{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6IJ6EX56NRLMSVYQ44A5OK4PVW","short_pith_number":"pith:6IJ6EX56","schema_version":"1.0","canonical_sha256":"f213e25fbe6c56c95710e701d72b8fadb778cef1666c5e70c0e2b98d3461ae9f","source":{"kind":"arxiv","id":"2602.09402","version":2},"attestation_state":"computed","paper":{"title":"Learning with Multiple Correct Answers -- Regret Bounds under Different Feedback Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alireza F. Pour, Farnam Mansouri, Shai Ben-David","submitted_at":"2026-02-10T04:17:02Z","abstract_excerpt":"We study the problem of learning with multiple correct answers, where each instance admits a set of valid labels. We primarily focus on the online setup, where in each round the learner must output a valid label for the queried example. This setting is motivated by language generation, in which a prompt may admit many acceptable completions, but not every completion is acceptable. We study this problem under three feedback models. For each model, we characterize the optimal mistake bound in the realizable setting using an appropriate combinatorial dimension. We then show that the rate of regre"},"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":"2602.09402","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T04:17:02Z","cross_cats_sorted":[],"title_canon_sha256":"e6e0182a4a37628298a154fe06f4ad6043538601f52e81f3c7fc0a19afaec5f3","abstract_canon_sha256":"5a7580507bd051d751001aa157f9ef89f3abfd5048136e408de90ca1b93b73e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:03.487272Z","signature_b64":"EdZSnY4c8mFVBlAfeo/UA5ZZiJ1K9ZOJvjZvKrAG9j4OD2zRYzOUye3pwPEHkesSkWV6E259cE9Es+wDFHq7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f213e25fbe6c56c95710e701d72b8fadb778cef1666c5e70c0e2b98d3461ae9f","last_reissued_at":"2026-06-23T01:13:03.486591Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:03.486591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning with Multiple Correct Answers -- Regret Bounds under Different Feedback Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alireza F. Pour, Farnam Mansouri, Shai Ben-David","submitted_at":"2026-02-10T04:17:02Z","abstract_excerpt":"We study the problem of learning with multiple correct answers, where each instance admits a set of valid labels. We primarily focus on the online setup, where in each round the learner must output a valid label for the queried example. This setting is motivated by language generation, in which a prompt may admit many acceptable completions, but not every completion is acceptable. We study this problem under three feedback models. For each model, we characterize the optimal mistake bound in the realizable setting using an appropriate combinatorial dimension. We then show that the rate of regre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.09402","kind":"arxiv","version":2},"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/2602.09402/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":"2602.09402","created_at":"2026-06-23T01:13:03.486669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.09402v2","created_at":"2026-06-23T01:13:03.486669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.09402","created_at":"2026-06-23T01:13:03.486669+00:00"},{"alias_kind":"pith_short_12","alias_value":"6IJ6EX56NRLM","created_at":"2026-06-23T01:13:03.486669+00:00"},{"alias_kind":"pith_short_16","alias_value":"6IJ6EX56NRLMSVYQ","created_at":"2026-06-23T01:13:03.486669+00:00"},{"alias_kind":"pith_short_8","alias_value":"6IJ6EX56","created_at":"2026-06-23T01:13:03.486669+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/6IJ6EX56NRLMSVYQ44A5OK4PVW","json":"https://pith.science/pith/6IJ6EX56NRLMSVYQ44A5OK4PVW.json","graph_json":"https://pith.science/api/pith-number/6IJ6EX56NRLMSVYQ44A5OK4PVW/graph.json","events_json":"https://pith.science/api/pith-number/6IJ6EX56NRLMSVYQ44A5OK4PVW/events.json","paper":"https://pith.science/paper/6IJ6EX56"},"agent_actions":{"view_html":"https://pith.science/pith/6IJ6EX56NRLMSVYQ44A5OK4PVW","download_json":"https://pith.science/pith/6IJ6EX56NRLMSVYQ44A5OK4PVW.json","view_paper":"https://pith.science/paper/6IJ6EX56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.09402&json=true","fetch_graph":"https://pith.science/api/pith-number/6IJ6EX56NRLMSVYQ44A5OK4PVW/graph.json","fetch_events":"https://pith.science/api/pith-number/6IJ6EX56NRLMSVYQ44A5OK4PVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6IJ6EX56NRLMSVYQ44A5OK4PVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6IJ6EX56NRLMSVYQ44A5OK4PVW/action/storage_attestation","attest_author":"https://pith.science/pith/6IJ6EX56NRLMSVYQ44A5OK4PVW/action/author_attestation","sign_citation":"https://pith.science/pith/6IJ6EX56NRLMSVYQ44A5OK4PVW/action/citation_signature","submit_replication":"https://pith.science/pith/6IJ6EX56NRLMSVYQ44A5OK4PVW/action/replication_record"}},"created_at":"2026-06-23T01:13:03.486669+00:00","updated_at":"2026-06-23T01:13:03.486669+00:00"}