{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4BFVVQAHPW4RE5PATL25MQPNIM","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":"58bb15317176b2ef2706a3989f87e70d718047da5052b1af61ca1d193a48d31f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T15:28:51Z","title_canon_sha256":"60ff5bb930ada3f6ad0d1edb4b3d1e64b4527a6762ee1b15a96f4c535c81c576"},"schema_version":"1.0","source":{"id":"2407.15724","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15724","created_at":"2026-07-05T08:50:57Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15724v2","created_at":"2026-07-05T08:50:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15724","created_at":"2026-07-05T08:50:57Z"},{"alias_kind":"pith_short_12","alias_value":"4BFVVQAHPW4R","created_at":"2026-07-05T08:50:57Z"},{"alias_kind":"pith_short_16","alias_value":"4BFVVQAHPW4RE5PA","created_at":"2026-07-05T08:50:57Z"},{"alias_kind":"pith_short_8","alias_value":"4BFVVQAH","created_at":"2026-07-05T08:50:57Z"}],"graph_snapshots":[{"event_id":"sha256:cc85fec5af734b089e551d97e431880903167c7511989b9652de4a511d0db4bf","target":"graph","created_at":"2026-07-05T08:50:57Z","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/2407.15724/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In deep learning, achieving high performance on image classification tasks requires diverse training sets. However, the current best practice$\\unicode{x2013}$maximizing dataset size and class balance$\\unicode{x2013}$does not guarantee dataset diversity. We hypothesized that, for a given model architecture, model performance can be improved by maximizing diversity more directly. To test this hypothesis, we introduce a comprehensive framework of diversity measures from ecology that generalizes familiar quantities like Shannon entropy by accounting for similarities among images. (Size and class b","authors_text":"Josiah Couch, Ramy Arnaout, Rima Arnaout","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T15:28:51Z","title":"Beyond Size and Class Balance: Alpha as a New Dataset Quality Metric for Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15724","kind":"arxiv","version":2},"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:aaa1d01f18b1832fab2667913bcaf4a91a3394cde26227560b5303d37584cee3","target":"record","created_at":"2026-07-05T08:50:57Z","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":"58bb15317176b2ef2706a3989f87e70d718047da5052b1af61ca1d193a48d31f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T15:28:51Z","title_canon_sha256":"60ff5bb930ada3f6ad0d1edb4b3d1e64b4527a6762ee1b15a96f4c535c81c576"},"schema_version":"1.0","source":{"id":"2407.15724","kind":"arxiv","version":2}},"canonical_sha256":"e04b5ac0077db91275e09af5d641ed4309167742c8bb52cf0fc1028d2efdcd1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e04b5ac0077db91275e09af5d641ed4309167742c8bb52cf0fc1028d2efdcd1e","first_computed_at":"2026-07-05T08:50:57.910538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:57.910538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iDzqISRs4zQPcxxuB+sE5aua6FT1V/NAwZoJGNB+PWj9cQopfjFPGrkEV49DxiJ/tyqC0UZAZYqi6qitjXvdCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:57.910956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15724","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaa1d01f18b1832fab2667913bcaf4a91a3394cde26227560b5303d37584cee3","sha256:cc85fec5af734b089e551d97e431880903167c7511989b9652de4a511d0db4bf"],"state_sha256":"8eb3153261b6d2c86d9fd560f5270344754e002048c69dc20d1d9670b61daf47"}