{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SEEG2IJF6IK2E73T6J4U2SKQMQ","short_pith_number":"pith:SEEG2IJF","schema_version":"1.0","canonical_sha256":"91086d2125f215a27f73f2794d49506413ff21be7f8365042df234c5c049986b","source":{"kind":"arxiv","id":"1708.01715","version":3},"attestation_state":"computed","paper":{"title":"Training Deep AutoEncoders for Collaborative Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Boris Ginsburg, Oleksii Kuchaiev","submitted_at":"2017-08-05T06:31:50Z","abstract_excerpt":"This paper proposes a novel model for the rating prediction task in recommender systems which significantly outperforms previous state-of-the art models on a time-split Netflix data set. Our model is based on deep autoencoder with 6 layers and is trained end-to-end without any layer-wise pre-training. We empirically demonstrate that: a) deep autoencoder models generalize much better than the shallow ones, b) non-linear activation functions with negative parts are crucial for training deep models, and c) heavy use of regularization techniques such as dropout is necessary to prevent over-fiting."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1708.01715","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-08-05T06:31:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"08bba1044e1cef3eb5bfdd2328180eb3653deff90a539bac0e2d81265a174eab","abstract_canon_sha256":"a336f10587caef51fd915a258715b0893cf16457be2ad79bdc782ad8c06804eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:06.322631Z","signature_b64":"5DJjs3i2A8cJBLwuN5PCsyV5Dmuk9BOWIks11aSG1YnxPVRG1JQQGhKRHrrEr5oEil4mlnXplQ3yTiq2mS1NAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91086d2125f215a27f73f2794d49506413ff21be7f8365042df234c5c049986b","last_reissued_at":"2026-05-18T00:33:06.321943Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:06.321943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Deep AutoEncoders for Collaborative Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Boris Ginsburg, Oleksii Kuchaiev","submitted_at":"2017-08-05T06:31:50Z","abstract_excerpt":"This paper proposes a novel model for the rating prediction task in recommender systems which significantly outperforms previous state-of-the art models on a time-split Netflix data set. Our model is based on deep autoencoder with 6 layers and is trained end-to-end without any layer-wise pre-training. We empirically demonstrate that: a) deep autoencoder models generalize much better than the shallow ones, b) non-linear activation functions with negative parts are crucial for training deep models, and c) heavy use of regularization techniques such as dropout is necessary to prevent over-fiting."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01715","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1708.01715","created_at":"2026-05-18T00:33:06.322052+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.01715v3","created_at":"2026-05-18T00:33:06.322052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01715","created_at":"2026-05-18T00:33:06.322052+00:00"},{"alias_kind":"pith_short_12","alias_value":"SEEG2IJF6IK2","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SEEG2IJF6IK2E73T","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SEEG2IJF","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.10910","citing_title":"Creating A Neural Pedagogical Agent by Jointly Learning to Review and Assess","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SEEG2IJF6IK2E73T6J4U2SKQMQ","json":"https://pith.science/pith/SEEG2IJF6IK2E73T6J4U2SKQMQ.json","graph_json":"https://pith.science/api/pith-number/SEEG2IJF6IK2E73T6J4U2SKQMQ/graph.json","events_json":"https://pith.science/api/pith-number/SEEG2IJF6IK2E73T6J4U2SKQMQ/events.json","paper":"https://pith.science/paper/SEEG2IJF"},"agent_actions":{"view_html":"https://pith.science/pith/SEEG2IJF6IK2E73T6J4U2SKQMQ","download_json":"https://pith.science/pith/SEEG2IJF6IK2E73T6J4U2SKQMQ.json","view_paper":"https://pith.science/paper/SEEG2IJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.01715&json=true","fetch_graph":"https://pith.science/api/pith-number/SEEG2IJF6IK2E73T6J4U2SKQMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SEEG2IJF6IK2E73T6J4U2SKQMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SEEG2IJF6IK2E73T6J4U2SKQMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SEEG2IJF6IK2E73T6J4U2SKQMQ/action/storage_attestation","attest_author":"https://pith.science/pith/SEEG2IJF6IK2E73T6J4U2SKQMQ/action/author_attestation","sign_citation":"https://pith.science/pith/SEEG2IJF6IK2E73T6J4U2SKQMQ/action/citation_signature","submit_replication":"https://pith.science/pith/SEEG2IJF6IK2E73T6J4U2SKQMQ/action/replication_record"}},"created_at":"2026-05-18T00:33:06.322052+00:00","updated_at":"2026-05-18T00:33:06.322052+00:00"}