{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:3YKEMNG7A3FZ2R6Q447EKTUH73","short_pith_number":"pith:3YKEMNG7","schema_version":"1.0","canonical_sha256":"de144634df06cb9d47d0e73e454e87feffbd50c3d946e6e3bc2b100a2955feeb","source":{"kind":"arxiv","id":"1602.07182","version":3},"attestation_state":"computed","paper":{"title":"Explore First, Exploit Next: The True Shape of Regret in Bandit Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.TH"],"primary_cat":"math.ST","authors_text":"Aur\\'elien Garivier (IMT), Gilles Stoltz (GREGH), Pierre M\\'enard (IMT)","submitted_at":"2016-02-23T15:04:13Z","abstract_excerpt":"We revisit lower bounds on the regret in the case of multi-armed bandit problems. We obtain non-asymptotic, distribution-dependent bounds and provide straightforward proofs based only on well-known properties of Kullback-Leibler divergences. These bounds show in particular that in an initial phase the regret grows almost linearly, and that the well-known logarithmic growth of the regret only holds in a final phase. The proof techniques come to the essence of the information-theoretic arguments used and they are deprived of all unnecessary complications."},"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":"1602.07182","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2016-02-23T15:04:13Z","cross_cats_sorted":["cs.LG","stat.TH"],"title_canon_sha256":"8c2f32366b1085e31bed99833862bbb9acf1dc9ffc0a9a5260cb45821daf9b87","abstract_canon_sha256":"4ecacefac1163509f3991cea1e07cf709b9543fd1122ad31d17ca8e9cd87429c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:29.833237Z","signature_b64":"tmXOiwpicAJYmsn4W5F0/fTanQikoycPHTBjmtGUxXRrOILVutNyTu6WRSlRiExrqQk0r+bl3eOo3zGDfGAsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de144634df06cb9d47d0e73e454e87feffbd50c3d946e6e3bc2b100a2955feeb","last_reissued_at":"2026-05-18T00:03:29.832623Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:29.832623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explore First, Exploit Next: The True Shape of Regret in Bandit Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.TH"],"primary_cat":"math.ST","authors_text":"Aur\\'elien Garivier (IMT), Gilles Stoltz (GREGH), Pierre M\\'enard (IMT)","submitted_at":"2016-02-23T15:04:13Z","abstract_excerpt":"We revisit lower bounds on the regret in the case of multi-armed bandit problems. We obtain non-asymptotic, distribution-dependent bounds and provide straightforward proofs based only on well-known properties of Kullback-Leibler divergences. These bounds show in particular that in an initial phase the regret grows almost linearly, and that the well-known logarithmic growth of the regret only holds in a final phase. The proof techniques come to the essence of the information-theoretic arguments used and they are deprived of all unnecessary complications."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.07182","kind":"arxiv","version":3},"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":"1602.07182","created_at":"2026-05-18T00:03:29.832730+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.07182v3","created_at":"2026-05-18T00:03:29.832730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.07182","created_at":"2026-05-18T00:03:29.832730+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YKEMNG7A3FZ","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YKEMNG7A3FZ2R6Q","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YKEMNG7","created_at":"2026-05-18T12:29:58.707656+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":217,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YKEMNG7A3FZ2R6Q447EKTUH73","json":"https://pith.science/pith/3YKEMNG7A3FZ2R6Q447EKTUH73.json","graph_json":"https://pith.science/api/pith-number/3YKEMNG7A3FZ2R6Q447EKTUH73/graph.json","events_json":"https://pith.science/api/pith-number/3YKEMNG7A3FZ2R6Q447EKTUH73/events.json","paper":"https://pith.science/paper/3YKEMNG7"},"agent_actions":{"view_html":"https://pith.science/pith/3YKEMNG7A3FZ2R6Q447EKTUH73","download_json":"https://pith.science/pith/3YKEMNG7A3FZ2R6Q447EKTUH73.json","view_paper":"https://pith.science/paper/3YKEMNG7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.07182&json=true","fetch_graph":"https://pith.science/api/pith-number/3YKEMNG7A3FZ2R6Q447EKTUH73/graph.json","fetch_events":"https://pith.science/api/pith-number/3YKEMNG7A3FZ2R6Q447EKTUH73/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YKEMNG7A3FZ2R6Q447EKTUH73/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YKEMNG7A3FZ2R6Q447EKTUH73/action/storage_attestation","attest_author":"https://pith.science/pith/3YKEMNG7A3FZ2R6Q447EKTUH73/action/author_attestation","sign_citation":"https://pith.science/pith/3YKEMNG7A3FZ2R6Q447EKTUH73/action/citation_signature","submit_replication":"https://pith.science/pith/3YKEMNG7A3FZ2R6Q447EKTUH73/action/replication_record"}},"created_at":"2026-05-18T00:03:29.832730+00:00","updated_at":"2026-05-18T00:03:29.832730+00:00"}