{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OR6VRC6W2CHS6YUOF6TARF57GI","short_pith_number":"pith:OR6VRC6W","canonical_record":{"source":{"id":"2310.16524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T10:18:44Z","cross_cats_sorted":[],"title_canon_sha256":"159413152dca6c9b1bf0c5eb6d0327fc21f4b00ddb70d48e54c182dbe193d825","abstract_canon_sha256":"00dd812e4db50813243480c92c411b1b6af601fea6d7a4c239d39e257d9fa71d"},"schema_version":"1.0"},"canonical_sha256":"747d588bd6d08f2f628e2fa60897bf321a8f11144cd13ddd32e9676600e28124","source":{"kind":"arxiv","id":"2310.16524","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16524","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16524v1","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16524","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"OR6VRC6W2CHS","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"OR6VRC6W2CHS6YUO","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"OR6VRC6W","created_at":"2026-07-05T07:04:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OR6VRC6W2CHS6YUOF6TARF57GI","target":"record","payload":{"canonical_record":{"source":{"id":"2310.16524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T10:18:44Z","cross_cats_sorted":[],"title_canon_sha256":"159413152dca6c9b1bf0c5eb6d0327fc21f4b00ddb70d48e54c182dbe193d825","abstract_canon_sha256":"00dd812e4db50813243480c92c411b1b6af601fea6d7a4c239d39e257d9fa71d"},"schema_version":"1.0"},"canonical_sha256":"747d588bd6d08f2f628e2fa60897bf321a8f11144cd13ddd32e9676600e28124","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:58.820023Z","signature_b64":"WFc8oFschg+cMZ0BFZhXIgh4TdG93zxRWhHnV+oCOQNJWxWOpH0iWg6tCiYfH2C6HvjWQWpIgLOc2pB/134SAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"747d588bd6d08f2f628e2fa60897bf321a8f11144cd13ddd32e9676600e28124","last_reissued_at":"2026-07-05T07:04:58.819529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:58.819529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.16524","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":"2026-07-05T07:04:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IzbOtK3mk88PmmNtIMcbtxG+6aMyjQEqvNKixutRYC5KGhoUyeZ1joOs43pbDc56O8QsfzcgKItcoClGQlINDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:38:42.348905Z"},"content_sha256":"9a9bfd798918e23181a7edac14b9388c3a5ef652ba4f2b83938f59faf06a32c9","schema_version":"1.0","event_id":"sha256:9a9bfd798918e23181a7edac14b9388c3a5ef652ba4f2b83938f59faf06a32c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OR6VRC6W2CHS6YUOF6TARF57GI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boris van Breugel, Fergus Imrie, Mihaela van der Schaar, Nabeel Seedat","submitted_at":"2023-10-25T10:18:44Z","abstract_excerpt":"Evaluating the performance of machine learning models on diverse and underrepresented subgroups is essential for ensuring fairness and reliability in real-world applications. However, accurately assessing model performance becomes challenging due to two main issues: (1) a scarcity of test data, especially for small subgroups, and (2) possible distributional shifts in the model's deployment setting, which may not align with the available test data. In this work, we introduce 3S Testing, a deep generative modeling framework to facilitate model evaluation by generating synthetic test sets for sma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16524","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/2310.16524/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":"2026-07-05T07:04:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DrMCvp0/W7lN2NUjzOLX3wykzX8IclDFqEgFmb8xqXxjxb9jSN6x8foeXWIoi1QryPcZ6OC+cIsxojxDO/kIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:38:42.349278Z"},"content_sha256":"0b8810a950876d270e128a86bd55a20b8b8559822f621825c8227a9a2f130432","schema_version":"1.0","event_id":"sha256:0b8810a950876d270e128a86bd55a20b8b8559822f621825c8227a9a2f130432"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OR6VRC6W2CHS6YUOF6TARF57GI/bundle.json","state_url":"https://pith.science/pith/OR6VRC6W2CHS6YUOF6TARF57GI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OR6VRC6W2CHS6YUOF6TARF57GI/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":"2026-07-06T18:38:42Z","links":{"resolver":"https://pith.science/pith/OR6VRC6W2CHS6YUOF6TARF57GI","bundle":"https://pith.science/pith/OR6VRC6W2CHS6YUOF6TARF57GI/bundle.json","state":"https://pith.science/pith/OR6VRC6W2CHS6YUOF6TARF57GI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OR6VRC6W2CHS6YUOF6TARF57GI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OR6VRC6W2CHS6YUOF6TARF57GI","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":"00dd812e4db50813243480c92c411b1b6af601fea6d7a4c239d39e257d9fa71d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T10:18:44Z","title_canon_sha256":"159413152dca6c9b1bf0c5eb6d0327fc21f4b00ddb70d48e54c182dbe193d825"},"schema_version":"1.0","source":{"id":"2310.16524","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16524","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16524v1","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16524","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"OR6VRC6W2CHS","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"OR6VRC6W2CHS6YUO","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"OR6VRC6W","created_at":"2026-07-05T07:04:58Z"}],"graph_snapshots":[{"event_id":"sha256:0b8810a950876d270e128a86bd55a20b8b8559822f621825c8227a9a2f130432","target":"graph","created_at":"2026-07-05T07:04:58Z","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/2310.16524/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the performance of machine learning models on diverse and underrepresented subgroups is essential for ensuring fairness and reliability in real-world applications. However, accurately assessing model performance becomes challenging due to two main issues: (1) a scarcity of test data, especially for small subgroups, and (2) possible distributional shifts in the model's deployment setting, which may not align with the available test data. In this work, we introduce 3S Testing, a deep generative modeling framework to facilitate model evaluation by generating synthetic test sets for sma","authors_text":"Boris van Breugel, Fergus Imrie, Mihaela van der Schaar, Nabeel Seedat","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T10:18:44Z","title":"Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16524","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":"sha256:9a9bfd798918e23181a7edac14b9388c3a5ef652ba4f2b83938f59faf06a32c9","target":"record","created_at":"2026-07-05T07:04:58Z","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":"00dd812e4db50813243480c92c411b1b6af601fea6d7a4c239d39e257d9fa71d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T10:18:44Z","title_canon_sha256":"159413152dca6c9b1bf0c5eb6d0327fc21f4b00ddb70d48e54c182dbe193d825"},"schema_version":"1.0","source":{"id":"2310.16524","kind":"arxiv","version":1}},"canonical_sha256":"747d588bd6d08f2f628e2fa60897bf321a8f11144cd13ddd32e9676600e28124","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"747d588bd6d08f2f628e2fa60897bf321a8f11144cd13ddd32e9676600e28124","first_computed_at":"2026-07-05T07:04:58.819529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:58.819529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WFc8oFschg+cMZ0BFZhXIgh4TdG93zxRWhHnV+oCOQNJWxWOpH0iWg6tCiYfH2C6HvjWQWpIgLOc2pB/134SAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:58.820023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16524","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a9bfd798918e23181a7edac14b9388c3a5ef652ba4f2b83938f59faf06a32c9","sha256:0b8810a950876d270e128a86bd55a20b8b8559822f621825c8227a9a2f130432"],"state_sha256":"0c83d64634cd28607fb0b2d0dac0d520130247846028a11fa74da5e35267da9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7SZ4RW7Ioi9tvYQqH5NuzR/AXq9LHZO1eAkH96c+GeHCLhbnlZQqMrCrBgIf9VEPa1UQwfSpKfOBv5eBCHKhAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:38:42.351223Z","bundle_sha256":"29078796096d54e73313b34c529e7332e83f2d04d3e3efabb337f6cf28d52021"}}