{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GYRRJGLS3ODYNKJ6642WFSVTLE","short_pith_number":"pith:GYRRJGLS","canonical_record":{"source":{"id":"2308.04431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-08T17:58:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3f86834f662215a5cc013b0ff1ca88e63b04f7b65207ad661fdc86bf5c84aace","abstract_canon_sha256":"f4752c48e1076ff5b4bb706cb13bd1bfb598e5d17b458c7072a66b404e77ab78"},"schema_version":"1.0"},"canonical_sha256":"3623149972db8786a93ef73562cab359312a29df577fc1a87380e26380aa2637","source":{"kind":"arxiv","id":"2308.04431","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.04431","created_at":"2026-07-05T06:39:27Z"},{"alias_kind":"arxiv_version","alias_value":"2308.04431v1","created_at":"2026-07-05T06:39:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04431","created_at":"2026-07-05T06:39:27Z"},{"alias_kind":"pith_short_12","alias_value":"GYRRJGLS3ODY","created_at":"2026-07-05T06:39:27Z"},{"alias_kind":"pith_short_16","alias_value":"GYRRJGLS3ODYNKJ6","created_at":"2026-07-05T06:39:27Z"},{"alias_kind":"pith_short_8","alias_value":"GYRRJGLS","created_at":"2026-07-05T06:39:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GYRRJGLS3ODYNKJ6642WFSVTLE","target":"record","payload":{"canonical_record":{"source":{"id":"2308.04431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-08T17:58:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3f86834f662215a5cc013b0ff1ca88e63b04f7b65207ad661fdc86bf5c84aace","abstract_canon_sha256":"f4752c48e1076ff5b4bb706cb13bd1bfb598e5d17b458c7072a66b404e77ab78"},"schema_version":"1.0"},"canonical_sha256":"3623149972db8786a93ef73562cab359312a29df577fc1a87380e26380aa2637","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:27.418238Z","signature_b64":"PARmdRN9F//KsP0ohXjrJOBz81HNAlZdTYGsj5wKKYUAz0Hs6O8Bb3a6kXVPV1fnWYH5iwkRnUvU19ec+a1OBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3623149972db8786a93ef73562cab359312a29df577fc1a87380e26380aa2637","last_reissued_at":"2026-07-05T06:39:27.417684Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:27.417684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.04431","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":"2026-07-05T06:39:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+jkx4YvSkqcS0y6UOP8hGjuF7rrCoYa4ahDzMT58YTqlv4eZ2bxze/h4JVtm511OVKIavBKrSmr6pgEUAyUsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T18:28:37.621883Z"},"content_sha256":"b582f5ae2387eec40cefe53a5777ae513507ac77dd72178073ecc50e8df3ac30","schema_version":"1.0","event_id":"sha256:b582f5ae2387eec40cefe53a5777ae513507ac77dd72178073ecc50e8df3ac30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GYRRJGLS3ODYNKJ6642WFSVTLE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Aahlad Puli, Lily Zhang, Rajesh Ranganath, Rhys Compton","submitted_at":"2023-08-08T17:58:45Z","abstract_excerpt":"In machine learning, incorporating more data is often seen as a reliable strategy for improving model performance; this work challenges that notion by demonstrating that the addition of external datasets in many cases can hurt the resulting model's performance. In a large-scale empirical study across combinations of four different open-source chest x-ray datasets and 9 different labels, we demonstrate that in 43% of settings, a model trained on data from two hospitals has poorer worst group accuracy over both hospitals than a model trained on just a single hospital's data. This surprising resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04431","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/2308.04431/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":"2026-07-05T06:39:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PxpTdB4b38FE/3HBRRvWsQoJ9JskXb7ya4DwHS4Qamb9KDh+/DF4a9HVNLrDQzoi7GRz0dlWn4nSrbZlz8t5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T18:28:37.622418Z"},"content_sha256":"ddcf7ca46b393cd59e34df3188896360b5c56e81869e19ffd16f33c2fd562675","schema_version":"1.0","event_id":"sha256:ddcf7ca46b393cd59e34df3188896360b5c56e81869e19ffd16f33c2fd562675"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYRRJGLS3ODYNKJ6642WFSVTLE/bundle.json","state_url":"https://pith.science/pith/GYRRJGLS3ODYNKJ6642WFSVTLE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYRRJGLS3ODYNKJ6642WFSVTLE/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":"2026-08-01T18:28:37Z","links":{"resolver":"https://pith.science/pith/GYRRJGLS3ODYNKJ6642WFSVTLE","bundle":"https://pith.science/pith/GYRRJGLS3ODYNKJ6642WFSVTLE/bundle.json","state":"https://pith.science/pith/GYRRJGLS3ODYNKJ6642WFSVTLE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYRRJGLS3ODYNKJ6642WFSVTLE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GYRRJGLS3ODYNKJ6642WFSVTLE","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":"f4752c48e1076ff5b4bb706cb13bd1bfb598e5d17b458c7072a66b404e77ab78","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-08T17:58:45Z","title_canon_sha256":"3f86834f662215a5cc013b0ff1ca88e63b04f7b65207ad661fdc86bf5c84aace"},"schema_version":"1.0","source":{"id":"2308.04431","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.04431","created_at":"2026-07-05T06:39:27Z"},{"alias_kind":"arxiv_version","alias_value":"2308.04431v1","created_at":"2026-07-05T06:39:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04431","created_at":"2026-07-05T06:39:27Z"},{"alias_kind":"pith_short_12","alias_value":"GYRRJGLS3ODY","created_at":"2026-07-05T06:39:27Z"},{"alias_kind":"pith_short_16","alias_value":"GYRRJGLS3ODYNKJ6","created_at":"2026-07-05T06:39:27Z"},{"alias_kind":"pith_short_8","alias_value":"GYRRJGLS","created_at":"2026-07-05T06:39:27Z"}],"graph_snapshots":[{"event_id":"sha256:ddcf7ca46b393cd59e34df3188896360b5c56e81869e19ffd16f33c2fd562675","target":"graph","created_at":"2026-07-05T06:39:27Z","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/2308.04431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In machine learning, incorporating more data is often seen as a reliable strategy for improving model performance; this work challenges that notion by demonstrating that the addition of external datasets in many cases can hurt the resulting model's performance. In a large-scale empirical study across combinations of four different open-source chest x-ray datasets and 9 different labels, we demonstrate that in 43% of settings, a model trained on data from two hospitals has poorer worst group accuracy over both hospitals than a model trained on just a single hospital's data. This surprising resu","authors_text":"Aahlad Puli, Lily Zhang, Rajesh Ranganath, Rhys Compton","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-08T17:58:45Z","title":"When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04431","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:b582f5ae2387eec40cefe53a5777ae513507ac77dd72178073ecc50e8df3ac30","target":"record","created_at":"2026-07-05T06:39:27Z","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":"f4752c48e1076ff5b4bb706cb13bd1bfb598e5d17b458c7072a66b404e77ab78","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-08T17:58:45Z","title_canon_sha256":"3f86834f662215a5cc013b0ff1ca88e63b04f7b65207ad661fdc86bf5c84aace"},"schema_version":"1.0","source":{"id":"2308.04431","kind":"arxiv","version":1}},"canonical_sha256":"3623149972db8786a93ef73562cab359312a29df577fc1a87380e26380aa2637","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3623149972db8786a93ef73562cab359312a29df577fc1a87380e26380aa2637","first_computed_at":"2026-07-05T06:39:27.417684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:27.417684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PARmdRN9F//KsP0ohXjrJOBz81HNAlZdTYGsj5wKKYUAz0Hs6O8Bb3a6kXVPV1fnWYH5iwkRnUvU19ec+a1OBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:27.418238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.04431","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b582f5ae2387eec40cefe53a5777ae513507ac77dd72178073ecc50e8df3ac30","sha256:ddcf7ca46b393cd59e34df3188896360b5c56e81869e19ffd16f33c2fd562675"],"state_sha256":"dc076b69affde7a14b015256538b83a13effef6f27c271d3000b1bffe01a4d40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4D8a01woA1Y4r2Saa2lCLRUk3JGPlEXFWLTb/h39TyJKCyHRD7UHRBVrFBuRgt7MOVctQzMxxoRjRZmGyFhkCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T18:28:37.626581Z","bundle_sha256":"665250a63938c78ec3fdef03fde1f95ee0e7eddf0e89511b1cdee0913662d26c"}}