{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:U3CN342BTKWP7IZ4ZRXY43X74I","short_pith_number":"pith:U3CN342B","canonical_record":{"source":{"id":"2406.10366","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T18:47:37Z","cross_cats_sorted":["stat.AP","stat.ME"],"title_canon_sha256":"0a2f01a3a52276fadaa0e384740afa4dbb81e5e79ac72b9149d8363520e5c9bc","abstract_canon_sha256":"b1268d7523297369aaccd28088cba1217b23823d6252597d0b671367ddcdbd7d"},"schema_version":"1.0"},"canonical_sha256":"a6c4ddf3419aacffa33ccc6f8e6effe20b168a8cf48d038f67fa8686318e9c5d","source":{"kind":"arxiv","id":"2406.10366","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10366","created_at":"2026-07-05T08:32:15Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10366v1","created_at":"2026-07-05T08:32:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10366","created_at":"2026-07-05T08:32:15Z"},{"alias_kind":"pith_short_12","alias_value":"U3CN342BTKWP","created_at":"2026-07-05T08:32:15Z"},{"alias_kind":"pith_short_16","alias_value":"U3CN342BTKWP7IZ4","created_at":"2026-07-05T08:32:15Z"},{"alias_kind":"pith_short_8","alias_value":"U3CN342B","created_at":"2026-07-05T08:32:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:U3CN342BTKWP7IZ4ZRXY43X74I","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10366","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T18:47:37Z","cross_cats_sorted":["stat.AP","stat.ME"],"title_canon_sha256":"0a2f01a3a52276fadaa0e384740afa4dbb81e5e79ac72b9149d8363520e5c9bc","abstract_canon_sha256":"b1268d7523297369aaccd28088cba1217b23823d6252597d0b671367ddcdbd7d"},"schema_version":"1.0"},"canonical_sha256":"a6c4ddf3419aacffa33ccc6f8e6effe20b168a8cf48d038f67fa8686318e9c5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:15.660141Z","signature_b64":"TFQ1KRS0tSk3vEl2aRAEEHGj8zaDTTpXG8LdqnIu9x+yHE0DFgN9rbX6YqNOzfnI1nOS/ugyHpfYdQnCRwi2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6c4ddf3419aacffa33ccc6f8e6effe20b168a8cf48d038f67fa8686318e9c5d","last_reissued_at":"2026-07-05T08:32:15.659637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:15.659637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10366","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:32:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1NEGQ5OR85cWMifr5aDmdElnL21iV9WHH/sn9WR4iHqMMRo9qsu42vHpL0eiWbr03eMeK0dHe87Hlp+izscfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:00:14.132460Z"},"content_sha256":"e8108f7b4923e95f94066fd2f28f3463dd7432940fb6cf237d0bf0dbb44dd2fb","schema_version":"1.0","event_id":"sha256:e8108f7b4923e95f94066fd2f28f3463dd7432940fb6cf237d0bf0dbb44dd2fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:U3CN342BTKWP7IZ4ZRXY43X74I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving the Validity and Practical Usefulness of AI/ML Evaluations Using an Estimands Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ME"],"primary_cat":"cs.LG","authors_text":"Jerome P. Reiter, Olivier Binette","submitted_at":"2024-06-14T18:47:37Z","abstract_excerpt":"Commonly, AI or machine learning (ML) models are evaluated on benchmark datasets. This practice supports innovative methodological research, but benchmark performance can be poorly correlated with performance in real-world applications -- a construct validity issue. To improve the validity and practical usefulness of evaluations, we propose using an estimands framework adapted from international clinical trials guidelines. This framework provides a systematic structure for inference and reporting in evaluations, emphasizing the importance of a well-defined estimation target. We illustrate our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10366","kind":"arxiv","version":1},"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/2406.10366/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":"2026-07-05T08:32:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJ81lFXKL/9/0YCTyexqX8kzCcCZSR99jOgw809HjOsgia7TyjcglNVofMqw/WYHYXNB1as+KlP3MqfO7fWtAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:00:14.132987Z"},"content_sha256":"fc5cc99209f4636128d433037530c5de10a4ab6aeb472a70833dcef8b724caf6","schema_version":"1.0","event_id":"sha256:fc5cc99209f4636128d433037530c5de10a4ab6aeb472a70833dcef8b724caf6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U3CN342BTKWP7IZ4ZRXY43X74I/bundle.json","state_url":"https://pith.science/pith/U3CN342BTKWP7IZ4ZRXY43X74I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U3CN342BTKWP7IZ4ZRXY43X74I/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":"2026-08-19T02:00:14Z","links":{"resolver":"https://pith.science/pith/U3CN342BTKWP7IZ4ZRXY43X74I","bundle":"https://pith.science/pith/U3CN342BTKWP7IZ4ZRXY43X74I/bundle.json","state":"https://pith.science/pith/U3CN342BTKWP7IZ4ZRXY43X74I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U3CN342BTKWP7IZ4ZRXY43X74I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U3CN342BTKWP7IZ4ZRXY43X74I","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":"b1268d7523297369aaccd28088cba1217b23823d6252597d0b671367ddcdbd7d","cross_cats_sorted":["stat.AP","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T18:47:37Z","title_canon_sha256":"0a2f01a3a52276fadaa0e384740afa4dbb81e5e79ac72b9149d8363520e5c9bc"},"schema_version":"1.0","source":{"id":"2406.10366","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10366","created_at":"2026-07-05T08:32:15Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10366v1","created_at":"2026-07-05T08:32:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10366","created_at":"2026-07-05T08:32:15Z"},{"alias_kind":"pith_short_12","alias_value":"U3CN342BTKWP","created_at":"2026-07-05T08:32:15Z"},{"alias_kind":"pith_short_16","alias_value":"U3CN342BTKWP7IZ4","created_at":"2026-07-05T08:32:15Z"},{"alias_kind":"pith_short_8","alias_value":"U3CN342B","created_at":"2026-07-05T08:32:15Z"}],"graph_snapshots":[{"event_id":"sha256:fc5cc99209f4636128d433037530c5de10a4ab6aeb472a70833dcef8b724caf6","target":"graph","created_at":"2026-07-05T08:32:15Z","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/2406.10366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Commonly, AI or machine learning (ML) models are evaluated on benchmark datasets. This practice supports innovative methodological research, but benchmark performance can be poorly correlated with performance in real-world applications -- a construct validity issue. To improve the validity and practical usefulness of evaluations, we propose using an estimands framework adapted from international clinical trials guidelines. This framework provides a systematic structure for inference and reporting in evaluations, emphasizing the importance of a well-defined estimation target. We illustrate our ","authors_text":"Jerome P. Reiter, Olivier Binette","cross_cats":["stat.AP","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T18:47:37Z","title":"Improving the Validity and Practical Usefulness of AI/ML Evaluations Using an Estimands Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10366","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:e8108f7b4923e95f94066fd2f28f3463dd7432940fb6cf237d0bf0dbb44dd2fb","target":"record","created_at":"2026-07-05T08:32:15Z","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":"b1268d7523297369aaccd28088cba1217b23823d6252597d0b671367ddcdbd7d","cross_cats_sorted":["stat.AP","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T18:47:37Z","title_canon_sha256":"0a2f01a3a52276fadaa0e384740afa4dbb81e5e79ac72b9149d8363520e5c9bc"},"schema_version":"1.0","source":{"id":"2406.10366","kind":"arxiv","version":1}},"canonical_sha256":"a6c4ddf3419aacffa33ccc6f8e6effe20b168a8cf48d038f67fa8686318e9c5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6c4ddf3419aacffa33ccc6f8e6effe20b168a8cf48d038f67fa8686318e9c5d","first_computed_at":"2026-07-05T08:32:15.659637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:15.659637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TFQ1KRS0tSk3vEl2aRAEEHGj8zaDTTpXG8LdqnIu9x+yHE0DFgN9rbX6YqNOzfnI1nOS/ugyHpfYdQnCRwi2CA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:15.660141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10366","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8108f7b4923e95f94066fd2f28f3463dd7432940fb6cf237d0bf0dbb44dd2fb","sha256:fc5cc99209f4636128d433037530c5de10a4ab6aeb472a70833dcef8b724caf6"],"state_sha256":"6b9961ce9d59b814ad4defb0ae26b502ea63aa7c8a8fcefcb56ce7ac96b82dba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"neG7kr+gbl15EgBQK7h7gVEb15wcuqCeAe1/dYOQgDtTlx7vDZHZAYwq+fiNrWFRwuGJ46hEND4imDJPUCoHCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T02:00:14.137091Z","bundle_sha256":"6cabe49bc2f58241c2219c6aecb12cf4d4e379697b6f9f5add2cb34b741aa6c1"}}