{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PS5VT4CVCKRSFFXY5EHEFMUXSS","short_pith_number":"pith:PS5VT4CV","schema_version":"1.0","canonical_sha256":"7cbb59f05512a32296f8e90e42b29794869256306b83f77d5fe7fcc4347b3335","source":{"kind":"arxiv","id":"2201.06225","version":2},"attestation_state":"computed","paper":{"title":"Interactive Contrastive Learning for Self-supervised Entity Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jifan Yu, Juanzi Li, Kaisheng Zeng, Lei Hou, Ling Feng, Minghao Hu, Xin Lv, Yixin Cao, Zhenhao Dong","submitted_at":"2022-01-17T06:04:00Z","abstract_excerpt":"Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without seed alignments. The current SOTA self-supervised EA method draws inspiration from contrastive learning, originally designed in computer vision based on instance discrimination and contrastive loss, and suffers from two shortcomings. Firstly, it puts unidirectional emphasis on pushing sampled negative entities far away rather than pulling positively aligned pairs close, as is done in the well-established supervised EA. Secondly, KGs contain rich side information (e.g., 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":"2201.06225","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-17T06:04:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"47a45bbf7cba38bf93f721133bfb46ab5532613acdb458420fb8f4561e53bdcd","abstract_canon_sha256":"2255d9e1e2e4723f8d350faed788411b84bfcf06ed30dec4ff3b8d33212a8fd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:46.724172Z","signature_b64":"XLTV5qFc2afD5Iu5kdeWITzPYp+9q46AmSEffqUyiO2na8Ks9WphLyDis7KitxzEuSs9GOwBhVbnWc0BWStRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cbb59f05512a32296f8e90e42b29794869256306b83f77d5fe7fcc4347b3335","last_reissued_at":"2026-07-05T05:04:46.723748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:46.723748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Contrastive Learning for Self-supervised Entity Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jifan Yu, Juanzi Li, Kaisheng Zeng, Lei Hou, Ling Feng, Minghao Hu, Xin Lv, Yixin Cao, Zhenhao Dong","submitted_at":"2022-01-17T06:04:00Z","abstract_excerpt":"Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without seed alignments. The current SOTA self-supervised EA method draws inspiration from contrastive learning, originally designed in computer vision based on instance discrimination and contrastive loss, and suffers from two shortcomings. Firstly, it puts unidirectional emphasis on pushing sampled negative entities far away rather than pulling positively aligned pairs close, as is done in the well-established supervised EA. Secondly, KGs contain rich side information (e.g., entity "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06225","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/2201.06225/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":"2201.06225","created_at":"2026-07-05T05:04:46.723812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.06225v2","created_at":"2026-07-05T05:04:46.723812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06225","created_at":"2026-07-05T05:04:46.723812+00:00"},{"alias_kind":"pith_short_12","alias_value":"PS5VT4CVCKRS","created_at":"2026-07-05T05:04:46.723812+00:00"},{"alias_kind":"pith_short_16","alias_value":"PS5VT4CVCKRSFFXY","created_at":"2026-07-05T05:04:46.723812+00:00"},{"alias_kind":"pith_short_8","alias_value":"PS5VT4CV","created_at":"2026-07-05T05:04:46.723812+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/PS5VT4CVCKRSFFXY5EHEFMUXSS","json":"https://pith.science/pith/PS5VT4CVCKRSFFXY5EHEFMUXSS.json","graph_json":"https://pith.science/api/pith-number/PS5VT4CVCKRSFFXY5EHEFMUXSS/graph.json","events_json":"https://pith.science/api/pith-number/PS5VT4CVCKRSFFXY5EHEFMUXSS/events.json","paper":"https://pith.science/paper/PS5VT4CV"},"agent_actions":{"view_html":"https://pith.science/pith/PS5VT4CVCKRSFFXY5EHEFMUXSS","download_json":"https://pith.science/pith/PS5VT4CVCKRSFFXY5EHEFMUXSS.json","view_paper":"https://pith.science/paper/PS5VT4CV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.06225&json=true","fetch_graph":"https://pith.science/api/pith-number/PS5VT4CVCKRSFFXY5EHEFMUXSS/graph.json","fetch_events":"https://pith.science/api/pith-number/PS5VT4CVCKRSFFXY5EHEFMUXSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PS5VT4CVCKRSFFXY5EHEFMUXSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PS5VT4CVCKRSFFXY5EHEFMUXSS/action/storage_attestation","attest_author":"https://pith.science/pith/PS5VT4CVCKRSFFXY5EHEFMUXSS/action/author_attestation","sign_citation":"https://pith.science/pith/PS5VT4CVCKRSFFXY5EHEFMUXSS/action/citation_signature","submit_replication":"https://pith.science/pith/PS5VT4CVCKRSFFXY5EHEFMUXSS/action/replication_record"}},"created_at":"2026-07-05T05:04:46.723812+00:00","updated_at":"2026-07-05T05:04:46.723812+00:00"}