{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W6KFRXZJEDC7ULN3KEY364MXG5","short_pith_number":"pith:W6KFRXZJ","canonical_record":{"source":{"id":"2408.04154","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-08T01:42:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"583c1c6469be98a916b582f868a61ac8b97b4bfb841c3dd1c05cd426cbdc203b","abstract_canon_sha256":"9a326f1f502ef126aa0e732c6119f1d193b5c2e93162f021c1d8cd02c3386ada"},"schema_version":"1.0"},"canonical_sha256":"b79458df2920c5fa2dbb5131bf7197377ea2d301e7927fe17b6f8d50190a639f","source":{"kind":"arxiv","id":"2408.04154","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04154","created_at":"2026-07-05T08:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04154v1","created_at":"2026-07-05T08:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04154","created_at":"2026-07-05T08:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"W6KFRXZJEDC7","created_at":"2026-07-05T08:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"W6KFRXZJEDC7ULN3","created_at":"2026-07-05T08:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"W6KFRXZJ","created_at":"2026-07-05T08:53:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W6KFRXZJEDC7ULN3KEY364MXG5","target":"record","payload":{"canonical_record":{"source":{"id":"2408.04154","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-08T01:42:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"583c1c6469be98a916b582f868a61ac8b97b4bfb841c3dd1c05cd426cbdc203b","abstract_canon_sha256":"9a326f1f502ef126aa0e732c6119f1d193b5c2e93162f021c1d8cd02c3386ada"},"schema_version":"1.0"},"canonical_sha256":"b79458df2920c5fa2dbb5131bf7197377ea2d301e7927fe17b6f8d50190a639f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:28.762241Z","signature_b64":"XFOwyzyDRAzPpMxNBarjqXchKCKklxhh76cDBZUcqDKO2C8sHBaM3yXas7b24opf5VnaZCsiefvVEsNplbMECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b79458df2920c5fa2dbb5131bf7197377ea2d301e7927fe17b6f8d50190a639f","last_reissued_at":"2026-07-05T08:53:28.761831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:28.761831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.04154","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":"2026-07-05T08:53:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dUiUNt39o/h2wms25Cu5+IBBY3kcsfK1xEPaiT671gcr+Fr0Hsf1ucnX+atFicMEhu9ELwzi5Xfwr+YAc1/cBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:10:34.491674Z"},"content_sha256":"05547db3b6d82376548d62bba5a2703df0c368b53587ea4bb0c198e6a412549c","schema_version":"1.0","event_id":"sha256:05547db3b6d82376548d62bba5a2703df0c368b53587ea4bb0c198e6a412549c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W6KFRXZJEDC7ULN3KEY364MXG5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Data Addition Dilemma","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Inioluwa Deborah Raji, Irene Y. Chen, Judy Hanwen Shen","submitted_at":"2024-08-08T01:42:31Z","abstract_excerpt":"In many machine learning for healthcare tasks, standard datasets are constructed by amassing data across many, often fundamentally dissimilar, sources. But when does adding more data help, and when does it hinder progress on desired model outcomes in real-world settings? We identify this situation as the \\textit{Data Addition Dilemma}, demonstrating that adding training data in this multi-source scaling context can at times result in reduced overall accuracy, uncertain fairness outcomes, and reduced worst-subgroup performance. We find that this possibly arises from an empirically observed trad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04154","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/2408.04154/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":"2026-07-05T08:53:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rLT+WZ8K4Xi4TBmkiROJY+FQjjsZTeYkLoXe/BNV4KY5ZjI0lvyskzFrtRS+G0XMJL67bSKzD3H/mlNO/LaDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T19:10:34.492052Z"},"content_sha256":"20603b5ff1abd44e4d684bfb45727c3bb5eef69a405484e43584a47ba8bc22c6","schema_version":"1.0","event_id":"sha256:20603b5ff1abd44e4d684bfb45727c3bb5eef69a405484e43584a47ba8bc22c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W6KFRXZJEDC7ULN3KEY364MXG5/bundle.json","state_url":"https://pith.science/pith/W6KFRXZJEDC7ULN3KEY364MXG5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W6KFRXZJEDC7ULN3KEY364MXG5/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":"2026-07-08T19:10:34Z","links":{"resolver":"https://pith.science/pith/W6KFRXZJEDC7ULN3KEY364MXG5","bundle":"https://pith.science/pith/W6KFRXZJEDC7ULN3KEY364MXG5/bundle.json","state":"https://pith.science/pith/W6KFRXZJEDC7ULN3KEY364MXG5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W6KFRXZJEDC7ULN3KEY364MXG5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W6KFRXZJEDC7ULN3KEY364MXG5","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":"9a326f1f502ef126aa0e732c6119f1d193b5c2e93162f021c1d8cd02c3386ada","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-08T01:42:31Z","title_canon_sha256":"583c1c6469be98a916b582f868a61ac8b97b4bfb841c3dd1c05cd426cbdc203b"},"schema_version":"1.0","source":{"id":"2408.04154","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04154","created_at":"2026-07-05T08:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04154v1","created_at":"2026-07-05T08:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04154","created_at":"2026-07-05T08:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"W6KFRXZJEDC7","created_at":"2026-07-05T08:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"W6KFRXZJEDC7ULN3","created_at":"2026-07-05T08:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"W6KFRXZJ","created_at":"2026-07-05T08:53:28Z"}],"graph_snapshots":[{"event_id":"sha256:20603b5ff1abd44e4d684bfb45727c3bb5eef69a405484e43584a47ba8bc22c6","target":"graph","created_at":"2026-07-05T08:53:28Z","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/2408.04154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many machine learning for healthcare tasks, standard datasets are constructed by amassing data across many, often fundamentally dissimilar, sources. But when does adding more data help, and when does it hinder progress on desired model outcomes in real-world settings? We identify this situation as the \\textit{Data Addition Dilemma}, demonstrating that adding training data in this multi-source scaling context can at times result in reduced overall accuracy, uncertain fairness outcomes, and reduced worst-subgroup performance. We find that this possibly arises from an empirically observed trad","authors_text":"Inioluwa Deborah Raji, Irene Y. Chen, Judy Hanwen Shen","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-08T01:42:31Z","title":"The Data Addition Dilemma"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04154","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":"sha256:05547db3b6d82376548d62bba5a2703df0c368b53587ea4bb0c198e6a412549c","target":"record","created_at":"2026-07-05T08:53:28Z","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":"9a326f1f502ef126aa0e732c6119f1d193b5c2e93162f021c1d8cd02c3386ada","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-08T01:42:31Z","title_canon_sha256":"583c1c6469be98a916b582f868a61ac8b97b4bfb841c3dd1c05cd426cbdc203b"},"schema_version":"1.0","source":{"id":"2408.04154","kind":"arxiv","version":1}},"canonical_sha256":"b79458df2920c5fa2dbb5131bf7197377ea2d301e7927fe17b6f8d50190a639f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b79458df2920c5fa2dbb5131bf7197377ea2d301e7927fe17b6f8d50190a639f","first_computed_at":"2026-07-05T08:53:28.761831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:28.761831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XFOwyzyDRAzPpMxNBarjqXchKCKklxhh76cDBZUcqDKO2C8sHBaM3yXas7b24opf5VnaZCsiefvVEsNplbMECw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:28.762241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04154","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05547db3b6d82376548d62bba5a2703df0c368b53587ea4bb0c198e6a412549c","sha256:20603b5ff1abd44e4d684bfb45727c3bb5eef69a405484e43584a47ba8bc22c6"],"state_sha256":"32e7041782d8219ae706dd35e56f5af3aef1874ce57d9e9acea6c5629922f28f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aqIXJjOASaAmSnSKyQ/+q09p8hwLIkk4J4FqvzppxXI+h2jw0OL3sbdHjx4gAnCtjDCsgCU84rxTbnklLbXkCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T19:10:34.494821Z","bundle_sha256":"00a1f35e22a1a12c9c52cffe58294d125d45a351a17f254fa458fdb10559b907"}}