{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ONEQLNJZ3KMEAJCD6WZLGL7O2M","short_pith_number":"pith:ONEQLNJZ","schema_version":"1.0","canonical_sha256":"734905b539da98402443f5b2b32feed32452074c7426d0daa9c0cd1901a99da4","source":{"kind":"arxiv","id":"2210.06242","version":1},"attestation_state":"computed","paper":{"title":"Entity Aware Negative Sampling with Auxiliary Loss of False Negative Prediction for Knowledge Graph Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Sang-hyun Je","submitted_at":"2022-10-12T14:27:51Z","abstract_excerpt":"Knowledge graph (KG) embedding is widely used in many downstream applications using KGs. Generally, since KGs contain only ground truth triples, it is necessary to construct arbitrary negative samples for representation learning of KGs. Recently, various methods for sampling high-quality negatives have been studied because the quality of negative triples has great effect on KG embedding. In this paper, we propose a novel method called Entity Aware Negative Sampling (EANS), which is able to sample negative entities resemble to positive one by adopting Gaussian distribution to the aligned entity"},"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":"2210.06242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T14:27:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9544ca56582e00a9cab9882f5875fa3910f2536603c9e316af5e435a1e74c29d","abstract_canon_sha256":"ff6686dfd3695109cd443b1fc1469ab695dd5dfbd1ce93b8e9f27d1b806aff4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:58.114096Z","signature_b64":"95k7dmVCXH+gqxHQ76qNP1GOf1z83NIQ2M6fMRq2d2asnrGGAEdp5lXZNUncqBJ2b2s42vGSmkkbG4mPdNbGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"734905b539da98402443f5b2b32feed32452074c7426d0daa9c0cd1901a99da4","last_reissued_at":"2026-07-05T05:05:58.113632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:58.113632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entity Aware Negative Sampling with Auxiliary Loss of False Negative Prediction for Knowledge Graph Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Sang-hyun Je","submitted_at":"2022-10-12T14:27:51Z","abstract_excerpt":"Knowledge graph (KG) embedding is widely used in many downstream applications using KGs. Generally, since KGs contain only ground truth triples, it is necessary to construct arbitrary negative samples for representation learning of KGs. Recently, various methods for sampling high-quality negatives have been studied because the quality of negative triples has great effect on KG embedding. In this paper, we propose a novel method called Entity Aware Negative Sampling (EANS), which is able to sample negative entities resemble to positive one by adopting Gaussian distribution to the aligned entity"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06242","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/2210.06242/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":"2210.06242","created_at":"2026-07-05T05:05:58.113690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.06242v1","created_at":"2026-07-05T05:05:58.113690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06242","created_at":"2026-07-05T05:05:58.113690+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONEQLNJZ3KME","created_at":"2026-07-05T05:05:58.113690+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONEQLNJZ3KMEAJCD","created_at":"2026-07-05T05:05:58.113690+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONEQLNJZ","created_at":"2026-07-05T05:05:58.113690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05587","citing_title":"Enhancing PyKEEN with Multiple Negative Sampling Solutions for Knowledge Graph Embedding Models","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONEQLNJZ3KMEAJCD6WZLGL7O2M","json":"https://pith.science/pith/ONEQLNJZ3KMEAJCD6WZLGL7O2M.json","graph_json":"https://pith.science/api/pith-number/ONEQLNJZ3KMEAJCD6WZLGL7O2M/graph.json","events_json":"https://pith.science/api/pith-number/ONEQLNJZ3KMEAJCD6WZLGL7O2M/events.json","paper":"https://pith.science/paper/ONEQLNJZ"},"agent_actions":{"view_html":"https://pith.science/pith/ONEQLNJZ3KMEAJCD6WZLGL7O2M","download_json":"https://pith.science/pith/ONEQLNJZ3KMEAJCD6WZLGL7O2M.json","view_paper":"https://pith.science/paper/ONEQLNJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.06242&json=true","fetch_graph":"https://pith.science/api/pith-number/ONEQLNJZ3KMEAJCD6WZLGL7O2M/graph.json","fetch_events":"https://pith.science/api/pith-number/ONEQLNJZ3KMEAJCD6WZLGL7O2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONEQLNJZ3KMEAJCD6WZLGL7O2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONEQLNJZ3KMEAJCD6WZLGL7O2M/action/storage_attestation","attest_author":"https://pith.science/pith/ONEQLNJZ3KMEAJCD6WZLGL7O2M/action/author_attestation","sign_citation":"https://pith.science/pith/ONEQLNJZ3KMEAJCD6WZLGL7O2M/action/citation_signature","submit_replication":"https://pith.science/pith/ONEQLNJZ3KMEAJCD6WZLGL7O2M/action/replication_record"}},"created_at":"2026-07-05T05:05:58.113690+00:00","updated_at":"2026-07-05T05:05:58.113690+00:00"}