{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SG54D44DSINQLBDZVRKFFUE4OD","short_pith_number":"pith:SG54D44D","schema_version":"1.0","canonical_sha256":"91bbc1f383921b058479ac5452d09c70d97b628a4a4d86e5807b017aa080eaed","source":{"kind":"arxiv","id":"2112.00979","version":1},"attestation_state":"computed","paper":{"title":"Recommending with Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Franklyn Wang, Naveen Durvasula, Scott Duke Kominers","submitted_at":"2021-12-02T04:30:15Z","abstract_excerpt":"Recommendation systems are a key modern application of machine learning, but they have the downside that they often draw upon sensitive user information in making their predictions. We show how to address this deficiency by basing a service's recommendation engine upon recommendations from other existing services, which contain no sensitive information by nature. Specifically, we introduce a contextual multi-armed bandit recommendation framework where the agent has access to recommendations for other services. In our setting, the user's (potentially sensitive) information belongs to a high-dim"},"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":"2112.00979","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-02T04:30:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bdc350ab41ce2e0d9cb2855931fe82a837502f21f6ad80bcef0bce370c50f10c","abstract_canon_sha256":"8b0ab0b622d1a31b2c46635bb577a351b3d0dbe27412ea482a1a31356ac3fb05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:02.169565Z","signature_b64":"wkw3oVAX3aOzXWwAwjl77R0/f8uG3vDy/x2jqwmOqST4Zr03/ma8NiijvMneRyyvDXM9kQJG+C7ZHA0Xo7ptAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91bbc1f383921b058479ac5452d09c70d97b628a4a4d86e5807b017aa080eaed","last_reissued_at":"2026-07-05T03:37:02.169097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:02.169097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recommending with Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Franklyn Wang, Naveen Durvasula, Scott Duke Kominers","submitted_at":"2021-12-02T04:30:15Z","abstract_excerpt":"Recommendation systems are a key modern application of machine learning, but they have the downside that they often draw upon sensitive user information in making their predictions. We show how to address this deficiency by basing a service's recommendation engine upon recommendations from other existing services, which contain no sensitive information by nature. Specifically, we introduce a contextual multi-armed bandit recommendation framework where the agent has access to recommendations for other services. In our setting, the user's (potentially sensitive) information belongs to a high-dim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.00979","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.00979/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":"2112.00979","created_at":"2026-07-05T03:37:02.169156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.00979v1","created_at":"2026-07-05T03:37:02.169156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.00979","created_at":"2026-07-05T03:37:02.169156+00:00"},{"alias_kind":"pith_short_12","alias_value":"SG54D44DSINQ","created_at":"2026-07-05T03:37:02.169156+00:00"},{"alias_kind":"pith_short_16","alias_value":"SG54D44DSINQLBDZ","created_at":"2026-07-05T03:37:02.169156+00:00"},{"alias_kind":"pith_short_8","alias_value":"SG54D44D","created_at":"2026-07-05T03:37:02.169156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SG54D44DSINQLBDZVRKFFUE4OD","json":"https://pith.science/pith/SG54D44DSINQLBDZVRKFFUE4OD.json","graph_json":"https://pith.science/api/pith-number/SG54D44DSINQLBDZVRKFFUE4OD/graph.json","events_json":"https://pith.science/api/pith-number/SG54D44DSINQLBDZVRKFFUE4OD/events.json","paper":"https://pith.science/paper/SG54D44D"},"agent_actions":{"view_html":"https://pith.science/pith/SG54D44DSINQLBDZVRKFFUE4OD","download_json":"https://pith.science/pith/SG54D44DSINQLBDZVRKFFUE4OD.json","view_paper":"https://pith.science/paper/SG54D44D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.00979&json=true","fetch_graph":"https://pith.science/api/pith-number/SG54D44DSINQLBDZVRKFFUE4OD/graph.json","fetch_events":"https://pith.science/api/pith-number/SG54D44DSINQLBDZVRKFFUE4OD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SG54D44DSINQLBDZVRKFFUE4OD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SG54D44DSINQLBDZVRKFFUE4OD/action/storage_attestation","attest_author":"https://pith.science/pith/SG54D44DSINQLBDZVRKFFUE4OD/action/author_attestation","sign_citation":"https://pith.science/pith/SG54D44DSINQLBDZVRKFFUE4OD/action/citation_signature","submit_replication":"https://pith.science/pith/SG54D44DSINQLBDZVRKFFUE4OD/action/replication_record"}},"created_at":"2026-07-05T03:37:02.169156+00:00","updated_at":"2026-07-05T03:37:02.169156+00:00"}