{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RNYNQ34S6JQONGC2C6325NTVWZ","short_pith_number":"pith:RNYNQ34S","schema_version":"1.0","canonical_sha256":"8b70d86f92f260e6985a17b7aeb675b64ec8a37d037713e62068dead9e73f97d","source":{"kind":"arxiv","id":"2112.12303","version":2},"attestation_state":"computed","paper":{"title":"Learning with Proper Partial Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaqi Lv, Masashi Sugiyama, Zhenguo Wu","submitted_at":"2021-12-23T01:37:03Z","abstract_excerpt":"Partial-label learning is a kind of weakly-supervised learning with inexact labels, where for each training example, we are given a set of candidate labels instead of only one true label. Recently, various approaches on partial-label learning have been proposed under different generation models of candidate label sets. However, these methods require relatively strong distributional assumptions on the generation models. When the assumptions do not hold, the performance of the methods is not guaranteed theoretically. In this paper, we propose the notion of properness on partial labels. We show t"},"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":"2112.12303","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-23T01:37:03Z","cross_cats_sorted":[],"title_canon_sha256":"030ffbcfb10ce2beb1060aa8de99c7f90ba75bf06439b2ff67efc19c9716958f","abstract_canon_sha256":"c59e53ae78ad4cf9499844999d5076e50cb62897f1cd0fe5271995e19d4fded8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:51:54.066581Z","signature_b64":"A1pe+7P6/ChR+4VItDnZN4UbxY8g6w8fV7xXD9Fwn/n4/htf93pL8PMwJNKA6VrMdl6mplB73RtPdJJwobNjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b70d86f92f260e6985a17b7aeb675b64ec8a37d037713e62068dead9e73f97d","last_reissued_at":"2026-07-05T04:51:54.066157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:51:54.066157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning with Proper Partial Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaqi Lv, Masashi Sugiyama, Zhenguo Wu","submitted_at":"2021-12-23T01:37:03Z","abstract_excerpt":"Partial-label learning is a kind of weakly-supervised learning with inexact labels, where for each training example, we are given a set of candidate labels instead of only one true label. Recently, various approaches on partial-label learning have been proposed under different generation models of candidate label sets. However, these methods require relatively strong distributional assumptions on the generation models. When the assumptions do not hold, the performance of the methods is not guaranteed theoretically. In this paper, we propose the notion of properness on partial labels. We show t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.12303","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/2112.12303/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":"2112.12303","created_at":"2026-07-05T04:51:54.066211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.12303v2","created_at":"2026-07-05T04:51:54.066211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.12303","created_at":"2026-07-05T04:51:54.066211+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNYNQ34S6JQO","created_at":"2026-07-05T04:51:54.066211+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNYNQ34S6JQONGC2","created_at":"2026-07-05T04:51:54.066211+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNYNQ34S","created_at":"2026-07-05T04:51:54.066211+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/RNYNQ34S6JQONGC2C6325NTVWZ","json":"https://pith.science/pith/RNYNQ34S6JQONGC2C6325NTVWZ.json","graph_json":"https://pith.science/api/pith-number/RNYNQ34S6JQONGC2C6325NTVWZ/graph.json","events_json":"https://pith.science/api/pith-number/RNYNQ34S6JQONGC2C6325NTVWZ/events.json","paper":"https://pith.science/paper/RNYNQ34S"},"agent_actions":{"view_html":"https://pith.science/pith/RNYNQ34S6JQONGC2C6325NTVWZ","download_json":"https://pith.science/pith/RNYNQ34S6JQONGC2C6325NTVWZ.json","view_paper":"https://pith.science/paper/RNYNQ34S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.12303&json=true","fetch_graph":"https://pith.science/api/pith-number/RNYNQ34S6JQONGC2C6325NTVWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/RNYNQ34S6JQONGC2C6325NTVWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNYNQ34S6JQONGC2C6325NTVWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNYNQ34S6JQONGC2C6325NTVWZ/action/storage_attestation","attest_author":"https://pith.science/pith/RNYNQ34S6JQONGC2C6325NTVWZ/action/author_attestation","sign_citation":"https://pith.science/pith/RNYNQ34S6JQONGC2C6325NTVWZ/action/citation_signature","submit_replication":"https://pith.science/pith/RNYNQ34S6JQONGC2C6325NTVWZ/action/replication_record"}},"created_at":"2026-07-05T04:51:54.066211+00:00","updated_at":"2026-07-05T04:51:54.066211+00:00"}