{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6OY3VXMVL7EPSTUWU2EXMHYU4S","short_pith_number":"pith:6OY3VXMV","schema_version":"1.0","canonical_sha256":"f3b1badd955fc8f94e96a689761f14e4b17479865962e4e5df386d1dfd7fd2d9","source":{"kind":"arxiv","id":"1801.03423","version":1},"attestation_state":"computed","paper":{"title":"A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Roth, Bo Waggoner, Jamie Morgenstern, Sampath Kannan, Zhiwei Steven Wu","submitted_at":"2018-01-10T15:40:05Z","abstract_excerpt":"Bandit learning is characterized by the tension between long-term exploration and short-term exploitation. However, as has recently been noted, in settings in which the choices of the learning algorithm correspond to important decisions about individual people (such as criminal recidivism prediction, lending, and sequential drug trials), exploration corresponds to explicitly sacrificing the well-being of one individual for the potential future benefit of others. This raises a fairness concern. In such settings, one might like to run a \"greedy\" algorithm, which always makes the (myopically) opt"},"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":"1801.03423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-10T15:40:05Z","cross_cats_sorted":[],"title_canon_sha256":"9cad9c735db2405046c265fc4fa6774b20ec883c2771182883920b95f357c630","abstract_canon_sha256":"2be890346a3a58f8f7bf4edfb0233f85574c46c3fd46c4c9a945b9906d10e42f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:17.114504Z","signature_b64":"0qBgNAOl8SCtZIZJWzfsXrIyCoWgqFXivfhDW67vS0s7gqljiCpzU10d5IvVuTswZGURlBnXuUNLd95cDWmBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3b1badd955fc8f94e96a689761f14e4b17479865962e4e5df386d1dfd7fd2d9","last_reissued_at":"2026-05-18T00:26:17.113844Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:17.113844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Roth, Bo Waggoner, Jamie Morgenstern, Sampath Kannan, Zhiwei Steven Wu","submitted_at":"2018-01-10T15:40:05Z","abstract_excerpt":"Bandit learning is characterized by the tension between long-term exploration and short-term exploitation. However, as has recently been noted, in settings in which the choices of the learning algorithm correspond to important decisions about individual people (such as criminal recidivism prediction, lending, and sequential drug trials), exploration corresponds to explicitly sacrificing the well-being of one individual for the potential future benefit of others. This raises a fairness concern. In such settings, one might like to run a \"greedy\" algorithm, which always makes the (myopically) opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.03423","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":""},"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":"1801.03423","created_at":"2026-05-18T00:26:17.113960+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.03423v1","created_at":"2026-05-18T00:26:17.113960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.03423","created_at":"2026-05-18T00:26:17.113960+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OY3VXMVL7EP","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OY3VXMVL7EPSTUW","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OY3VXMV","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19672","citing_title":"Budgeted Online Influence Maximization","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6OY3VXMVL7EPSTUWU2EXMHYU4S","json":"https://pith.science/pith/6OY3VXMVL7EPSTUWU2EXMHYU4S.json","graph_json":"https://pith.science/api/pith-number/6OY3VXMVL7EPSTUWU2EXMHYU4S/graph.json","events_json":"https://pith.science/api/pith-number/6OY3VXMVL7EPSTUWU2EXMHYU4S/events.json","paper":"https://pith.science/paper/6OY3VXMV"},"agent_actions":{"view_html":"https://pith.science/pith/6OY3VXMVL7EPSTUWU2EXMHYU4S","download_json":"https://pith.science/pith/6OY3VXMVL7EPSTUWU2EXMHYU4S.json","view_paper":"https://pith.science/paper/6OY3VXMV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.03423&json=true","fetch_graph":"https://pith.science/api/pith-number/6OY3VXMVL7EPSTUWU2EXMHYU4S/graph.json","fetch_events":"https://pith.science/api/pith-number/6OY3VXMVL7EPSTUWU2EXMHYU4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OY3VXMVL7EPSTUWU2EXMHYU4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OY3VXMVL7EPSTUWU2EXMHYU4S/action/storage_attestation","attest_author":"https://pith.science/pith/6OY3VXMVL7EPSTUWU2EXMHYU4S/action/author_attestation","sign_citation":"https://pith.science/pith/6OY3VXMVL7EPSTUWU2EXMHYU4S/action/citation_signature","submit_replication":"https://pith.science/pith/6OY3VXMVL7EPSTUWU2EXMHYU4S/action/replication_record"}},"created_at":"2026-05-18T00:26:17.113960+00:00","updated_at":"2026-05-18T00:26:17.113960+00:00"}