{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5JZ34VOVGBZN37FNX5ACEAWLUT","short_pith_number":"pith:5JZ34VOV","schema_version":"1.0","canonical_sha256":"ea73be55d53072ddfcadbf402202cba4ea70565237f9ae16f28d35eb1f55812d","source":{"kind":"arxiv","id":"2008.01246","version":2},"attestation_state":"computed","paper":{"title":"Noise Contrastive Estimation for Autoencoding-based One-Class Collaborative Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ga Wu, Jin Peng Zhou, Scott Sanner, Zheda Mai","submitted_at":"2020-08-03T23:49:45Z","abstract_excerpt":"One-class collaborative filtering (OC-CF) is a common class of recommendation problem where only the positive class is explicitly observed (e.g., purchases, clicks). Autoencoder based recommenders such as AutoRec and variants demonstrate strong performance on many OC-CF benchmarks, but also empirically suffer from a strong popularity bias. While a careful choice of negative samples in the OC-CF setting can mitigate popularity bias, Negative Sampling (NS) is often better for training embeddings than for the end task itself. To address this, we propose a two-headed AutoRec to first train an embe"},"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":"2008.01246","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2020-08-03T23:49:45Z","cross_cats_sorted":[],"title_canon_sha256":"758b002247c728cdfef87a2edf0c5ff22be681afc1ea6b02033bd735860637a8","abstract_canon_sha256":"736a1cf5f93c3f661f350fdfc6c988033a81f5a6e55a8dba45121d89d6a6c4cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:03.551216Z","signature_b64":"+KJnVR2qe0tmh8T6tkS1tStzy6bCfMOZ4OGmrbnWweacyIr8fLW6Ah/2uZ/PtXDry9eRZEhcBVHxhs+wImVbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea73be55d53072ddfcadbf402202cba4ea70565237f9ae16f28d35eb1f55812d","last_reissued_at":"2026-07-05T01:25:03.550663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:03.550663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noise Contrastive Estimation for Autoencoding-based One-Class Collaborative Filtering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ga Wu, Jin Peng Zhou, Scott Sanner, Zheda Mai","submitted_at":"2020-08-03T23:49:45Z","abstract_excerpt":"One-class collaborative filtering (OC-CF) is a common class of recommendation problem where only the positive class is explicitly observed (e.g., purchases, clicks). Autoencoder based recommenders such as AutoRec and variants demonstrate strong performance on many OC-CF benchmarks, but also empirically suffer from a strong popularity bias. While a careful choice of negative samples in the OC-CF setting can mitigate popularity bias, Negative Sampling (NS) is often better for training embeddings than for the end task itself. To address this, we propose a two-headed AutoRec to first train an embe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.01246","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.01246/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2008.01246","created_at":"2026-07-05T01:25:03.550725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.01246v2","created_at":"2026-07-05T01:25:03.550725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.01246","created_at":"2026-07-05T01:25:03.550725+00:00"},{"alias_kind":"pith_short_12","alias_value":"5JZ34VOVGBZN","created_at":"2026-07-05T01:25:03.550725+00:00"},{"alias_kind":"pith_short_16","alias_value":"5JZ34VOVGBZN37FN","created_at":"2026-07-05T01:25:03.550725+00:00"},{"alias_kind":"pith_short_8","alias_value":"5JZ34VOV","created_at":"2026-07-05T01:25:03.550725+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19651","citing_title":"Divergence Meets Consensus: A Multi-Source Negative Sampling Framework for Sequential Recommendation","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5JZ34VOVGBZN37FNX5ACEAWLUT","json":"https://pith.science/pith/5JZ34VOVGBZN37FNX5ACEAWLUT.json","graph_json":"https://pith.science/api/pith-number/5JZ34VOVGBZN37FNX5ACEAWLUT/graph.json","events_json":"https://pith.science/api/pith-number/5JZ34VOVGBZN37FNX5ACEAWLUT/events.json","paper":"https://pith.science/paper/5JZ34VOV"},"agent_actions":{"view_html":"https://pith.science/pith/5JZ34VOVGBZN37FNX5ACEAWLUT","download_json":"https://pith.science/pith/5JZ34VOVGBZN37FNX5ACEAWLUT.json","view_paper":"https://pith.science/paper/5JZ34VOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.01246&json=true","fetch_graph":"https://pith.science/api/pith-number/5JZ34VOVGBZN37FNX5ACEAWLUT/graph.json","fetch_events":"https://pith.science/api/pith-number/5JZ34VOVGBZN37FNX5ACEAWLUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5JZ34VOVGBZN37FNX5ACEAWLUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5JZ34VOVGBZN37FNX5ACEAWLUT/action/storage_attestation","attest_author":"https://pith.science/pith/5JZ34VOVGBZN37FNX5ACEAWLUT/action/author_attestation","sign_citation":"https://pith.science/pith/5JZ34VOVGBZN37FNX5ACEAWLUT/action/citation_signature","submit_replication":"https://pith.science/pith/5JZ34VOVGBZN37FNX5ACEAWLUT/action/replication_record"}},"created_at":"2026-07-05T01:25:03.550725+00:00","updated_at":"2026-07-05T01:25:03.550725+00:00"}