{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UWMC4VBJTPU52UKXFEOXTGEHTB","short_pith_number":"pith:UWMC4VBJ","schema_version":"1.0","canonical_sha256":"a5982e54299be9dd5157291d799887986197c7cb4c2569e2705fed27d12a4a28","source":{"kind":"arxiv","id":"1910.13339","version":2},"attestation_state":"computed","paper":{"title":"Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alon Jacovi, Gang Niu, Masashi Sugiyama, Yoav Goldberg","submitted_at":"2019-10-29T15:56:33Z","abstract_excerpt":"We consider the situation in which a user has collected a small set of documents on a cohesive topic, and they want to retrieve additional documents on this topic from a large collection. Information Retrieval (IR) solutions treat the document set as a query, and look for similar documents in the collection. We propose to extend the IR approach by treating the problem as an instance of positive-unlabeled (PU) learning -- i.e., learning binary classifiers from only positive and unlabeled data, where the positive data corresponds to the query documents, and the unlabeled data is the results retu"},"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":"1910.13339","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-29T15:56:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b8b4ec2240e351c6503f79eca271013668fcdd49d213d1c59313b89ac6d670d3","abstract_canon_sha256":"62ecdba8174f85969291be5e0332a6f246c04b9f22fc84c1e2bb6cc884e70647"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:07:01.036738Z","signature_b64":"c9ivja2ZHWB0e/jPYvfzylzubJoB8IvctSekdeN8c3yxMfF2iYjxnWBR9NKGJYVPEj5I++oaNjxfCAj6bnpIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5982e54299be9dd5157291d799887986197c7cb4c2569e2705fed27d12a4a28","last_reissued_at":"2026-07-05T02:07:01.036185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:07:01.036185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alon Jacovi, Gang Niu, Masashi Sugiyama, Yoav Goldberg","submitted_at":"2019-10-29T15:56:33Z","abstract_excerpt":"We consider the situation in which a user has collected a small set of documents on a cohesive topic, and they want to retrieve additional documents on this topic from a large collection. Information Retrieval (IR) solutions treat the document set as a query, and look for similar documents in the collection. We propose to extend the IR approach by treating the problem as an instance of positive-unlabeled (PU) learning -- i.e., learning binary classifiers from only positive and unlabeled data, where the positive data corresponds to the query documents, and the unlabeled data is the results retu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.13339","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/1910.13339/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":"1910.13339","created_at":"2026-07-05T02:07:01.036245+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.13339v2","created_at":"2026-07-05T02:07:01.036245+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.13339","created_at":"2026-07-05T02:07:01.036245+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWMC4VBJTPU5","created_at":"2026-07-05T02:07:01.036245+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWMC4VBJTPU52UKX","created_at":"2026-07-05T02:07:01.036245+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWMC4VBJ","created_at":"2026-07-05T02:07:01.036245+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/UWMC4VBJTPU52UKXFEOXTGEHTB","json":"https://pith.science/pith/UWMC4VBJTPU52UKXFEOXTGEHTB.json","graph_json":"https://pith.science/api/pith-number/UWMC4VBJTPU52UKXFEOXTGEHTB/graph.json","events_json":"https://pith.science/api/pith-number/UWMC4VBJTPU52UKXFEOXTGEHTB/events.json","paper":"https://pith.science/paper/UWMC4VBJ"},"agent_actions":{"view_html":"https://pith.science/pith/UWMC4VBJTPU52UKXFEOXTGEHTB","download_json":"https://pith.science/pith/UWMC4VBJTPU52UKXFEOXTGEHTB.json","view_paper":"https://pith.science/paper/UWMC4VBJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.13339&json=true","fetch_graph":"https://pith.science/api/pith-number/UWMC4VBJTPU52UKXFEOXTGEHTB/graph.json","fetch_events":"https://pith.science/api/pith-number/UWMC4VBJTPU52UKXFEOXTGEHTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWMC4VBJTPU52UKXFEOXTGEHTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWMC4VBJTPU52UKXFEOXTGEHTB/action/storage_attestation","attest_author":"https://pith.science/pith/UWMC4VBJTPU52UKXFEOXTGEHTB/action/author_attestation","sign_citation":"https://pith.science/pith/UWMC4VBJTPU52UKXFEOXTGEHTB/action/citation_signature","submit_replication":"https://pith.science/pith/UWMC4VBJTPU52UKXFEOXTGEHTB/action/replication_record"}},"created_at":"2026-07-05T02:07:01.036245+00:00","updated_at":"2026-07-05T02:07:01.036245+00:00"}