{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WQYFEHR7ZTTLJLQMPZANOVCFBH","short_pith_number":"pith:WQYFEHR7","schema_version":"1.0","canonical_sha256":"b430521e3fcce6b4ae0c7e40d7544509e589d4ab028b1f3e9fc5237fea1ff5fe","source":{"kind":"arxiv","id":"2206.14268","version":3},"attestation_state":"computed","paper":{"title":"BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Ni, Bowen Tan, Eric P. Xing, Hengzhe Zhang, Kaiwen Tang, Shibo Hao, Xiyan Shao, Zhiting Hu","submitted_at":"2022-06-28T19:46:29Z","abstract_excerpt":"It is crucial to automatically construct knowledge graphs (KGs) of diverse new relations to support knowledge discovery and broad applications. Previous KG construction methods, based on either crowdsourcing or text mining, are often limited to a small predefined set of relations due to manual cost or restrictions in text corpus. Recent research proposed to use pretrained language models (LMs) as implicit knowledge bases that accept knowledge queries with prompts. Yet, the implicit knowledge lacks many desirable properties of a full-scale symbolic KG, such as easy access, navigation, editing, "},"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":"2206.14268","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-28T19:46:29Z","cross_cats_sorted":[],"title_canon_sha256":"60463989e6347f7e33b7f6b9ece05a6cf0c1ca7b6e97b17a06c006e5f977bc47","abstract_canon_sha256":"0413cc46dbbaa0e76b6f08fdb2ff4b3e49cab93f26581bb43cc1ac182ab9b991"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:46.634347Z","signature_b64":"pLIvf9TJpbZEgoGNOip0UmWKSerivMnhX5YzmBYtDGzT7Qx3VIV1f59fkGDbCNq+YEzaWlQhl1lr2nCTIRNtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b430521e3fcce6b4ae0c7e40d7544509e589d4ab028b1f3e9fc5237fea1ff5fe","last_reissued_at":"2026-07-05T06:16:46.633817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:46.633817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Ni, Bowen Tan, Eric P. Xing, Hengzhe Zhang, Kaiwen Tang, Shibo Hao, Xiyan Shao, Zhiting Hu","submitted_at":"2022-06-28T19:46:29Z","abstract_excerpt":"It is crucial to automatically construct knowledge graphs (KGs) of diverse new relations to support knowledge discovery and broad applications. Previous KG construction methods, based on either crowdsourcing or text mining, are often limited to a small predefined set of relations due to manual cost or restrictions in text corpus. Recent research proposed to use pretrained language models (LMs) as implicit knowledge bases that accept knowledge queries with prompts. Yet, the implicit knowledge lacks many desirable properties of a full-scale symbolic KG, such as easy access, navigation, editing, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.14268","kind":"arxiv","version":3},"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/2206.14268/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":"2206.14268","created_at":"2026-07-05T06:16:46.633875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.14268v3","created_at":"2026-07-05T06:16:46.633875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.14268","created_at":"2026-07-05T06:16:46.633875+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQYFEHR7ZTTL","created_at":"2026-07-05T06:16:46.633875+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQYFEHR7ZTTLJLQM","created_at":"2026-07-05T06:16:46.633875+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQYFEHR7","created_at":"2026-07-05T06:16:46.633875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19174","citing_title":"Restructure This: Using AI to Restructure Onboarding Documents to Reduce Cognitive Overload","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14169","citing_title":"BOOKMARKS: Efficient Active Storyline Memory for Role-playing","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19137","citing_title":"Construction of Knowledge Graph based on Language Model","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQYFEHR7ZTTLJLQMPZANOVCFBH","json":"https://pith.science/pith/WQYFEHR7ZTTLJLQMPZANOVCFBH.json","graph_json":"https://pith.science/api/pith-number/WQYFEHR7ZTTLJLQMPZANOVCFBH/graph.json","events_json":"https://pith.science/api/pith-number/WQYFEHR7ZTTLJLQMPZANOVCFBH/events.json","paper":"https://pith.science/paper/WQYFEHR7"},"agent_actions":{"view_html":"https://pith.science/pith/WQYFEHR7ZTTLJLQMPZANOVCFBH","download_json":"https://pith.science/pith/WQYFEHR7ZTTLJLQMPZANOVCFBH.json","view_paper":"https://pith.science/paper/WQYFEHR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.14268&json=true","fetch_graph":"https://pith.science/api/pith-number/WQYFEHR7ZTTLJLQMPZANOVCFBH/graph.json","fetch_events":"https://pith.science/api/pith-number/WQYFEHR7ZTTLJLQMPZANOVCFBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQYFEHR7ZTTLJLQMPZANOVCFBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQYFEHR7ZTTLJLQMPZANOVCFBH/action/storage_attestation","attest_author":"https://pith.science/pith/WQYFEHR7ZTTLJLQMPZANOVCFBH/action/author_attestation","sign_citation":"https://pith.science/pith/WQYFEHR7ZTTLJLQMPZANOVCFBH/action/citation_signature","submit_replication":"https://pith.science/pith/WQYFEHR7ZTTLJLQMPZANOVCFBH/action/replication_record"}},"created_at":"2026-07-05T06:16:46.633875+00:00","updated_at":"2026-07-05T06:16:46.633875+00:00"}