{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C5J6ERRS3BZAXN5KCCWOCXOLGE","short_pith_number":"pith:C5J6ERRS","canonical_record":{"source":{"id":"2401.08702","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2024-01-14T23:19:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8b1f3382b18fbcf9fef3141caea39444c017475baa3d0bf4e88ac9a358e6efca","abstract_canon_sha256":"81bb94245a8ecbcc64843b4e1bdd9f5a86a8604e74b4eeb17d2dd3ebee0a1e81"},"schema_version":"1.0"},"canonical_sha256":"1753e24632d8720bb7aa10ace15dcb3128d8edf13b8cce2980b60e696577117d","source":{"kind":"arxiv","id":"2401.08702","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08702","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08702v2","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08702","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"C5J6ERRS3BZA","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"pith_short_16","alias_value":"C5J6ERRS3BZAXN5K","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"pith_short_8","alias_value":"C5J6ERRS","created_at":"2026-07-05T07:41:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C5J6ERRS3BZAXN5KCCWOCXOLGE","target":"record","payload":{"canonical_record":{"source":{"id":"2401.08702","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2024-01-14T23:19:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8b1f3382b18fbcf9fef3141caea39444c017475baa3d0bf4e88ac9a358e6efca","abstract_canon_sha256":"81bb94245a8ecbcc64843b4e1bdd9f5a86a8604e74b4eeb17d2dd3ebee0a1e81"},"schema_version":"1.0"},"canonical_sha256":"1753e24632d8720bb7aa10ace15dcb3128d8edf13b8cce2980b60e696577117d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:02.236272Z","signature_b64":"JHBXz5y31Ghtir2vDsueBejmm4e6IiSUfm9z1nwAsZKS41yaAZ2OZ6mIYsWkTZ5FJsMLh14oxTwNhIe1XPleCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1753e24632d8720bb7aa10ace15dcb3128d8edf13b8cce2980b60e696577117d","last_reissued_at":"2026-07-05T07:41:02.235782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:02.235782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.08702","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":"2026-07-05T07:41:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HmHiTrzv03JOq2wBQp/CBlQaUSuUk6ZSla3pQznIjPRCHm3Oy9/Dl9hjZFOGY+rWRO1FZmweSoxGWc3UYTHZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:59:34.156392Z"},"content_sha256":"d1fe7326e6d662730695bf0fbb3819ec1d933060efcf225e99a9aa7f18d1138b","schema_version":"1.0","event_id":"sha256:d1fe7326e6d662730695bf0fbb3819ec1d933060efcf225e99a9aa7f18d1138b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C5J6ERRS3BZAXN5KCCWOCXOLGE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do We Really Even Need Data?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Awan Afiaz, Jeffrey T. Leek, Kentaro Hoffman, Stephen Salerno, Tyler H. McCormick","submitted_at":"2024-01-14T23:19:21Z","abstract_excerpt":"As artificial intelligence and machine learning tools become more accessible, and scientists face new obstacles to data collection (e.g. rising costs, declining survey response rates), researchers increasingly use predictions from pre-trained algorithms as outcome variables. Though appealing for financial and logistical reasons, using standard tools for inference can misrepresent the association between independent variables and the outcome of interest when the true, unobserved outcome is replaced by a predicted value. In this paper, we characterize the statistical challenges inherent to this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08702","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/2401.08702/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":"2026-07-05T07:41:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OAdGwhPqwR6do6IrA2KiGOtOF5SP1H1k5VuLyi0r6URtgOwriva5t3lDQvAUmzOqwfXmFCd0nrm9lQAbtf4GDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:59:34.157142Z"},"content_sha256":"9c71e51f82340c81e91c2482e37b4abf92e5c8508d7655e08ada39fb926bb830","schema_version":"1.0","event_id":"sha256:9c71e51f82340c81e91c2482e37b4abf92e5c8508d7655e08ada39fb926bb830"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C5J6ERRS3BZAXN5KCCWOCXOLGE/bundle.json","state_url":"https://pith.science/pith/C5J6ERRS3BZAXN5KCCWOCXOLGE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C5J6ERRS3BZAXN5KCCWOCXOLGE/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":"2026-08-20T12:59:34Z","links":{"resolver":"https://pith.science/pith/C5J6ERRS3BZAXN5KCCWOCXOLGE","bundle":"https://pith.science/pith/C5J6ERRS3BZAXN5KCCWOCXOLGE/bundle.json","state":"https://pith.science/pith/C5J6ERRS3BZAXN5KCCWOCXOLGE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C5J6ERRS3BZAXN5KCCWOCXOLGE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C5J6ERRS3BZAXN5KCCWOCXOLGE","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":"81bb94245a8ecbcc64843b4e1bdd9f5a86a8604e74b4eeb17d2dd3ebee0a1e81","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2024-01-14T23:19:21Z","title_canon_sha256":"8b1f3382b18fbcf9fef3141caea39444c017475baa3d0bf4e88ac9a358e6efca"},"schema_version":"1.0","source":{"id":"2401.08702","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08702","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08702v2","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08702","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"C5J6ERRS3BZA","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"pith_short_16","alias_value":"C5J6ERRS3BZAXN5K","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"pith_short_8","alias_value":"C5J6ERRS","created_at":"2026-07-05T07:41:02Z"}],"graph_snapshots":[{"event_id":"sha256:9c71e51f82340c81e91c2482e37b4abf92e5c8508d7655e08ada39fb926bb830","target":"graph","created_at":"2026-07-05T07:41:02Z","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/2401.08702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As artificial intelligence and machine learning tools become more accessible, and scientists face new obstacles to data collection (e.g. rising costs, declining survey response rates), researchers increasingly use predictions from pre-trained algorithms as outcome variables. Though appealing for financial and logistical reasons, using standard tools for inference can misrepresent the association between independent variables and the outcome of interest when the true, unobserved outcome is replaced by a predicted value. In this paper, we characterize the statistical challenges inherent to this ","authors_text":"Awan Afiaz, Jeffrey T. Leek, Kentaro Hoffman, Stephen Salerno, Tyler H. McCormick","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2024-01-14T23:19:21Z","title":"Do We Really Even Need Data?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08702","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:d1fe7326e6d662730695bf0fbb3819ec1d933060efcf225e99a9aa7f18d1138b","target":"record","created_at":"2026-07-05T07:41:02Z","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":"81bb94245a8ecbcc64843b4e1bdd9f5a86a8604e74b4eeb17d2dd3ebee0a1e81","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2024-01-14T23:19:21Z","title_canon_sha256":"8b1f3382b18fbcf9fef3141caea39444c017475baa3d0bf4e88ac9a358e6efca"},"schema_version":"1.0","source":{"id":"2401.08702","kind":"arxiv","version":2}},"canonical_sha256":"1753e24632d8720bb7aa10ace15dcb3128d8edf13b8cce2980b60e696577117d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1753e24632d8720bb7aa10ace15dcb3128d8edf13b8cce2980b60e696577117d","first_computed_at":"2026-07-05T07:41:02.235782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:02.235782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JHBXz5y31Ghtir2vDsueBejmm4e6IiSUfm9z1nwAsZKS41yaAZ2OZ6mIYsWkTZ5FJsMLh14oxTwNhIe1XPleCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:02.236272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.08702","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1fe7326e6d662730695bf0fbb3819ec1d933060efcf225e99a9aa7f18d1138b","sha256:9c71e51f82340c81e91c2482e37b4abf92e5c8508d7655e08ada39fb926bb830"],"state_sha256":"2df2c06aa87da970bf8f9e082abefd4dc18cadf378a27dcae87ceddd8f00db95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ugjr2+LxzUbqjRzdSZy64n71woDQwZtQLocgAQRIlRRAb8TszpDEiKdEA81aDKGGqgFj+lUdz/Nbk2N0g8JRBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T12:59:34.164375Z","bundle_sha256":"78319ac46bfe0aaeaa779ee31ad6484c2b5917685e5ca083366ba3f0f7230603"}}