{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:K6X4LOTANLS2PWYMZDXQDOIDAV","short_pith_number":"pith:K6X4LOTA","schema_version":"1.0","canonical_sha256":"57afc5ba606ae5a7db0cc8ef01b903054651f4fdb7187eab3d992b23d5664996","source":{"kind":"arxiv","id":"1207.0166","version":3},"attestation_state":"computed","paper":{"title":"On Multilabel Classification and Ranking with Partial Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Claudio Gentile, Francesco Orabona","submitted_at":"2012-06-30T23:07:03Z","abstract_excerpt":"We present a novel multilabel/ranking algorithm working in partial information settings. The algorithm is based on 2nd-order descent methods, and relies on upper-confidence bounds to trade-off exploration and exploitation. We analyze this algorithm in a partial adversarial setting, where covariates can be adversarial, but multilabel probabilities are ruled by (generalized) linear models. We show O(T^{1/2} log T) regret bounds, which improve in several ways on the existing results. We test the effectiveness of our upper-confidence scheme by contrasting against full-information baselines on real"},"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":"1207.0166","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-30T23:07:03Z","cross_cats_sorted":[],"title_canon_sha256":"c4d25fc0bdc5ff3aaa7de0fcf238899426a8ca39ed72931cf3c685ffcd91006a","abstract_canon_sha256":"8525a8c98a8bc3f078a1646fa19edcf8a7d50e594e9ae4875e2524aabeb3c29a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:36:16.682407Z","signature_b64":"wZHkiaDJJolXrZYneH8N3/EWFwdD81qt8xPpGFrBIoEIK9xTe/5ooDDRjIlAkWRwREtsyVdmjFJ4rMqRHX/jAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57afc5ba606ae5a7db0cc8ef01b903054651f4fdb7187eab3d992b23d5664996","last_reissued_at":"2026-05-18T03:36:16.681762Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:36:16.681762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Multilabel Classification and Ranking with Partial Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Claudio Gentile, Francesco Orabona","submitted_at":"2012-06-30T23:07:03Z","abstract_excerpt":"We present a novel multilabel/ranking algorithm working in partial information settings. The algorithm is based on 2nd-order descent methods, and relies on upper-confidence bounds to trade-off exploration and exploitation. We analyze this algorithm in a partial adversarial setting, where covariates can be adversarial, but multilabel probabilities are ruled by (generalized) linear models. We show O(T^{1/2} log T) regret bounds, which improve in several ways on the existing results. We test the effectiveness of our upper-confidence scheme by contrasting against full-information baselines on real"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.0166","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":"1207.0166","created_at":"2026-05-18T03:36:16.681859+00:00"},{"alias_kind":"arxiv_version","alias_value":"1207.0166v3","created_at":"2026-05-18T03:36:16.681859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.0166","created_at":"2026-05-18T03:36:16.681859+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6X4LOTANLS2","created_at":"2026-05-18T12:27:11.947152+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6X4LOTANLS2PWYM","created_at":"2026-05-18T12:27:11.947152+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6X4LOTA","created_at":"2026-05-18T12:27:11.947152+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/K6X4LOTANLS2PWYMZDXQDOIDAV","json":"https://pith.science/pith/K6X4LOTANLS2PWYMZDXQDOIDAV.json","graph_json":"https://pith.science/api/pith-number/K6X4LOTANLS2PWYMZDXQDOIDAV/graph.json","events_json":"https://pith.science/api/pith-number/K6X4LOTANLS2PWYMZDXQDOIDAV/events.json","paper":"https://pith.science/paper/K6X4LOTA"},"agent_actions":{"view_html":"https://pith.science/pith/K6X4LOTANLS2PWYMZDXQDOIDAV","download_json":"https://pith.science/pith/K6X4LOTANLS2PWYMZDXQDOIDAV.json","view_paper":"https://pith.science/paper/K6X4LOTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1207.0166&json=true","fetch_graph":"https://pith.science/api/pith-number/K6X4LOTANLS2PWYMZDXQDOIDAV/graph.json","fetch_events":"https://pith.science/api/pith-number/K6X4LOTANLS2PWYMZDXQDOIDAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6X4LOTANLS2PWYMZDXQDOIDAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6X4LOTANLS2PWYMZDXQDOIDAV/action/storage_attestation","attest_author":"https://pith.science/pith/K6X4LOTANLS2PWYMZDXQDOIDAV/action/author_attestation","sign_citation":"https://pith.science/pith/K6X4LOTANLS2PWYMZDXQDOIDAV/action/citation_signature","submit_replication":"https://pith.science/pith/K6X4LOTANLS2PWYMZDXQDOIDAV/action/replication_record"}},"created_at":"2026-05-18T03:36:16.681859+00:00","updated_at":"2026-05-18T03:36:16.681859+00:00"}