{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Z6SQOECHST6MEERTWQTJ2A2TCV","short_pith_number":"pith:Z6SQOECH","schema_version":"1.0","canonical_sha256":"cfa507104794fcc21233b4269d0353156901426c2c80b6b82453043649190c79","source":{"kind":"arxiv","id":"2012.00386","version":1},"attestation_state":"computed","paper":{"title":"Non-Stationary Latent Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amr Ahmed, Branislav Kveton, Craig Boutilier, Joey Hong, Manzil Zaheer, Mohammad Ghavamzadeh, Yinlam Chow","submitted_at":"2020-12-01T10:31:57Z","abstract_excerpt":"Users of recommender systems often behave in a non-stationary fashion, due to their evolving preferences and tastes over time. In this work, we propose a practical approach for fast personalization to non-stationary users. The key idea is to frame this problem as a latent bandit, where the prototypical models of user behavior are learned offline and the latent state of the user is inferred online from its interactions with the models. We call this problem a non-stationary latent bandit. We propose Thompson sampling algorithms for regret minimization in non-stationary latent bandits, analyze th"},"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":"2012.00386","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-12-01T10:31:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad890783b8c71ca21eb5e26c9926962bd91fee4bfb1c649a0e4822e8e2c7f671","abstract_canon_sha256":"d64c5469ed79d6cbf98b893de820e6bc7aa2d57e45c0574d03c4499669ff6f63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:55:35.769015Z","signature_b64":"voIzVgQopuc/qKztnZ5GI6Rkdf32cXh/pbUu4J9wyRgZ/Za4vQ4dzFkItQwU3vxVS3w5YdIeE0hi+J1ajr56AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfa507104794fcc21233b4269d0353156901426c2c80b6b82453043649190c79","last_reissued_at":"2026-07-05T01:55:35.768516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:55:35.768516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Stationary Latent Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amr Ahmed, Branislav Kveton, Craig Boutilier, Joey Hong, Manzil Zaheer, Mohammad Ghavamzadeh, Yinlam Chow","submitted_at":"2020-12-01T10:31:57Z","abstract_excerpt":"Users of recommender systems often behave in a non-stationary fashion, due to their evolving preferences and tastes over time. In this work, we propose a practical approach for fast personalization to non-stationary users. The key idea is to frame this problem as a latent bandit, where the prototypical models of user behavior are learned offline and the latent state of the user is inferred online from its interactions with the models. We call this problem a non-stationary latent bandit. We propose Thompson sampling algorithms for regret minimization in non-stationary latent bandits, analyze th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.00386","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/2012.00386/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":"2012.00386","created_at":"2026-07-05T01:55:35.768576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.00386v1","created_at":"2026-07-05T01:55:35.768576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.00386","created_at":"2026-07-05T01:55:35.768576+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6SQOECHST6M","created_at":"2026-07-05T01:55:35.768576+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6SQOECHST6MEERT","created_at":"2026-07-05T01:55:35.768576+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6SQOECH","created_at":"2026-07-05T01:55:35.768576+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07304","citing_title":"Latent Order Bandits","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6SQOECHST6MEERTWQTJ2A2TCV","json":"https://pith.science/pith/Z6SQOECHST6MEERTWQTJ2A2TCV.json","graph_json":"https://pith.science/api/pith-number/Z6SQOECHST6MEERTWQTJ2A2TCV/graph.json","events_json":"https://pith.science/api/pith-number/Z6SQOECHST6MEERTWQTJ2A2TCV/events.json","paper":"https://pith.science/paper/Z6SQOECH"},"agent_actions":{"view_html":"https://pith.science/pith/Z6SQOECHST6MEERTWQTJ2A2TCV","download_json":"https://pith.science/pith/Z6SQOECHST6MEERTWQTJ2A2TCV.json","view_paper":"https://pith.science/paper/Z6SQOECH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.00386&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6SQOECHST6MEERTWQTJ2A2TCV/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6SQOECHST6MEERTWQTJ2A2TCV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6SQOECHST6MEERTWQTJ2A2TCV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6SQOECHST6MEERTWQTJ2A2TCV/action/storage_attestation","attest_author":"https://pith.science/pith/Z6SQOECHST6MEERTWQTJ2A2TCV/action/author_attestation","sign_citation":"https://pith.science/pith/Z6SQOECHST6MEERTWQTJ2A2TCV/action/citation_signature","submit_replication":"https://pith.science/pith/Z6SQOECHST6MEERTWQTJ2A2TCV/action/replication_record"}},"created_at":"2026-07-05T01:55:35.768576+00:00","updated_at":"2026-07-05T01:55:35.768576+00:00"}