{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TTIOGXLWGWITWXKFLOEF5FHBRM","short_pith_number":"pith:TTIOGXLW","canonical_record":{"source":{"id":"2207.14251","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-28T17:36:24Z","cross_cats_sorted":[],"title_canon_sha256":"4687a2ebb983d76e7d1d7d31ce11059bad0261b98879abaa389299c5d7d0819d","abstract_canon_sha256":"49dc8c9891c80eb68dd0e08c92e5cecc121aa4dfa029621e1c450c7dc2e41a73"},"schema_version":"1.0"},"canonical_sha256":"9cd0e35d7635913b5d455b885e94e18b244b9e0c68b28618b9b8435174e01c0e","source":{"kind":"arxiv","id":"2207.14251","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.14251","created_at":"2026-07-05T05:54:12Z"},{"alias_kind":"arxiv_version","alias_value":"2207.14251v2","created_at":"2026-07-05T05:54:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.14251","created_at":"2026-07-05T05:54:12Z"},{"alias_kind":"pith_short_12","alias_value":"TTIOGXLWGWIT","created_at":"2026-07-05T05:54:12Z"},{"alias_kind":"pith_short_16","alias_value":"TTIOGXLWGWITWXKF","created_at":"2026-07-05T05:54:12Z"},{"alias_kind":"pith_short_8","alias_value":"TTIOGXLW","created_at":"2026-07-05T05:54:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TTIOGXLWGWITWXKFLOEF5FHBRM","target":"record","payload":{"canonical_record":{"source":{"id":"2207.14251","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-28T17:36:24Z","cross_cats_sorted":[],"title_canon_sha256":"4687a2ebb983d76e7d1d7d31ce11059bad0261b98879abaa389299c5d7d0819d","abstract_canon_sha256":"49dc8c9891c80eb68dd0e08c92e5cecc121aa4dfa029621e1c450c7dc2e41a73"},"schema_version":"1.0"},"canonical_sha256":"9cd0e35d7635913b5d455b885e94e18b244b9e0c68b28618b9b8435174e01c0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:12.312076Z","signature_b64":"JRuiqxIYmzeKgQKxecs/eufCoHQBfxi2CfbnR2dfOmC/DPx/eKLa57wO50ZRUZPOcKVoVmR7LKbIYTla1CDfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cd0e35d7635913b5d455b885e94e18b244b9e0c68b28618b9b8435174e01c0e","last_reissued_at":"2026-07-05T05:54:12.311587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:12.311587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.14251","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":"2026-07-05T05:54:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fiwVsHq+ig0/w2vDZd9fO4qWmBZEGStUT6vRgpb4feQdHr25LkZqyK8Kn+7fCjs4c9MZPg47CyCznS2XSUlnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:57:58.376947Z"},"content_sha256":"064387315e10aec97e7bfd50eb849e93485514a4c0c0d4b6db452dc3ddd0711d","schema_version":"1.0","event_id":"sha256:064387315e10aec97e7bfd50eb849e93485514a4c0c0d4b6db452dc3ddd0711d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TTIOGXLWGWITWXKFLOEF5FHBRM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhilasha Ravichander, Amir Feder, Hinrich Sch\\\"utze, Marius Mosbach, Nora Kassner, Shauli Ravfogel, Yanai Elazar, Yoav Goldberg, Yonatan Belinkov","submitted_at":"2022-07-28T17:36:24Z","abstract_excerpt":"Large amounts of training data are one of the major reasons for the high performance of state-of-the-art NLP models. But what exactly in the training data causes a model to make a certain prediction? We seek to answer this question by providing a language for describing how training data influences predictions, through a causal framework. Importantly, our framework bypasses the need to retrain expensive models and allows us to estimate causal effects based on observational data alone. Addressing the problem of extracting factual knowledge from pretrained language models (PLMs), we focus on sim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.14251","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/2207.14251/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":"2026-07-05T05:54:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3pvTf1T/aDXS9tcOkR9wVBxPxBVnkU8dgSS0jYqzlyR/JZWmCsAocDjgQSyhkljMnlox6NuLL2EyToa3d7nmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:57:58.377555Z"},"content_sha256":"17e10f77d34b2517bd17736c519c7213217d3f797edd922527cb1bbab8f02720","schema_version":"1.0","event_id":"sha256:17e10f77d34b2517bd17736c519c7213217d3f797edd922527cb1bbab8f02720"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TTIOGXLWGWITWXKFLOEF5FHBRM/bundle.json","state_url":"https://pith.science/pith/TTIOGXLWGWITWXKFLOEF5FHBRM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TTIOGXLWGWITWXKFLOEF5FHBRM/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":"2026-08-09T23:57:58Z","links":{"resolver":"https://pith.science/pith/TTIOGXLWGWITWXKFLOEF5FHBRM","bundle":"https://pith.science/pith/TTIOGXLWGWITWXKFLOEF5FHBRM/bundle.json","state":"https://pith.science/pith/TTIOGXLWGWITWXKFLOEF5FHBRM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TTIOGXLWGWITWXKFLOEF5FHBRM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TTIOGXLWGWITWXKFLOEF5FHBRM","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":"49dc8c9891c80eb68dd0e08c92e5cecc121aa4dfa029621e1c450c7dc2e41a73","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-28T17:36:24Z","title_canon_sha256":"4687a2ebb983d76e7d1d7d31ce11059bad0261b98879abaa389299c5d7d0819d"},"schema_version":"1.0","source":{"id":"2207.14251","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.14251","created_at":"2026-07-05T05:54:12Z"},{"alias_kind":"arxiv_version","alias_value":"2207.14251v2","created_at":"2026-07-05T05:54:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.14251","created_at":"2026-07-05T05:54:12Z"},{"alias_kind":"pith_short_12","alias_value":"TTIOGXLWGWIT","created_at":"2026-07-05T05:54:12Z"},{"alias_kind":"pith_short_16","alias_value":"TTIOGXLWGWITWXKF","created_at":"2026-07-05T05:54:12Z"},{"alias_kind":"pith_short_8","alias_value":"TTIOGXLW","created_at":"2026-07-05T05:54:12Z"}],"graph_snapshots":[{"event_id":"sha256:17e10f77d34b2517bd17736c519c7213217d3f797edd922527cb1bbab8f02720","target":"graph","created_at":"2026-07-05T05:54:12Z","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/2207.14251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large amounts of training data are one of the major reasons for the high performance of state-of-the-art NLP models. But what exactly in the training data causes a model to make a certain prediction? We seek to answer this question by providing a language for describing how training data influences predictions, through a causal framework. Importantly, our framework bypasses the need to retrain expensive models and allows us to estimate causal effects based on observational data alone. Addressing the problem of extracting factual knowledge from pretrained language models (PLMs), we focus on sim","authors_text":"Abhilasha Ravichander, Amir Feder, Hinrich Sch\\\"utze, Marius Mosbach, Nora Kassner, Shauli Ravfogel, Yanai Elazar, Yoav Goldberg, Yonatan Belinkov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-28T17:36:24Z","title":"Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.14251","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":"sha256:064387315e10aec97e7bfd50eb849e93485514a4c0c0d4b6db452dc3ddd0711d","target":"record","created_at":"2026-07-05T05:54:12Z","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":"49dc8c9891c80eb68dd0e08c92e5cecc121aa4dfa029621e1c450c7dc2e41a73","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-28T17:36:24Z","title_canon_sha256":"4687a2ebb983d76e7d1d7d31ce11059bad0261b98879abaa389299c5d7d0819d"},"schema_version":"1.0","source":{"id":"2207.14251","kind":"arxiv","version":2}},"canonical_sha256":"9cd0e35d7635913b5d455b885e94e18b244b9e0c68b28618b9b8435174e01c0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cd0e35d7635913b5d455b885e94e18b244b9e0c68b28618b9b8435174e01c0e","first_computed_at":"2026-07-05T05:54:12.311587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:12.311587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JRuiqxIYmzeKgQKxecs/eufCoHQBfxi2CfbnR2dfOmC/DPx/eKLa57wO50ZRUZPOcKVoVmR7LKbIYTla1CDfAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:12.312076Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.14251","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:064387315e10aec97e7bfd50eb849e93485514a4c0c0d4b6db452dc3ddd0711d","sha256:17e10f77d34b2517bd17736c519c7213217d3f797edd922527cb1bbab8f02720"],"state_sha256":"e8bdffbf520c3504db75c761694f2ac9bb5a6da0e96a3592f5af68364e2e3a96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0LjAkTCOqLoNJbXNINUIkpjwVS3mpZw5Kj6TlUaKH27+l2Lywr+s7LY92zT1oqIewzqYw9oG3hlasDzebZkSBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:57:58.382772Z","bundle_sha256":"73bfc22eae62a8827db4752b7bb01e7ce9c738624147ad745a5b2fdd0b00c9be"}}