{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GISD4YOVPCPW6RCRGQ6J3KDVFQ","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":"c0396511ec16efac224d3fcfafecc85a2be3ada4fffaa886d82afcfdad7b534e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-11T16:48:27Z","title_canon_sha256":"5fcf18b8f59dfe7b79fe5ba8204a5d9dffe675c1fb16eeb260b0d65612602571"},"schema_version":"1.0","source":{"id":"2211.06348","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06348","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06348v1","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06348","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"pith_short_12","alias_value":"GISD4YOVPCPW","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"pith_short_16","alias_value":"GISD4YOVPCPW6RCR","created_at":"2026-07-05T05:15:20Z"},{"alias_kind":"pith_short_8","alias_value":"GISD4YOV","created_at":"2026-07-05T05:15:20Z"}],"graph_snapshots":[{"event_id":"sha256:e2051e3a28c4a7b710c63379a2fbfdd49181360f9e789a28bb7733c8e39a0d28","target":"graph","created_at":"2026-07-05T05:15:20Z","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/2211.06348/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building trustworthy, effective, and responsible machine learning systems hinges on understanding how differences in training data and modeling decisions interact to impact predictive performance. In this work, we seek to better understand how we might characterize, detect, and design for data-model synergies. We focus on a particular type of data-model inefficiency, in which adding training data from some sources can actually lower performance evaluated on key sub-groups of the population, a phenomenon we refer to as negative data externalities on group performance. Such externalities can ari","authors_text":"Alex Beutel, Ben Packer, Esther Rolf, Fernando Diaz","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-11T16:48:27Z","title":"Striving for data-model efficiency: Identifying data externalities on group performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06348","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":"sha256:3d824f2d16b9b10c93ce36360301f7e8923d3ec44d94ddd485ba85632980112f","target":"record","created_at":"2026-07-05T05:15:20Z","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":"c0396511ec16efac224d3fcfafecc85a2be3ada4fffaa886d82afcfdad7b534e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-11T16:48:27Z","title_canon_sha256":"5fcf18b8f59dfe7b79fe5ba8204a5d9dffe675c1fb16eeb260b0d65612602571"},"schema_version":"1.0","source":{"id":"2211.06348","kind":"arxiv","version":1}},"canonical_sha256":"32243e61d5789f6f4451343c9da8752c231992407bb16ea15422e43aab202d22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32243e61d5789f6f4451343c9da8752c231992407bb16ea15422e43aab202d22","first_computed_at":"2026-07-05T05:15:20.026981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:20.026981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wdT+bayOljTGVuIdxDS/1LdDJ3XPpJP7fuVuw4X7T7iC18Vvx8ckyZVl9Bnzm7HGkh36Nmc8FJP9HMpvKkB4Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:20.027368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.06348","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d824f2d16b9b10c93ce36360301f7e8923d3ec44d94ddd485ba85632980112f","sha256:e2051e3a28c4a7b710c63379a2fbfdd49181360f9e789a28bb7733c8e39a0d28"],"state_sha256":"a82f0e317a15f51cb1e6bb5c8ef18b9d06b95c9df373b520e7b429c4d8a8e455"}