c7231ee2f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZEUMAUNPOQR5QCU36MQPCQTTF7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regularizing Autoencoder-Based Matrix Completion Models via Manifold Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Duc Minh Nguyen, Evaggelia Tsiligianni, Nikos Deligiannis, Robert Calderbank","submitted_at":"2018-07-04T21:54:27Z","abstract_excerpt":"Autoencoders are popular among neural-network-based matrix completion models due to their ability to retrieve potential latent factors from the partially observed matrices. Nevertheless, when training data is scarce their performance is significantly degraded due to overfitting. In this paper, we mit- igate overfitting with a data-dependent regularization technique that relies on the principles of multi-task learning. Specifically, we propose an autoencoder-based matrix completion model that performs prediction of the unknown matrix values as a main task, and manifold learning as an auxiliary "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01798","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":"2026-05-18T00:11:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mnOKGCCFf/IfScmzent4GiUJgAz4RTMQlC8UNZ2u6Q6ahHndIRWUu75Aw/YxbN+v8b/Xi2DFzSzfSjT0kPyyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T09:46:29.177047Z"},"content_sha256":"9848316611441c15322ac7733fca3e648cf629edea1cb743e68f5fa5f91ba88b","schema_version":"1.0","event_id":"sha256:9848316611441c15322ac7733fca3e648cf629edea1cb743e68f5fa5f91ba88b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZEUMAUNPOQR5QCU36MQPCQTTF7/bundle.json","state_url":"https://pith.science/pith/ZEUMAUNPOQR5QCU36MQPCQTTF7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZEUMAUNPOQR5QCU36MQPCQTTF7/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":"2026-06-12T09:46:29Z","links":{"resolver":"https://pith.science/pith/ZEUMAUNPOQR5QCU36MQPCQTTF7","bundle":"https://pith.science/pith/ZEUMAUNPOQR5QCU36MQPCQTTF7/bundle.json","state":"https://pith.science/pith/ZEUMAUNPOQR5QCU36MQPCQTTF7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZEUMAUNPOQR5QCU36MQPCQTTF7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZEUMAUNPOQR5QCU36MQPCQTTF7","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":"4e6fa12adde6c48a9e6834d21baf57e9487291dbdd0577e6ff34f8a542ee272b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T21:54:27Z","title_canon_sha256":"98844c50b57c8ece836cc53416f317b2c6493d1c83ca66d9ba7eb068432e1f54"},"schema_version":"1.0","source":{"id":"1807.01798","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.01798","created_at":"2026-05-18T00:11:28Z"},{"alias_kind":"arxiv_version","alias_value":"1807.01798v1","created_at":"2026-05-18T00:11:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01798","created_at":"2026-05-18T00:11:28Z"},{"alias_kind":"pith_short_12","alias_value":"ZEUMAUNPOQR5","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZEUMAUNPOQR5QCU3","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZEUMAUNP","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:9848316611441c15322ac7733fca3e648cf629edea1cb743e68f5fa5f91ba88b","target":"graph","created_at":"2026-05-18T00:11:28Z","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":"Autoencoders are popular among neural-network-based matrix completion models due to their ability to retrieve potential latent factors from the partially observed matrices. Nevertheless, when training data is scarce their performance is significantly degraded due to overfitting. In this paper, we mit- igate overfitting with a data-dependent regularization technique that relies on the principles of multi-task learning. Specifically, we propose an autoencoder-based matrix completion model that performs prediction of the unknown matrix values as a main task, and manifold learning as an auxiliary ","authors_text":"Duc Minh Nguyen, Evaggelia Tsiligianni, Nikos Deligiannis, Robert Calderbank","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T21:54:27Z","title":"Regularizing Autoencoder-Based Matrix Completion Models via Manifold Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01798","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":"sha256:6b75acccb168d2317337a6834f5b8c38ae0420dc37461de9fac5ea0c7231ee2f","target":"record","created_at":"2026-05-18T00:11:28Z","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":"4e6fa12adde6c48a9e6834d21baf57e9487291dbdd0577e6ff34f8a542ee272b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-04T21:54:27Z","title_canon_sha256":"98844c50b57c8ece836cc53416f317b2c6493d1c83ca66d9ba7eb068432e1f54"},"schema_version":"1.0","source":{"id":"1807.01798","kind":"arxiv","version":1}},"canonical_sha256":"c928c051af7423d80a9bf320f142732fc43aa2ba20559188779ebd404e2d9489","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c928c051af7423d80a9bf320f142732fc43aa2ba20559188779ebd404e2d9489","first_computed_at":"2026-05-18T00:11:28.609213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:28.609213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zsjejhi/d/aE0qooffjPZRzi2sE6fJXI8gnytbJr14Spt+0czJvV1jzKuZ0JFcziPkn83O7yy1ulobfQOCP0Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:28.609642Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.01798","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b75acccb168d2317337a6834f5b8c38ae0420dc37461de9fac5ea0c7231ee2f","sha256:9848316611441c15322ac7733fca3e648cf629edea1cb743e68f5fa5f91ba88b"],"state_sha256":"630ee00ae9cbac86630ff39b8e26697072c8780da02ea50f45fd9d1a682dcc21"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ljCounIjLRHLSPHSGsfUpvX3TQm9nmWNBEwAg52yvQ7IID0D3nBGmvcCiinOKmMLqxo6T1kf4JScSjTq7BajBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T09:46:29.179376Z","bundle_sha256":"9f9be41aa36e4b9ca05eeaf3cfa9e9124171d7cc593bac4f43b2bf4087d4eb1a"}}