{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4ZCMPOC2KDJU53OKUGASWPZIL6","short_pith_number":"pith:4ZCMPOC2","schema_version":"1.0","canonical_sha256":"e644c7b85a50d34eedcaa1812b3f285f94c0be34c52321d007634c7c06876739","source":{"kind":"arxiv","id":"2402.19195","version":2},"attestation_state":"computed","paper":{"title":"Negative Sampling in Knowledge Graph Representation Learning: A Review","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ryutaro Ichise, Tiroshan Madushanka","submitted_at":"2024-02-29T14:26:20Z","abstract_excerpt":"Knowledge Graph Representation Learning (KGRL), or Knowledge Graph Embedding (KGE), is essential for AI applications such as knowledge construction and information retrieval. These models encode entities and relations into lower-dimensional vectors, supporting tasks like link prediction and recommendation systems. Training KGE models relies on both positive and negative samples for effective learning, but generating high-quality negative samples from existing knowledge graphs is challenging. The quality of these samples significantly impacts the model's accuracy. This comprehensive survey pape"},"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":"2402.19195","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-29T14:26:20Z","cross_cats_sorted":[],"title_canon_sha256":"1a130b6c86c4b38f1d99695e79da381e87c2e6b55a3c0000636210d8013439f9","abstract_canon_sha256":"7d6e91d8026d53eb5218e29b7ce90e11eae6aa28c0add02d9d58624e13513360"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:03.938541Z","signature_b64":"Mz+YGnt6hX2g26Eq5vUwMv4Rd5+L8AefHFUSKXdWQtD5V1APS1gxkgfTBo4+O8jnTsBpR+aiOVXN/UNGJl0YAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e644c7b85a50d34eedcaa1812b3f285f94c0be34c52321d007634c7c06876739","last_reissued_at":"2026-07-05T09:23:03.938068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:03.938068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Negative Sampling in Knowledge Graph Representation Learning: A Review","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ryutaro Ichise, Tiroshan Madushanka","submitted_at":"2024-02-29T14:26:20Z","abstract_excerpt":"Knowledge Graph Representation Learning (KGRL), or Knowledge Graph Embedding (KGE), is essential for AI applications such as knowledge construction and information retrieval. These models encode entities and relations into lower-dimensional vectors, supporting tasks like link prediction and recommendation systems. Training KGE models relies on both positive and negative samples for effective learning, but generating high-quality negative samples from existing knowledge graphs is challenging. The quality of these samples significantly impacts the model's accuracy. This comprehensive survey pape"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.19195","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/2402.19195/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":"2402.19195","created_at":"2026-07-05T09:23:03.938124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.19195v2","created_at":"2026-07-05T09:23:03.938124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19195","created_at":"2026-07-05T09:23:03.938124+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZCMPOC2KDJU","created_at":"2026-07-05T09:23:03.938124+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZCMPOC2KDJU53OK","created_at":"2026-07-05T09:23:03.938124+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZCMPOC2","created_at":"2026-07-05T09:23:03.938124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.12075","citing_title":"T-TExTS (Teaching Text Expansion for Teacher Scaffolding): Enhancing Text Selection in High School Literature through Knowledge Graph-Based Recommendation","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZCMPOC2KDJU53OKUGASWPZIL6","json":"https://pith.science/pith/4ZCMPOC2KDJU53OKUGASWPZIL6.json","graph_json":"https://pith.science/api/pith-number/4ZCMPOC2KDJU53OKUGASWPZIL6/graph.json","events_json":"https://pith.science/api/pith-number/4ZCMPOC2KDJU53OKUGASWPZIL6/events.json","paper":"https://pith.science/paper/4ZCMPOC2"},"agent_actions":{"view_html":"https://pith.science/pith/4ZCMPOC2KDJU53OKUGASWPZIL6","download_json":"https://pith.science/pith/4ZCMPOC2KDJU53OKUGASWPZIL6.json","view_paper":"https://pith.science/paper/4ZCMPOC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.19195&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZCMPOC2KDJU53OKUGASWPZIL6/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZCMPOC2KDJU53OKUGASWPZIL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZCMPOC2KDJU53OKUGASWPZIL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZCMPOC2KDJU53OKUGASWPZIL6/action/storage_attestation","attest_author":"https://pith.science/pith/4ZCMPOC2KDJU53OKUGASWPZIL6/action/author_attestation","sign_citation":"https://pith.science/pith/4ZCMPOC2KDJU53OKUGASWPZIL6/action/citation_signature","submit_replication":"https://pith.science/pith/4ZCMPOC2KDJU53OKUGASWPZIL6/action/replication_record"}},"created_at":"2026-07-05T09:23:03.938124+00:00","updated_at":"2026-07-05T09:23:03.938124+00:00"}