{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7SFQHVOGGFLJA4P4WEGJGXJLEZ","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":"be86856608b2701bc84d4660f053bfb6f3745f7c7af6539bff4b6dab43be38c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-31T02:01:26Z","title_canon_sha256":"4c9c9220e7de2ea668cab75b7a8dbd44ab30725a79f91c3e0c717663d7277903"},"schema_version":"1.0","source":{"id":"2203.16747","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16747","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16747v1","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16747","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"7SFQHVOGGFLJ","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"7SFQHVOGGFLJA4P4","created_at":"2026-07-05T04:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"7SFQHVOG","created_at":"2026-07-05T04:10:15Z"}],"graph_snapshots":[{"event_id":"sha256:9daa61d41b193f2409899a6ee2c047086bdb3c4f941bc830f5f8f7a62201f99d","target":"graph","created_at":"2026-07-05T04:10:15Z","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/2203.16747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, there has been a trend to investigate the factual knowledge captured by Pre-trained Language Models (PLMs). Many works show the PLMs' ability to fill in the missing factual words in cloze-style prompts such as \"Dante was born in [MASK].\" However, it is still a mystery how PLMs generate the results correctly: relying on effective clues or shortcut patterns? We try to answer this question by a causal-inspired analysis that quantitatively measures and evaluates the word-level patterns that PLMs depend on to generate the missing words. We check the words that have three typical associati","authors_text":"Bingquan Liu, Chengjie Sun, Lifeng Shang, Qun Liu, Shaobo Li, Xiaoguang Li, Xin Jiang, Zhenhua Dong, Zhenzhou Ji","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-31T02:01:26Z","title":"How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16747","kind":"arxiv","version":1},"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":"sha256:6f8986f9997f44b05dcc30cf8635661642141ac423031c1f2127a8b25840a434","target":"record","created_at":"2026-07-05T04:10:15Z","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":"be86856608b2701bc84d4660f053bfb6f3745f7c7af6539bff4b6dab43be38c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-31T02:01:26Z","title_canon_sha256":"4c9c9220e7de2ea668cab75b7a8dbd44ab30725a79f91c3e0c717663d7277903"},"schema_version":"1.0","source":{"id":"2203.16747","kind":"arxiv","version":1}},"canonical_sha256":"fc8b03d5c631569071fcb10c935d2b264391dfb6550751febf63811d10f93cd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc8b03d5c631569071fcb10c935d2b264391dfb6550751febf63811d10f93cd1","first_computed_at":"2026-07-05T04:10:15.793868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:15.793868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sBPUH/LRmLd7SqbcN9FzJV2gnFJxTlIL2XUQSDcm9TfA0WPZjrROI+up9hF66gRqeAXh7hOTX2fXx+IxswMoCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:15.794339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.16747","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f8986f9997f44b05dcc30cf8635661642141ac423031c1f2127a8b25840a434","sha256:9daa61d41b193f2409899a6ee2c047086bdb3c4f941bc830f5f8f7a62201f99d"],"state_sha256":"c4442476cad1e75195351e95252406573af5d0f267a99f2109f2f1b2e38bbf6e"}