{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QOUWHUOE2P64JOEIIZIEIIMEJ2","short_pith_number":"pith:QOUWHUOE","schema_version":"1.0","canonical_sha256":"83a963d1c4d3fdc4b88846504421844ebc03f260283cb8f2f110a9cdbb9bd952","source":{"kind":"arxiv","id":"2408.08981","version":3},"attestation_state":"computed","paper":{"title":"From Lazy to Prolific: Tackling Missing Labels in Open Vocabulary Extreme Classification by Positive-Unlabeled Sequence Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Bensu U\\c{c}ar, Binbin Li, Hansi Wu, Ranran Haoran Zhang, Rui Zhang, Soumik Dey","submitted_at":"2024-08-16T19:10:48Z","abstract_excerpt":"Open-vocabulary Extreme Multi-label Classification (OXMC) extends traditional XMC by allowing prediction beyond an extremely large, predefined label set (typically $10^3$ to $10^{12}$ labels), addressing the dynamic nature of real-world labeling tasks. However, self-selection bias in data annotation leads to significant missing labels in both training and test data, particularly for less popular inputs. This creates two critical challenges: generation models learn to be \"lazy'\" by under-generating labels, and evaluation becomes unreliable due to insufficient annotation in the test set. In this"},"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":"2408.08981","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-16T19:10:48Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"34e18b8de125a7ce1946ead916914c1f686c42c135eb2b8adc26a014e2ae1830","abstract_canon_sha256":"2c780bb599eb9e65a0dc1d9f013186a56f4dffa2e72850f8734346462d6014aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:42.322494Z","signature_b64":"8Ty1ue7ZgpBaHaKuzoHE/svGjhncaS+O2ChU2hkuGPEP+EmLAXZUmJywj2N76ba32OmFUEPFnN93rTnIU/gWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83a963d1c4d3fdc4b88846504421844ebc03f260283cb8f2f110a9cdbb9bd952","last_reissued_at":"2026-07-05T09:58:42.322037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:42.322037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Lazy to Prolific: Tackling Missing Labels in Open Vocabulary Extreme Classification by Positive-Unlabeled Sequence Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Bensu U\\c{c}ar, Binbin Li, Hansi Wu, Ranran Haoran Zhang, Rui Zhang, Soumik Dey","submitted_at":"2024-08-16T19:10:48Z","abstract_excerpt":"Open-vocabulary Extreme Multi-label Classification (OXMC) extends traditional XMC by allowing prediction beyond an extremely large, predefined label set (typically $10^3$ to $10^{12}$ labels), addressing the dynamic nature of real-world labeling tasks. However, self-selection bias in data annotation leads to significant missing labels in both training and test data, particularly for less popular inputs. This creates two critical challenges: generation models learn to be \"lazy'\" by under-generating labels, and evaluation becomes unreliable due to insufficient annotation in the test set. In this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08981","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.08981/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":"2408.08981","created_at":"2026-07-05T09:58:42.322096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08981v3","created_at":"2026-07-05T09:58:42.322096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08981","created_at":"2026-07-05T09:58:42.322096+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOUWHUOE2P64","created_at":"2026-07-05T09:58:42.322096+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOUWHUOE2P64JOEI","created_at":"2026-07-05T09:58:42.322096+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOUWHUOE","created_at":"2026-07-05T09:58:42.322096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00131","citing_title":"Middleman Bias in Advertising: Aligning Relevance of Keyphrase Recommendations with Search","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOUWHUOE2P64JOEIIZIEIIMEJ2","json":"https://pith.science/pith/QOUWHUOE2P64JOEIIZIEIIMEJ2.json","graph_json":"https://pith.science/api/pith-number/QOUWHUOE2P64JOEIIZIEIIMEJ2/graph.json","events_json":"https://pith.science/api/pith-number/QOUWHUOE2P64JOEIIZIEIIMEJ2/events.json","paper":"https://pith.science/paper/QOUWHUOE"},"agent_actions":{"view_html":"https://pith.science/pith/QOUWHUOE2P64JOEIIZIEIIMEJ2","download_json":"https://pith.science/pith/QOUWHUOE2P64JOEIIZIEIIMEJ2.json","view_paper":"https://pith.science/paper/QOUWHUOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08981&json=true","fetch_graph":"https://pith.science/api/pith-number/QOUWHUOE2P64JOEIIZIEIIMEJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/QOUWHUOE2P64JOEIIZIEIIMEJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOUWHUOE2P64JOEIIZIEIIMEJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOUWHUOE2P64JOEIIZIEIIMEJ2/action/storage_attestation","attest_author":"https://pith.science/pith/QOUWHUOE2P64JOEIIZIEIIMEJ2/action/author_attestation","sign_citation":"https://pith.science/pith/QOUWHUOE2P64JOEIIZIEIIMEJ2/action/citation_signature","submit_replication":"https://pith.science/pith/QOUWHUOE2P64JOEIIZIEIIMEJ2/action/replication_record"}},"created_at":"2026-07-05T09:58:42.322096+00:00","updated_at":"2026-07-05T09:58:42.322096+00:00"}