{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:O7QDRWIOSI6TEFSF7WSENTXPZN","short_pith_number":"pith:O7QDRWIO","schema_version":"1.0","canonical_sha256":"77e038d90e923d321645fda446ceefcb6fdd6250a40eab756f29c13ec7e1d54a","source":{"kind":"arxiv","id":"1811.12253","version":1},"attestation_state":"computed","paper":{"title":"Unifying the stochastic and the adversarial Bandits with Knapsack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anshuka Rangi, Long Tran-Thanh, Massimo Franceschetti","submitted_at":"2018-10-23T04:34:30Z","abstract_excerpt":"This paper investigates the adversarial Bandits with Knapsack (BwK) online learning problem, where a player repeatedly chooses to perform an action, pays the corresponding cost, and receives a reward associated with the action. The player is constrained by the maximum budget $B$ that can be spent to perform actions, and the rewards and the costs of the actions are assigned by an adversary. This problem has only been studied in the restricted setting where the reward of an action is greater than the cost of the action, while we provide a solution in the general setting. Namely, we propose EXP3."},"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":"1811.12253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-23T04:34:30Z","cross_cats_sorted":["cs.GT","cs.MA","stat.ML"],"title_canon_sha256":"b78c0094370374b6008e708d1fd73adc755e84576bac6eaf89a6bc11691b0809","abstract_canon_sha256":"1f9af7f1e8b5b3cd4a8b95f8c0606aaca59e7755482424ced05dfea48108cc83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:33.915266Z","signature_b64":"EA/vrsMUlv4Jq4wqRc1+V1u8Vbfq3BS0Tfnf5fU3cMauK2SyvllmpkC4Mfk10QoRUvMp47MjGjNm1nWw885ICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77e038d90e923d321645fda446ceefcb6fdd6250a40eab756f29c13ec7e1d54a","last_reissued_at":"2026-05-17T23:59:33.914358Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:33.914358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying the stochastic and the adversarial Bandits with Knapsack","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anshuka Rangi, Long Tran-Thanh, Massimo Franceschetti","submitted_at":"2018-10-23T04:34:30Z","abstract_excerpt":"This paper investigates the adversarial Bandits with Knapsack (BwK) online learning problem, where a player repeatedly chooses to perform an action, pays the corresponding cost, and receives a reward associated with the action. The player is constrained by the maximum budget $B$ that can be spent to perform actions, and the rewards and the costs of the actions are assigned by an adversary. This problem has only been studied in the restricted setting where the reward of an action is greater than the cost of the action, while we provide a solution in the general setting. Namely, we propose EXP3."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.12253","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":"1811.12253","created_at":"2026-05-17T23:59:33.914516+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.12253v1","created_at":"2026-05-17T23:59:33.914516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.12253","created_at":"2026-05-17T23:59:33.914516+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7QDRWIOSI6T","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7QDRWIOSI6TEFSF","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7QDRWIO","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05599","citing_title":"Online Bidding Algorithms with Strict Return on Spend (ROS) Constraint","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7QDRWIOSI6TEFSF7WSENTXPZN","json":"https://pith.science/pith/O7QDRWIOSI6TEFSF7WSENTXPZN.json","graph_json":"https://pith.science/api/pith-number/O7QDRWIOSI6TEFSF7WSENTXPZN/graph.json","events_json":"https://pith.science/api/pith-number/O7QDRWIOSI6TEFSF7WSENTXPZN/events.json","paper":"https://pith.science/paper/O7QDRWIO"},"agent_actions":{"view_html":"https://pith.science/pith/O7QDRWIOSI6TEFSF7WSENTXPZN","download_json":"https://pith.science/pith/O7QDRWIOSI6TEFSF7WSENTXPZN.json","view_paper":"https://pith.science/paper/O7QDRWIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.12253&json=true","fetch_graph":"https://pith.science/api/pith-number/O7QDRWIOSI6TEFSF7WSENTXPZN/graph.json","fetch_events":"https://pith.science/api/pith-number/O7QDRWIOSI6TEFSF7WSENTXPZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7QDRWIOSI6TEFSF7WSENTXPZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7QDRWIOSI6TEFSF7WSENTXPZN/action/storage_attestation","attest_author":"https://pith.science/pith/O7QDRWIOSI6TEFSF7WSENTXPZN/action/author_attestation","sign_citation":"https://pith.science/pith/O7QDRWIOSI6TEFSF7WSENTXPZN/action/citation_signature","submit_replication":"https://pith.science/pith/O7QDRWIOSI6TEFSF7WSENTXPZN/action/replication_record"}},"created_at":"2026-05-17T23:59:33.914516+00:00","updated_at":"2026-05-17T23:59:33.914516+00:00"}