{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HCXWDX2NZKG6DP5CJIGWUTJ7KY","short_pith_number":"pith:HCXWDX2N","schema_version":"1.0","canonical_sha256":"38af61df4dca8de1bfa24a0d6a4d3f563d7d0a46e1d39a61d6f4b8bb8ba6ae34","source":{"kind":"arxiv","id":"2306.02622","version":1},"attestation_state":"computed","paper":{"title":"What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jiacheng Huang, Qijin Chen, Wei Hu, Weijun Ren, Xiaozhou Xu, Zequn Sun","submitted_at":"2023-06-05T06:50:09Z","abstract_excerpt":"Joint representation learning over multi-sourced knowledge graphs (KGs) yields transferable and expressive embeddings that improve downstream tasks. Entity alignment (EA) is a critical step in this process. Despite recent considerable research progress in embedding-based EA, how it works remains to be explored. In this paper, we provide a similarity flooding perspective to explain existing translation-based and aggregation-based EA models. We prove that the embedding learning process of these models actually seeks a fixpoint of pairwise similarities between entities. We also provide experiment"},"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":"2306.02622","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-05T06:50:09Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0bc148713d51525dadeffd34785dc834861ef6e835a755330eb5be6fcb84261c","abstract_canon_sha256":"2358c53815a4d21603afebec4ede2657e2afb82708c81c6f79b8960d8c769771"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:19.731147Z","signature_b64":"5tVFVtnH2kcBnnn22LohoJXVLXxu/3kcHRjI/IAVOM9tCl91jZ9XzhTe6eEiP5Y4xU+miQkUq2cPEt2U/a71CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38af61df4dca8de1bfa24a0d6a4d3f563d7d0a46e1d39a61d6f4b8bb8ba6ae34","last_reissued_at":"2026-07-05T06:17:19.730606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:19.730606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Jiacheng Huang, Qijin Chen, Wei Hu, Weijun Ren, Xiaozhou Xu, Zequn Sun","submitted_at":"2023-06-05T06:50:09Z","abstract_excerpt":"Joint representation learning over multi-sourced knowledge graphs (KGs) yields transferable and expressive embeddings that improve downstream tasks. Entity alignment (EA) is a critical step in this process. Despite recent considerable research progress in embedding-based EA, how it works remains to be explored. In this paper, we provide a similarity flooding perspective to explain existing translation-based and aggregation-based EA models. We prove that the embedding learning process of these models actually seeks a fixpoint of pairwise similarities between entities. We also provide experiment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02622","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/2306.02622/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":"2306.02622","created_at":"2026-07-05T06:17:19.730667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02622v1","created_at":"2026-07-05T06:17:19.730667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02622","created_at":"2026-07-05T06:17:19.730667+00:00"},{"alias_kind":"pith_short_12","alias_value":"HCXWDX2NZKG6","created_at":"2026-07-05T06:17:19.730667+00:00"},{"alias_kind":"pith_short_16","alias_value":"HCXWDX2NZKG6DP5C","created_at":"2026-07-05T06:17:19.730667+00:00"},{"alias_kind":"pith_short_8","alias_value":"HCXWDX2N","created_at":"2026-07-05T06:17:19.730667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28308","citing_title":"HELEA: Hard-Negative Benchmark and LLM-based Reranking for Robust Entity Alignment","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HCXWDX2NZKG6DP5CJIGWUTJ7KY","json":"https://pith.science/pith/HCXWDX2NZKG6DP5CJIGWUTJ7KY.json","graph_json":"https://pith.science/api/pith-number/HCXWDX2NZKG6DP5CJIGWUTJ7KY/graph.json","events_json":"https://pith.science/api/pith-number/HCXWDX2NZKG6DP5CJIGWUTJ7KY/events.json","paper":"https://pith.science/paper/HCXWDX2N"},"agent_actions":{"view_html":"https://pith.science/pith/HCXWDX2NZKG6DP5CJIGWUTJ7KY","download_json":"https://pith.science/pith/HCXWDX2NZKG6DP5CJIGWUTJ7KY.json","view_paper":"https://pith.science/paper/HCXWDX2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02622&json=true","fetch_graph":"https://pith.science/api/pith-number/HCXWDX2NZKG6DP5CJIGWUTJ7KY/graph.json","fetch_events":"https://pith.science/api/pith-number/HCXWDX2NZKG6DP5CJIGWUTJ7KY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HCXWDX2NZKG6DP5CJIGWUTJ7KY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HCXWDX2NZKG6DP5CJIGWUTJ7KY/action/storage_attestation","attest_author":"https://pith.science/pith/HCXWDX2NZKG6DP5CJIGWUTJ7KY/action/author_attestation","sign_citation":"https://pith.science/pith/HCXWDX2NZKG6DP5CJIGWUTJ7KY/action/citation_signature","submit_replication":"https://pith.science/pith/HCXWDX2NZKG6DP5CJIGWUTJ7KY/action/replication_record"}},"created_at":"2026-07-05T06:17:19.730667+00:00","updated_at":"2026-07-05T06:17:19.730667+00:00"}