{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2MJ4IXMMVQW776LDV53YUBOVH2","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":"7fedfd1f006eac7a1df0893bc5742a55f5705a53f582e3fcbffdb8b6d51d606e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-03-09T13:34:52Z","title_canon_sha256":"2e4900f388475232a99e6868ac4baa34a2f635b5bb4d160232add2d907cbabbe"},"schema_version":"1.0","source":{"id":"2203.04706","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.04706","created_at":"2026-07-05T05:38:27Z"},{"alias_kind":"arxiv_version","alias_value":"2203.04706v2","created_at":"2026-07-05T05:38:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.04706","created_at":"2026-07-05T05:38:27Z"},{"alias_kind":"pith_short_12","alias_value":"2MJ4IXMMVQW7","created_at":"2026-07-05T05:38:27Z"},{"alias_kind":"pith_short_16","alias_value":"2MJ4IXMMVQW776LD","created_at":"2026-07-05T05:38:27Z"},{"alias_kind":"pith_short_8","alias_value":"2MJ4IXMM","created_at":"2026-07-05T05:38:27Z"}],"graph_snapshots":[{"event_id":"sha256:8a1fdd6f5194128fb981322c922c04c89abe49ab0385f97b79b9c103961a2159","target":"graph","created_at":"2026-07-05T05:38:27Z","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/2203.04706/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data representativity is crucial when drawing inference from data through machine learning models. Scholars have increased focus on unraveling the bias and fairness in models, also in relation to inherent biases in the input data. However, limited work exists on the representativity of samples (datasets) for appropriate inference in AI systems. This paper reviews definitions and notions of a representative sample and surveys their use in scientific AI literature. We introduce three measurable concepts to help focus the notions and evaluate different data samples. Furthermore, we demonstrate th","authors_text":"Line H. Clemmensen, Rune D. Kj{\\ae}rsgaard","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-03-09T13:34:52Z","title":"Data Representativity for Machine Learning and AI Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.04706","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:c12a60a7bcb05f736c3a18e2ada3366ec7ca0a492fcda30648847a0e1338a3ed","target":"record","created_at":"2026-07-05T05:38:27Z","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":"7fedfd1f006eac7a1df0893bc5742a55f5705a53f582e3fcbffdb8b6d51d606e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-03-09T13:34:52Z","title_canon_sha256":"2e4900f388475232a99e6868ac4baa34a2f635b5bb4d160232add2d907cbabbe"},"schema_version":"1.0","source":{"id":"2203.04706","kind":"arxiv","version":2}},"canonical_sha256":"d313c45d8cac2dfff963af778a05d53e93e717c9aa76703ea0d08c38a2c85bf5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d313c45d8cac2dfff963af778a05d53e93e717c9aa76703ea0d08c38a2c85bf5","first_computed_at":"2026-07-05T05:38:27.327426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:27.327426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BBhr9l0GcNXsIUgMpKdnqPu9Bqaw/j/4TUqc/8AY5RC/s47yLH41nPEoGcld1no5BN+i/pPAFq0+MfscXgPlBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:27.327990Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.04706","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c12a60a7bcb05f736c3a18e2ada3366ec7ca0a492fcda30648847a0e1338a3ed","sha256:8a1fdd6f5194128fb981322c922c04c89abe49ab0385f97b79b9c103961a2159"],"state_sha256":"15e2cb940873b76102de7a34876ac661f6dc1cf38f9f4b1155dd8e0f3792cdaa"}