{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UWMC4VBJTPU52UKXFEOXTGEHTB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"62ecdba8174f85969291be5e0332a6f246c04b9f22fc84c1e2bb6cc884e70647","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-29T15:56:33Z","title_canon_sha256":"b8b4ec2240e351c6503f79eca271013668fcdd49d213d1c59313b89ac6d670d3"},"schema_version":"1.0","source":{"id":"1910.13339","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.13339","created_at":"2026-07-05T02:07:01Z"},{"alias_kind":"arxiv_version","alias_value":"1910.13339v2","created_at":"2026-07-05T02:07:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.13339","created_at":"2026-07-05T02:07:01Z"},{"alias_kind":"pith_short_12","alias_value":"UWMC4VBJTPU5","created_at":"2026-07-05T02:07:01Z"},{"alias_kind":"pith_short_16","alias_value":"UWMC4VBJTPU52UKX","created_at":"2026-07-05T02:07:01Z"},{"alias_kind":"pith_short_8","alias_value":"UWMC4VBJ","created_at":"2026-07-05T02:07:01Z"}],"graph_snapshots":[{"event_id":"sha256:c90e98632c4bc0b5e5f86142f49d2511c51cfb5978d5bef2b4d82fffb6d5ae2b","target":"graph","created_at":"2026-07-05T02:07:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1910.13339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alon Jacovi, Gang Niu, Masashi Sugiyama, Yoav Goldberg","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-29T15:56:33Z","title":"Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.13339","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3da21ae576a22fae274044db4ee97b6c2d261e5fcc563a7b3715bb74d270ebc0","target":"record","created_at":"2026-07-05T02:07:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"62ecdba8174f85969291be5e0332a6f246c04b9f22fc84c1e2bb6cc884e70647","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-29T15:56:33Z","title_canon_sha256":"b8b4ec2240e351c6503f79eca271013668fcdd49d213d1c59313b89ac6d670d3"},"schema_version":"1.0","source":{"id":"1910.13339","kind":"arxiv","version":2}},"canonical_sha256":"a5982e54299be9dd5157291d799887986197c7cb4c2569e2705fed27d12a4a28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5982e54299be9dd5157291d799887986197c7cb4c2569e2705fed27d12a4a28","first_computed_at":"2026-07-05T02:07:01.036185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:07:01.036185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c9ivja2ZHWB0e/jPYvfzylzubJoB8IvctSekdeN8c3yxMfF2iYjxnWBR9NKGJYVPEj5I++oaNjxfCAj6bnpIBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:07:01.036738Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.13339","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3da21ae576a22fae274044db4ee97b6c2d261e5fcc563a7b3715bb74d270ebc0","sha256:c90e98632c4bc0b5e5f86142f49d2511c51cfb5978d5bef2b4d82fffb6d5ae2b"],"state_sha256":"f69a7cb50387b3e026e1cf7446426c38e691575d4f5241957a2af47bf6a7c947"}