{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4VQIM6C6XIWMFA37O3WCM65JTB","short_pith_number":"pith:4VQIM6C6","schema_version":"1.0","canonical_sha256":"e56086785eba2cc2837f76ec267ba99878f68fd47a975f23ce2fd4d8ba6b058f","source":{"kind":"arxiv","id":"2107.09852","version":2},"attestation_state":"computed","paper":{"title":"CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, Kuo Liao, Ting Liu, Xiao Ding, Zhongyang Li","submitted_at":"2021-07-21T02:49:46Z","abstract_excerpt":"Recent work has shown success in incorporating pre-trained models like BERT to improve NLP systems. However, existing pre-trained models lack of causal knowledge which prevents today's NLP systems from thinking like humans. In this paper, we investigate the problem of injecting causal knowledge into pre-trained models. There are two fundamental problems: 1) how to collect various granularities of causal pairs from unstructured texts; 2) how to effectively inject causal knowledge into pre-trained models. To address these issues, we extend the idea of CausalBERT from previous studies, and conduc"},"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":"2107.09852","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-21T02:49:46Z","cross_cats_sorted":[],"title_canon_sha256":"e17fad005cce35ded7cc1842f190ddac07a02b30b99ba066920e1357c1b9a1ad","abstract_canon_sha256":"a964c5e2b599af92a7f89f0d49ee64517eb03a16b2490c29d26c5ab6e429915a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:05.976482Z","signature_b64":"P+Sd3SpMr4RVgeFto8iUugvaS2hBtG27d+o0ZDfRTiDWVzbR8CNr4MqsYKN8bGJgpjhFHbaQGdSpc3VnD3+ADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e56086785eba2cc2837f76ec267ba99878f68fd47a975f23ce2fd4d8ba6b058f","last_reissued_at":"2026-07-05T03:04:05.976079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:05.976079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, Kuo Liao, Ting Liu, Xiao Ding, Zhongyang Li","submitted_at":"2021-07-21T02:49:46Z","abstract_excerpt":"Recent work has shown success in incorporating pre-trained models like BERT to improve NLP systems. However, existing pre-trained models lack of causal knowledge which prevents today's NLP systems from thinking like humans. In this paper, we investigate the problem of injecting causal knowledge into pre-trained models. There are two fundamental problems: 1) how to collect various granularities of causal pairs from unstructured texts; 2) how to effectively inject causal knowledge into pre-trained models. To address these issues, we extend the idea of CausalBERT from previous studies, and conduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09852","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/2107.09852/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":"2107.09852","created_at":"2026-07-05T03:04:05.976144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.09852v2","created_at":"2026-07-05T03:04:05.976144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09852","created_at":"2026-07-05T03:04:05.976144+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VQIM6C6XIWM","created_at":"2026-07-05T03:04:05.976144+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VQIM6C6XIWMFA37","created_at":"2026-07-05T03:04:05.976144+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VQIM6C6","created_at":"2026-07-05T03:04:05.976144+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05675","citing_title":"Zero-Shot Event Causality Identification via Multi-source Evidence Fuzzy Aggregation with Large Language Models","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB","json":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB.json","graph_json":"https://pith.science/api/pith-number/4VQIM6C6XIWMFA37O3WCM65JTB/graph.json","events_json":"https://pith.science/api/pith-number/4VQIM6C6XIWMFA37O3WCM65JTB/events.json","paper":"https://pith.science/paper/4VQIM6C6"},"agent_actions":{"view_html":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB","download_json":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB.json","view_paper":"https://pith.science/paper/4VQIM6C6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.09852&json=true","fetch_graph":"https://pith.science/api/pith-number/4VQIM6C6XIWMFA37O3WCM65JTB/graph.json","fetch_events":"https://pith.science/api/pith-number/4VQIM6C6XIWMFA37O3WCM65JTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB/action/storage_attestation","attest_author":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB/action/author_attestation","sign_citation":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB/action/citation_signature","submit_replication":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB/action/replication_record"}},"created_at":"2026-07-05T03:04:05.976144+00:00","updated_at":"2026-07-05T03:04:05.976144+00:00"}