{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SEEZU6XE22RWLKCM7OU5ELTXEB","short_pith_number":"pith:SEEZU6XE","schema_version":"1.0","canonical_sha256":"91099a7ae4d6a365a84cfba9d22e77205f7c37f4a40593c4f73f3000eeec6e62","source":{"kind":"arxiv","id":"2306.07512","version":1},"attestation_state":"computed","paper":{"title":"Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SI"],"primary_cat":"cs.LG","authors_text":"Baoyu Li, Dachun Sun, Hanghang Tong, Jinning Li, Ruijie Wang, Shengzhong Liu, Tarek F. Abdelzaher, Yichen Lu, Yuchen Yan","submitted_at":"2023-06-13T02:43:21Z","abstract_excerpt":"This paper studies speculative reasoning task on real-world knowledge graphs (KG) that contain both \\textit{false negative issue} (i.e., potential true facts being excluded) and \\textit{false positive issue} (i.e., unreliable or outdated facts being included). State-of-the-art methods fall short in the speculative reasoning ability, as they assume the correctness of a fact is solely determined by its presence in KG, making them vulnerable to false negative/positive issues. The new reasoning task is formulated as a noisy Positive-Unlabeled learning problem. We propose a variational framework, n"},"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":"2306.07512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T02:43:21Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SI"],"title_canon_sha256":"7fcb0c30f81a2ca461d99fa877e196a0f63ca35ec16196181513eaffad02d991","abstract_canon_sha256":"b2e2e1d3da7cbdf3616c17888138283882c7a89f1206bff1c0fd03d1873578ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:05.668221Z","signature_b64":"Layqi8FF6N5jAztBkLNQJtsqgyb6VVz5KKLA3QY2PCLnOWG0pjMTa8RvwukxYe9rPvX0cpGjvLr4KOSWeGKuDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91099a7ae4d6a365a84cfba9d22e77205f7c37f4a40593c4f73f3000eeec6e62","last_reissued_at":"2026-07-05T06:20:05.667763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:05.667763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SI"],"primary_cat":"cs.LG","authors_text":"Baoyu Li, Dachun Sun, Hanghang Tong, Jinning Li, Ruijie Wang, Shengzhong Liu, Tarek F. Abdelzaher, Yichen Lu, Yuchen Yan","submitted_at":"2023-06-13T02:43:21Z","abstract_excerpt":"This paper studies speculative reasoning task on real-world knowledge graphs (KG) that contain both \\textit{false negative issue} (i.e., potential true facts being excluded) and \\textit{false positive issue} (i.e., unreliable or outdated facts being included). State-of-the-art methods fall short in the speculative reasoning ability, as they assume the correctness of a fact is solely determined by its presence in KG, making them vulnerable to false negative/positive issues. The new reasoning task is formulated as a noisy Positive-Unlabeled learning problem. We propose a variational framework, n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07512","kind":"arxiv","version":1},"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/2306.07512/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":"2306.07512","created_at":"2026-07-05T06:20:05.667819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07512v1","created_at":"2026-07-05T06:20:05.667819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07512","created_at":"2026-07-05T06:20:05.667819+00:00"},{"alias_kind":"pith_short_12","alias_value":"SEEZU6XE22RW","created_at":"2026-07-05T06:20:05.667819+00:00"},{"alias_kind":"pith_short_16","alias_value":"SEEZU6XE22RWLKCM","created_at":"2026-07-05T06:20:05.667819+00:00"},{"alias_kind":"pith_short_8","alias_value":"SEEZU6XE","created_at":"2026-07-05T06:20:05.667819+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20858","citing_title":"Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation","ref_index":112,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SEEZU6XE22RWLKCM7OU5ELTXEB","json":"https://pith.science/pith/SEEZU6XE22RWLKCM7OU5ELTXEB.json","graph_json":"https://pith.science/api/pith-number/SEEZU6XE22RWLKCM7OU5ELTXEB/graph.json","events_json":"https://pith.science/api/pith-number/SEEZU6XE22RWLKCM7OU5ELTXEB/events.json","paper":"https://pith.science/paper/SEEZU6XE"},"agent_actions":{"view_html":"https://pith.science/pith/SEEZU6XE22RWLKCM7OU5ELTXEB","download_json":"https://pith.science/pith/SEEZU6XE22RWLKCM7OU5ELTXEB.json","view_paper":"https://pith.science/paper/SEEZU6XE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07512&json=true","fetch_graph":"https://pith.science/api/pith-number/SEEZU6XE22RWLKCM7OU5ELTXEB/graph.json","fetch_events":"https://pith.science/api/pith-number/SEEZU6XE22RWLKCM7OU5ELTXEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SEEZU6XE22RWLKCM7OU5ELTXEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SEEZU6XE22RWLKCM7OU5ELTXEB/action/storage_attestation","attest_author":"https://pith.science/pith/SEEZU6XE22RWLKCM7OU5ELTXEB/action/author_attestation","sign_citation":"https://pith.science/pith/SEEZU6XE22RWLKCM7OU5ELTXEB/action/citation_signature","submit_replication":"https://pith.science/pith/SEEZU6XE22RWLKCM7OU5ELTXEB/action/replication_record"}},"created_at":"2026-07-05T06:20:05.667819+00:00","updated_at":"2026-07-05T06:20:05.667819+00:00"}