{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4VQIM6C6XIWMFA37O3WCM65JTB","short_pith_number":"pith:4VQIM6C6","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"},"canonical_sha256":"e56086785eba2cc2837f76ec267ba99878f68fd47a975f23ce2fd4d8ba6b058f","source":{"kind":"arxiv","id":"2107.09852","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.09852","created_at":"2026-07-05T03:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2107.09852v2","created_at":"2026-07-05T03:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09852","created_at":"2026-07-05T03:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"4VQIM6C6XIWM","created_at":"2026-07-05T03:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"4VQIM6C6XIWMFA37","created_at":"2026-07-05T03:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"4VQIM6C6","created_at":"2026-07-05T03:04:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4VQIM6C6XIWMFA37O3WCM65JTB","target":"record","payload":{"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"},"canonical_sha256":"e56086785eba2cc2837f76ec267ba99878f68fd47a975f23ce2fd4d8ba6b058f","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"},"source_kind":"arxiv","source_id":"2107.09852","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zs2/20OwzndzsbG8gl3voERd3HI3lXJuuFbMvWvoNwgt0MjaChL72oTWiJ8l19+MdH9fQK7ZCxzQL1vAv9ayDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:16:54.326165Z"},"content_sha256":"de8757b00b3dcf37f09f1ddfddbeff26336c46765bd520076ce9bc440b706fb6","schema_version":"1.0","event_id":"sha256:de8757b00b3dcf37f09f1ddfddbeff26336c46765bd520076ce9bc440b706fb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4VQIM6C6XIWMFA37O3WCM65JTB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:04:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IqiEM97lqJJtOZ72QlL2oc+00TD4eXP6QUw483p95fxqjDEfUtR78RBNQxKTswEJVA+XyKbdqXiXd1Rq5I2uAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:16:54.326843Z"},"content_sha256":"a7ade35469ace75ccf5404bf9fa5e242d4521bb7cbd3e4149ea8cae6918a5333","schema_version":"1.0","event_id":"sha256:a7ade35469ace75ccf5404bf9fa5e242d4521bb7cbd3e4149ea8cae6918a5333"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB/bundle.json","state_url":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4VQIM6C6XIWMFA37O3WCM65JTB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T05:16:54Z","links":{"resolver":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB","bundle":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB/bundle.json","state":"https://pith.science/pith/4VQIM6C6XIWMFA37O3WCM65JTB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4VQIM6C6XIWMFA37O3WCM65JTB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4VQIM6C6XIWMFA37O3WCM65JTB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a964c5e2b599af92a7f89f0d49ee64517eb03a16b2490c29d26c5ab6e429915a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-21T02:49:46Z","title_canon_sha256":"e17fad005cce35ded7cc1842f190ddac07a02b30b99ba066920e1357c1b9a1ad"},"schema_version":"1.0","source":{"id":"2107.09852","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.09852","created_at":"2026-07-05T03:04:05Z"},{"alias_kind":"arxiv_version","alias_value":"2107.09852v2","created_at":"2026-07-05T03:04:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.09852","created_at":"2026-07-05T03:04:05Z"},{"alias_kind":"pith_short_12","alias_value":"4VQIM6C6XIWM","created_at":"2026-07-05T03:04:05Z"},{"alias_kind":"pith_short_16","alias_value":"4VQIM6C6XIWMFA37","created_at":"2026-07-05T03:04:05Z"},{"alias_kind":"pith_short_8","alias_value":"4VQIM6C6","created_at":"2026-07-05T03:04:05Z"}],"graph_snapshots":[{"event_id":"sha256:a7ade35469ace75ccf5404bf9fa5e242d4521bb7cbd3e4149ea8cae6918a5333","target":"graph","created_at":"2026-07-05T03:04:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2107.09852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bing Qin, Kuo Liao, Ting Liu, Xiao Ding, Zhongyang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-21T02:49:46Z","title":"CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.09852","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:de8757b00b3dcf37f09f1ddfddbeff26336c46765bd520076ce9bc440b706fb6","target":"record","created_at":"2026-07-05T03:04:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a964c5e2b599af92a7f89f0d49ee64517eb03a16b2490c29d26c5ab6e429915a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-21T02:49:46Z","title_canon_sha256":"e17fad005cce35ded7cc1842f190ddac07a02b30b99ba066920e1357c1b9a1ad"},"schema_version":"1.0","source":{"id":"2107.09852","kind":"arxiv","version":2}},"canonical_sha256":"e56086785eba2cc2837f76ec267ba99878f68fd47a975f23ce2fd4d8ba6b058f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e56086785eba2cc2837f76ec267ba99878f68fd47a975f23ce2fd4d8ba6b058f","first_computed_at":"2026-07-05T03:04:05.976079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:04:05.976079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P+Sd3SpMr4RVgeFto8iUugvaS2hBtG27d+o0ZDfRTiDWVzbR8CNr4MqsYKN8bGJgpjhFHbaQGdSpc3VnD3+ADw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:04:05.976482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.09852","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de8757b00b3dcf37f09f1ddfddbeff26336c46765bd520076ce9bc440b706fb6","sha256:a7ade35469ace75ccf5404bf9fa5e242d4521bb7cbd3e4149ea8cae6918a5333"],"state_sha256":"a6c32d3a3db1a9da6d8c6973483401ad6093bb81a4132c72ac9456beb2b4edfc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Ed4SCdXXj/xMWskZHgcGUshek88BCYnui82g9ZHb5F16TCo+FJSGvl8NUkYYLkBIglO8gocoxN7o8q94oHBCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:16:54.333567Z","bundle_sha256":"ed004cbab5b1e165852606048c9ff4d0849f891b02ea31c60dc79be31344eea7"}}