{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M7DBRBYWXDJ5Q5S37XWF65QP23","short_pith_number":"pith:M7DBRBYW","schema_version":"1.0","canonical_sha256":"67c6188716b8d3d8765bfdec5f760fd6e4b28977c024ee94d08390bd8e124bba","source":{"kind":"arxiv","id":"2205.02225","version":4},"attestation_state":"computed","paper":{"title":"HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenwei Zhang, Lijie Wen, Philip S. Yu, Shu`ang Li, Shuliang Liu, Xuming Hu","submitted_at":"2022-05-04T17:56:48Z","abstract_excerpt":"Unsupervised relation extraction aims to extract the relationship between entities from natural language sentences without prior information on relational scope or distribution. Existing works either utilize self-supervised schemes to refine relational feature signals by iteratively leveraging adaptive clustering and classification that provoke gradual drift problems, or adopt instance-wise contrastive learning which unreasonably pushes apart those sentence pairs that are semantically similar. To overcome these defects, we propose a novel contrastive learning framework named HiURE, which has t"},"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":"2205.02225","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-04T17:56:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e83a718b31a32e21af0f5993a0653a9716bd00ca7456927a188f6ae1e17eda32","abstract_canon_sha256":"206708d51e5936ba01e81b845d9b26bc66ba6493a35d60d41d2ec82aa7622c14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:13.105442Z","signature_b64":"VJTmFMwaus5yR0c6q/11Mb0lQYxqJoiGt4yBHsyxXIZ2oo2i+o50EbnJ0p9pv/iXF4k1wYUwgoEdXMVJTzmrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67c6188716b8d3d8765bfdec5f760fd6e4b28977c024ee94d08390bd8e124bba","last_reissued_at":"2026-07-05T11:23:13.104924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:13.104924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chenwei Zhang, Lijie Wen, Philip S. Yu, Shu`ang Li, Shuliang Liu, Xuming Hu","submitted_at":"2022-05-04T17:56:48Z","abstract_excerpt":"Unsupervised relation extraction aims to extract the relationship between entities from natural language sentences without prior information on relational scope or distribution. Existing works either utilize self-supervised schemes to refine relational feature signals by iteratively leveraging adaptive clustering and classification that provoke gradual drift problems, or adopt instance-wise contrastive learning which unreasonably pushes apart those sentence pairs that are semantically similar. To overcome these defects, we propose a novel contrastive learning framework named HiURE, which has t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02225","kind":"arxiv","version":4},"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/2205.02225/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":"2205.02225","created_at":"2026-07-05T11:23:13.104982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.02225v4","created_at":"2026-07-05T11:23:13.104982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02225","created_at":"2026-07-05T11:23:13.104982+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7DBRBYWXDJ5","created_at":"2026-07-05T11:23:13.104982+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7DBRBYWXDJ5Q5S3","created_at":"2026-07-05T11:23:13.104982+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7DBRBYW","created_at":"2026-07-05T11:23:13.104982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12424","citing_title":"Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M7DBRBYWXDJ5Q5S37XWF65QP23","json":"https://pith.science/pith/M7DBRBYWXDJ5Q5S37XWF65QP23.json","graph_json":"https://pith.science/api/pith-number/M7DBRBYWXDJ5Q5S37XWF65QP23/graph.json","events_json":"https://pith.science/api/pith-number/M7DBRBYWXDJ5Q5S37XWF65QP23/events.json","paper":"https://pith.science/paper/M7DBRBYW"},"agent_actions":{"view_html":"https://pith.science/pith/M7DBRBYWXDJ5Q5S37XWF65QP23","download_json":"https://pith.science/pith/M7DBRBYWXDJ5Q5S37XWF65QP23.json","view_paper":"https://pith.science/paper/M7DBRBYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.02225&json=true","fetch_graph":"https://pith.science/api/pith-number/M7DBRBYWXDJ5Q5S37XWF65QP23/graph.json","fetch_events":"https://pith.science/api/pith-number/M7DBRBYWXDJ5Q5S37XWF65QP23/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7DBRBYWXDJ5Q5S37XWF65QP23/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7DBRBYWXDJ5Q5S37XWF65QP23/action/storage_attestation","attest_author":"https://pith.science/pith/M7DBRBYWXDJ5Q5S37XWF65QP23/action/author_attestation","sign_citation":"https://pith.science/pith/M7DBRBYWXDJ5Q5S37XWF65QP23/action/citation_signature","submit_replication":"https://pith.science/pith/M7DBRBYWXDJ5Q5S37XWF65QP23/action/replication_record"}},"created_at":"2026-07-05T11:23:13.104982+00:00","updated_at":"2026-07-05T11:23:13.104982+00:00"}