{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MGE5GLFLNE7YUIV44U6OGEQIEV","short_pith_number":"pith:MGE5GLFL","schema_version":"1.0","canonical_sha256":"6189d32cab693f8a22bce53ce312082552e81e3d3a1fa5b7879c62de5f155655","source":{"kind":"arxiv","id":"2311.18501","version":5},"attestation_state":"computed","paper":{"title":"Perturbation-based Effect Measures for Compositional Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"stat.ME","authors_text":"Anton Rask Lundborg, Niklas Pfister","submitted_at":"2023-11-30T12:27:15Z","abstract_excerpt":"Existing effect measures for compositional features are inadequate for many modern applications, for example, in microbiome research, since they display traits such as high-dimensionality and sparsity that can be poorly modelled with traditional parametric approaches. Further, assessing -- in an unbiased way -- how summary statistics of a composition (e.g., racial diversity) affect a response variable is not straightforward. We propose a framework based on hypothetical data perturbations which defines interpretable statistical functionals on the compositions themselves, which we call average p"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.18501","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2023-11-30T12:27:15Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"d941f64753d67c5e9e34d3321fe47186d92e9f71d9902937a6cbdec63c8fd638","abstract_canon_sha256":"970928bac524ddce34102cb8b7faec29211160ad4bf75f71decefa09ad8a7deb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:16.130019Z","signature_b64":"Cg53e88SJufgDD86vWU8pN5LEyDcFDK04ESWBNK1Jo3Is8ECNmhKbgrurjwAEJwp5LOKS5daSGaqNpPxobpXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6189d32cab693f8a22bce53ce312082552e81e3d3a1fa5b7879c62de5f155655","last_reissued_at":"2026-07-05T11:12:16.129568Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:16.129568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perturbation-based Effect Measures for Compositional Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"stat.ME","authors_text":"Anton Rask Lundborg, Niklas Pfister","submitted_at":"2023-11-30T12:27:15Z","abstract_excerpt":"Existing effect measures for compositional features are inadequate for many modern applications, for example, in microbiome research, since they display traits such as high-dimensionality and sparsity that can be poorly modelled with traditional parametric approaches. Further, assessing -- in an unbiased way -- how summary statistics of a composition (e.g., racial diversity) affect a response variable is not straightforward. We propose a framework based on hypothetical data perturbations which defines interpretable statistical functionals on the compositions themselves, which we call average p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18501","kind":"arxiv","version":5},"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/2311.18501/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.18501","created_at":"2026-07-05T11:12:16.129615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.18501v5","created_at":"2026-07-05T11:12:16.129615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18501","created_at":"2026-07-05T11:12:16.129615+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGE5GLFLNE7Y","created_at":"2026-07-05T11:12:16.129615+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGE5GLFLNE7YUIV4","created_at":"2026-07-05T11:12:16.129615+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGE5GLFL","created_at":"2026-07-05T11:12:16.129615+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.07906","citing_title":"Model-free Methods for Event History Analysis and Efficient Adjustment (PhD Thesis)","ref_index":91,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MGE5GLFLNE7YUIV44U6OGEQIEV","json":"https://pith.science/pith/MGE5GLFLNE7YUIV44U6OGEQIEV.json","graph_json":"https://pith.science/api/pith-number/MGE5GLFLNE7YUIV44U6OGEQIEV/graph.json","events_json":"https://pith.science/api/pith-number/MGE5GLFLNE7YUIV44U6OGEQIEV/events.json","paper":"https://pith.science/paper/MGE5GLFL"},"agent_actions":{"view_html":"https://pith.science/pith/MGE5GLFLNE7YUIV44U6OGEQIEV","download_json":"https://pith.science/pith/MGE5GLFLNE7YUIV44U6OGEQIEV.json","view_paper":"https://pith.science/paper/MGE5GLFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.18501&json=true","fetch_graph":"https://pith.science/api/pith-number/MGE5GLFLNE7YUIV44U6OGEQIEV/graph.json","fetch_events":"https://pith.science/api/pith-number/MGE5GLFLNE7YUIV44U6OGEQIEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGE5GLFLNE7YUIV44U6OGEQIEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGE5GLFLNE7YUIV44U6OGEQIEV/action/storage_attestation","attest_author":"https://pith.science/pith/MGE5GLFLNE7YUIV44U6OGEQIEV/action/author_attestation","sign_citation":"https://pith.science/pith/MGE5GLFLNE7YUIV44U6OGEQIEV/action/citation_signature","submit_replication":"https://pith.science/pith/MGE5GLFLNE7YUIV44U6OGEQIEV/action/replication_record"}},"created_at":"2026-07-05T11:12:16.129615+00:00","updated_at":"2026-07-05T11:12:16.129615+00:00"}