{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NXWALO7QNMUO3E2OCPTDKNLZBZ","short_pith_number":"pith:NXWALO7Q","canonical_record":{"source":{"id":"2501.14551","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T14:54:01Z","cross_cats_sorted":[],"title_canon_sha256":"c103bb525c2ca4b33b74f83c8a3f8ee68de7a6d2d81a73534304117a53c6aaa0","abstract_canon_sha256":"a213b437a042375b4da0d73958edba10153fcefc5e9c2c1bcafee144f989f343"},"schema_version":"1.0"},"canonical_sha256":"6dec05bbf06b28ed934e13e63535790e5efb4258e3f7562ecbc16dbe246f6537","source":{"kind":"arxiv","id":"2501.14551","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14551","created_at":"2026-07-05T10:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14551v1","created_at":"2026-07-05T10:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14551","created_at":"2026-07-05T10:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"NXWALO7QNMUO","created_at":"2026-07-05T10:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"NXWALO7QNMUO3E2O","created_at":"2026-07-05T10:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"NXWALO7Q","created_at":"2026-07-05T10:05:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NXWALO7QNMUO3E2OCPTDKNLZBZ","target":"record","payload":{"canonical_record":{"source":{"id":"2501.14551","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T14:54:01Z","cross_cats_sorted":[],"title_canon_sha256":"c103bb525c2ca4b33b74f83c8a3f8ee68de7a6d2d81a73534304117a53c6aaa0","abstract_canon_sha256":"a213b437a042375b4da0d73958edba10153fcefc5e9c2c1bcafee144f989f343"},"schema_version":"1.0"},"canonical_sha256":"6dec05bbf06b28ed934e13e63535790e5efb4258e3f7562ecbc16dbe246f6537","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:02.733211Z","signature_b64":"0ue6FJ3hAKXy7eXdFoNWDJShdsSzj1gG5MEMne9XraXrMDrYSZKHByvYu1yuHnVwQK/0ahh1SjxjAoqsa7GGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dec05bbf06b28ed934e13e63535790e5efb4258e3f7562ecbc16dbe246f6537","last_reissued_at":"2026-07-05T10:05:02.732721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:02.732721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.14551","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":"2026-07-05T10:05:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8GcZxWRTjH97b9r4Lh21Gpajk+9njE831wv3FYdz67vjJkwNmZy0EMynrnmIGJ/JDH+mEtu8EVt37S0vhlTwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:45:25.957026Z"},"content_sha256":"b031b4416592b25a9ce118bddd52b4c61299258ffa25d1b5265341efe0eb0774","schema_version":"1.0","event_id":"sha256:b031b4416592b25a9ce118bddd52b4c61299258ffa25d1b5265341efe0eb0774"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NXWALO7QNMUO3E2OCPTDKNLZBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fairness of Deep Ensembles: On the interplay between per-group task difficulty and under-representation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Diego H. Milone, Enzo Ferrante, Estanislao Claucich, Rodrigo Echeveste, Sara Hooker","submitted_at":"2025-01-24T14:54:01Z","abstract_excerpt":"Ensembling is commonly regarded as an effective way to improve the general performance of models in machine learning, while also increasing the robustness of predictions. When it comes to algorithmic fairness, heterogeneous ensembles, composed of multiple model types, have been employed to mitigate biases in terms of demographic attributes such as sex, age or ethnicity. Moreover, recent work has shown how in multi-class problems even simple homogeneous ensembles may favor performance of the worst-performing target classes. While homogeneous ensembles are simpler to implement in practice, it is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14551","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/2501.14551/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":"2026-07-05T10:05:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E9JvM0jdpnr4jfUO8UUBMYleLJVEMbkLz2ELoJ6BkQp/JHvdxj5xMJ4jenDSjkW3fkjRGOsN7EJMp/LYdnrSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T10:45:25.957783Z"},"content_sha256":"a32787ede3a07599da975bb44d34510ff851900746dfdcc19e03b953dfc3fbd9","schema_version":"1.0","event_id":"sha256:a32787ede3a07599da975bb44d34510ff851900746dfdcc19e03b953dfc3fbd9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NXWALO7QNMUO3E2OCPTDKNLZBZ/bundle.json","state_url":"https://pith.science/pith/NXWALO7QNMUO3E2OCPTDKNLZBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NXWALO7QNMUO3E2OCPTDKNLZBZ/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":"2026-08-11T10:45:25Z","links":{"resolver":"https://pith.science/pith/NXWALO7QNMUO3E2OCPTDKNLZBZ","bundle":"https://pith.science/pith/NXWALO7QNMUO3E2OCPTDKNLZBZ/bundle.json","state":"https://pith.science/pith/NXWALO7QNMUO3E2OCPTDKNLZBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NXWALO7QNMUO3E2OCPTDKNLZBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NXWALO7QNMUO3E2OCPTDKNLZBZ","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":"a213b437a042375b4da0d73958edba10153fcefc5e9c2c1bcafee144f989f343","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T14:54:01Z","title_canon_sha256":"c103bb525c2ca4b33b74f83c8a3f8ee68de7a6d2d81a73534304117a53c6aaa0"},"schema_version":"1.0","source":{"id":"2501.14551","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14551","created_at":"2026-07-05T10:05:02Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14551v1","created_at":"2026-07-05T10:05:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14551","created_at":"2026-07-05T10:05:02Z"},{"alias_kind":"pith_short_12","alias_value":"NXWALO7QNMUO","created_at":"2026-07-05T10:05:02Z"},{"alias_kind":"pith_short_16","alias_value":"NXWALO7QNMUO3E2O","created_at":"2026-07-05T10:05:02Z"},{"alias_kind":"pith_short_8","alias_value":"NXWALO7Q","created_at":"2026-07-05T10:05:02Z"}],"graph_snapshots":[{"event_id":"sha256:a32787ede3a07599da975bb44d34510ff851900746dfdcc19e03b953dfc3fbd9","target":"graph","created_at":"2026-07-05T10:05:02Z","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/2501.14551/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensembling is commonly regarded as an effective way to improve the general performance of models in machine learning, while also increasing the robustness of predictions. When it comes to algorithmic fairness, heterogeneous ensembles, composed of multiple model types, have been employed to mitigate biases in terms of demographic attributes such as sex, age or ethnicity. Moreover, recent work has shown how in multi-class problems even simple homogeneous ensembles may favor performance of the worst-performing target classes. While homogeneous ensembles are simpler to implement in practice, it is","authors_text":"Diego H. Milone, Enzo Ferrante, Estanislao Claucich, Rodrigo Echeveste, Sara Hooker","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T14:54:01Z","title":"Fairness of Deep Ensembles: On the interplay between per-group task difficulty and under-representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14551","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:b031b4416592b25a9ce118bddd52b4c61299258ffa25d1b5265341efe0eb0774","target":"record","created_at":"2026-07-05T10:05:02Z","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":"a213b437a042375b4da0d73958edba10153fcefc5e9c2c1bcafee144f989f343","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T14:54:01Z","title_canon_sha256":"c103bb525c2ca4b33b74f83c8a3f8ee68de7a6d2d81a73534304117a53c6aaa0"},"schema_version":"1.0","source":{"id":"2501.14551","kind":"arxiv","version":1}},"canonical_sha256":"6dec05bbf06b28ed934e13e63535790e5efb4258e3f7562ecbc16dbe246f6537","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6dec05bbf06b28ed934e13e63535790e5efb4258e3f7562ecbc16dbe246f6537","first_computed_at":"2026-07-05T10:05:02.732721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:02.732721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0ue6FJ3hAKXy7eXdFoNWDJShdsSzj1gG5MEMne9XraXrMDrYSZKHByvYu1yuHnVwQK/0ahh1SjxjAoqsa7GGBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:02.733211Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14551","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b031b4416592b25a9ce118bddd52b4c61299258ffa25d1b5265341efe0eb0774","sha256:a32787ede3a07599da975bb44d34510ff851900746dfdcc19e03b953dfc3fbd9"],"state_sha256":"10c6b72937c10ac44c97ff4d1161d7911152e1a40ec7e5b4f3bdc0689b4e26b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KE+SV7T551dcWBJKSL+u4QdPBCC46YnnWDM4Jqh++cxsco6FC44/ynLkzlYaEmaRjV6p1hohLA8meg40ZFfVBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T10:45:25.963433Z","bundle_sha256":"3e92c52417e9a470f240360023d03a010f12cd3d68700958721ac7327b228d56"}}