{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HPKPZXQXBYUF42BOAWRISTUXU2","short_pith_number":"pith:HPKPZXQX","schema_version":"1.0","canonical_sha256":"3bd4fcde170e285e682e05a2894e97a6b584a60b85227e950bb30c0b02816bb6","source":{"kind":"arxiv","id":"2105.08318","version":2},"attestation_state":"computed","paper":{"title":"Zero-Shot Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Anoop Deoras, Hao Ding, Hao Wang, Yifei Ma, Yuyang Wang","submitted_at":"2021-05-18T07:17:37Z","abstract_excerpt":"Performance of recommender systems (RS) relies heavily on the amount of training data available. This poses a chicken-and-egg problem for early-stage products, whose amount of data, in turn, relies on the performance of their RS. On the other hand, zero-shot learning promises some degree of generalization from an old dataset to an entirely new dataset. In this paper, we explore the possibility of zero-shot learning in RS. We develop an algorithm, dubbed ZEro-Shot Recommenders (ZESRec), that is trained on an old dataset and generalize to a new one where there are neither overlapping users nor o"},"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":"2105.08318","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-18T07:17:37Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"67cb9caa1111e24049cf76755f42cbf4638c6930972414b7babd2cf09053a3ad","abstract_canon_sha256":"1cf59b4059575815b623083ac35d928500d5b7dbaecf55f65f366bdf4c107714"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:48.987585Z","signature_b64":"RgkhyPYtwZqfMfiRWcdyK8n0A2Sd6eniy7zgtbqkt4fam0KlwbfLcXvpz4yWAPIaGMCQNaY8Jkyw+OUF4h9uDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bd4fcde170e285e682e05a2894e97a6b584a60b85227e950bb30c0b02816bb6","last_reissued_at":"2026-07-05T03:21:48.986695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:48.986695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Recommender Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.LG","authors_text":"Anoop Deoras, Hao Ding, Hao Wang, Yifei Ma, Yuyang Wang","submitted_at":"2021-05-18T07:17:37Z","abstract_excerpt":"Performance of recommender systems (RS) relies heavily on the amount of training data available. This poses a chicken-and-egg problem for early-stage products, whose amount of data, in turn, relies on the performance of their RS. On the other hand, zero-shot learning promises some degree of generalization from an old dataset to an entirely new dataset. In this paper, we explore the possibility of zero-shot learning in RS. We develop an algorithm, dubbed ZEro-Shot Recommenders (ZESRec), that is trained on an old dataset and generalize to a new one where there are neither overlapping users nor o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.08318","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/2105.08318/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":"2105.08318","created_at":"2026-07-05T03:21:48.986752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.08318v2","created_at":"2026-07-05T03:21:48.986752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.08318","created_at":"2026-07-05T03:21:48.986752+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPKPZXQXBYUF","created_at":"2026-07-05T03:21:48.986752+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPKPZXQXBYUF42BO","created_at":"2026-07-05T03:21:48.986752+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPKPZXQX","created_at":"2026-07-05T03:21:48.986752+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22195","citing_title":"Rethinking Semantic Collaborative Integration: Why Alignment Is Not Enough","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14833","citing_title":"Federated User Behavior Modeling for Privacy-Preserving LLM Recommendation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPKPZXQXBYUF42BOAWRISTUXU2","json":"https://pith.science/pith/HPKPZXQXBYUF42BOAWRISTUXU2.json","graph_json":"https://pith.science/api/pith-number/HPKPZXQXBYUF42BOAWRISTUXU2/graph.json","events_json":"https://pith.science/api/pith-number/HPKPZXQXBYUF42BOAWRISTUXU2/events.json","paper":"https://pith.science/paper/HPKPZXQX"},"agent_actions":{"view_html":"https://pith.science/pith/HPKPZXQXBYUF42BOAWRISTUXU2","download_json":"https://pith.science/pith/HPKPZXQXBYUF42BOAWRISTUXU2.json","view_paper":"https://pith.science/paper/HPKPZXQX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.08318&json=true","fetch_graph":"https://pith.science/api/pith-number/HPKPZXQXBYUF42BOAWRISTUXU2/graph.json","fetch_events":"https://pith.science/api/pith-number/HPKPZXQXBYUF42BOAWRISTUXU2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPKPZXQXBYUF42BOAWRISTUXU2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPKPZXQXBYUF42BOAWRISTUXU2/action/storage_attestation","attest_author":"https://pith.science/pith/HPKPZXQXBYUF42BOAWRISTUXU2/action/author_attestation","sign_citation":"https://pith.science/pith/HPKPZXQXBYUF42BOAWRISTUXU2/action/citation_signature","submit_replication":"https://pith.science/pith/HPKPZXQXBYUF42BOAWRISTUXU2/action/replication_record"}},"created_at":"2026-07-05T03:21:48.986752+00:00","updated_at":"2026-07-05T03:21:48.986752+00:00"}