{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JHBTUS3WTUNAE434OVBEUUWT3C","short_pith_number":"pith:JHBTUS3W","schema_version":"1.0","canonical_sha256":"49c33a4b769d1a02737c75424a52d3d88ced3e7bab6da363774b5083bd9c18fe","source":{"kind":"arxiv","id":"2310.09781","version":1},"attestation_state":"computed","paper":{"title":"Negative Sampling with Adaptive Denoising Mixup for Knowledge Graph Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mingyang Chen, Siliang Tang, Wen Zhang, Xiangnan Chen, Zhen Yao","submitted_at":"2023-10-15T09:01:24Z","abstract_excerpt":"Knowledge graph embedding (KGE) aims to map entities and relations of a knowledge graph (KG) into a low-dimensional and dense vector space via contrasting the positive and negative triples. In the training process of KGEs, negative sampling is essential to find high-quality negative triples since KGs only contain positive triples. Most existing negative sampling methods assume that non-existent triples with high scores are high-quality negative triples. However, negative triples sampled by these methods are likely to contain noise. Specifically, they ignore that non-existent triples with high "},"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":"2310.09781","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-15T09:01:24Z","cross_cats_sorted":[],"title_canon_sha256":"9d172d035105352939977d005bbc6de82fa9fcba36d8d4a9ff7873cb96452ff7","abstract_canon_sha256":"3da9706c378d37ac3eba0c2c9eab24b5cb10970f1ca38551934d5972c6287f13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:10.988483Z","signature_b64":"bq1bxLB26Qb+cHLSDgJUzti8Vwr4de0xOSiVjui5DG8U+ZPvAqpmZt25NNEO5A3mm+xTWc0ZxLnCbG5UDBWdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49c33a4b769d1a02737c75424a52d3d88ced3e7bab6da363774b5083bd9c18fe","last_reissued_at":"2026-07-05T07:01:10.987994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:10.987994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Negative Sampling with Adaptive Denoising Mixup for Knowledge Graph Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Mingyang Chen, Siliang Tang, Wen Zhang, Xiangnan Chen, Zhen Yao","submitted_at":"2023-10-15T09:01:24Z","abstract_excerpt":"Knowledge graph embedding (KGE) aims to map entities and relations of a knowledge graph (KG) into a low-dimensional and dense vector space via contrasting the positive and negative triples. In the training process of KGEs, negative sampling is essential to find high-quality negative triples since KGs only contain positive triples. Most existing negative sampling methods assume that non-existent triples with high scores are high-quality negative triples. However, negative triples sampled by these methods are likely to contain noise. Specifically, they ignore that non-existent triples with high "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09781","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/2310.09781/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":"2310.09781","created_at":"2026-07-05T07:01:10.988043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.09781v1","created_at":"2026-07-05T07:01:10.988043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09781","created_at":"2026-07-05T07:01:10.988043+00:00"},{"alias_kind":"pith_short_12","alias_value":"JHBTUS3WTUNA","created_at":"2026-07-05T07:01:10.988043+00:00"},{"alias_kind":"pith_short_16","alias_value":"JHBTUS3WTUNAE434","created_at":"2026-07-05T07:01:10.988043+00:00"},{"alias_kind":"pith_short_8","alias_value":"JHBTUS3W","created_at":"2026-07-05T07:01:10.988043+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/JHBTUS3WTUNAE434OVBEUUWT3C","json":"https://pith.science/pith/JHBTUS3WTUNAE434OVBEUUWT3C.json","graph_json":"https://pith.science/api/pith-number/JHBTUS3WTUNAE434OVBEUUWT3C/graph.json","events_json":"https://pith.science/api/pith-number/JHBTUS3WTUNAE434OVBEUUWT3C/events.json","paper":"https://pith.science/paper/JHBTUS3W"},"agent_actions":{"view_html":"https://pith.science/pith/JHBTUS3WTUNAE434OVBEUUWT3C","download_json":"https://pith.science/pith/JHBTUS3WTUNAE434OVBEUUWT3C.json","view_paper":"https://pith.science/paper/JHBTUS3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.09781&json=true","fetch_graph":"https://pith.science/api/pith-number/JHBTUS3WTUNAE434OVBEUUWT3C/graph.json","fetch_events":"https://pith.science/api/pith-number/JHBTUS3WTUNAE434OVBEUUWT3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JHBTUS3WTUNAE434OVBEUUWT3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JHBTUS3WTUNAE434OVBEUUWT3C/action/storage_attestation","attest_author":"https://pith.science/pith/JHBTUS3WTUNAE434OVBEUUWT3C/action/author_attestation","sign_citation":"https://pith.science/pith/JHBTUS3WTUNAE434OVBEUUWT3C/action/citation_signature","submit_replication":"https://pith.science/pith/JHBTUS3WTUNAE434OVBEUUWT3C/action/replication_record"}},"created_at":"2026-07-05T07:01:10.988043+00:00","updated_at":"2026-07-05T07:01:10.988043+00:00"}