{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6SZXJ7IVL7MMX5UXODRGFMWF2N","short_pith_number":"pith:6SZXJ7IV","schema_version":"1.0","canonical_sha256":"f4b374fd155fd8cbf69770e262b2c5d36c8c01cdfb4557fcbfa10a44170eacb2","source":{"kind":"arxiv","id":"2508.04740","version":1},"attestation_state":"computed","paper":{"title":"MissMecha: An All-in-One Python Package for Studying Missing Data Mechanisms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MS"],"primary_cat":"cs.LG","authors_text":"Mohamed Reda Bouadjenek, Sunil Aryal, Youran Zhou","submitted_at":"2025-08-06T02:40:45Z","abstract_excerpt":"Incomplete data is a persistent challenge in real-world datasets, often governed by complex and unobservable missing mechanisms. Simulating missingness has become a standard approach for understanding its impact on learning and analysis. However, existing tools are fragmented, mechanism-limited, and typically focus only on numerical variables, overlooking the heterogeneous nature of real-world tabular data. We present MissMecha, an open-source Python toolkit for simulating, visualizing, and evaluating missing data under MCAR, MAR, and MNAR assumptions. MissMecha supports both numerical and cat"},"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":"2508.04740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-06T02:40:45Z","cross_cats_sorted":["cs.MS"],"title_canon_sha256":"636db7eb2ff545aed94e5f843a87889b2a5055c2a1417728645c00505b8daef6","abstract_canon_sha256":"049355409aa4f677d514fa2a66026b27e6e33598dc297fcd57b4dd8e41642596"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:00.939080Z","signature_b64":"UjYXZkkmbZgfK20eR7VL47gKFz84Sg9x45wvzt9VWiDtK3UWiM64K/Mm25Wlt7e3nh0RNVXg2hJHul8dFXJ1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4b374fd155fd8cbf69770e262b2c5d36c8c01cdfb4557fcbfa10a44170eacb2","last_reissued_at":"2026-07-05T11:50:00.938651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:00.938651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MissMecha: An All-in-One Python Package for Studying Missing Data Mechanisms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MS"],"primary_cat":"cs.LG","authors_text":"Mohamed Reda Bouadjenek, Sunil Aryal, Youran Zhou","submitted_at":"2025-08-06T02:40:45Z","abstract_excerpt":"Incomplete data is a persistent challenge in real-world datasets, often governed by complex and unobservable missing mechanisms. Simulating missingness has become a standard approach for understanding its impact on learning and analysis. However, existing tools are fragmented, mechanism-limited, and typically focus only on numerical variables, overlooking the heterogeneous nature of real-world tabular data. We present MissMecha, an open-source Python toolkit for simulating, visualizing, and evaluating missing data under MCAR, MAR, and MNAR assumptions. MissMecha supports both numerical and cat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04740","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/2508.04740/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":"2508.04740","created_at":"2026-07-05T11:50:00.938706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04740v1","created_at":"2026-07-05T11:50:00.938706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04740","created_at":"2026-07-05T11:50:00.938706+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SZXJ7IVL7MM","created_at":"2026-07-05T11:50:00.938706+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SZXJ7IVL7MMX5UX","created_at":"2026-07-05T11:50:00.938706+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SZXJ7IV","created_at":"2026-07-05T11:50:00.938706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SZXJ7IVL7MMX5UXODRGFMWF2N","json":"https://pith.science/pith/6SZXJ7IVL7MMX5UXODRGFMWF2N.json","graph_json":"https://pith.science/api/pith-number/6SZXJ7IVL7MMX5UXODRGFMWF2N/graph.json","events_json":"https://pith.science/api/pith-number/6SZXJ7IVL7MMX5UXODRGFMWF2N/events.json","paper":"https://pith.science/paper/6SZXJ7IV"},"agent_actions":{"view_html":"https://pith.science/pith/6SZXJ7IVL7MMX5UXODRGFMWF2N","download_json":"https://pith.science/pith/6SZXJ7IVL7MMX5UXODRGFMWF2N.json","view_paper":"https://pith.science/paper/6SZXJ7IV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04740&json=true","fetch_graph":"https://pith.science/api/pith-number/6SZXJ7IVL7MMX5UXODRGFMWF2N/graph.json","fetch_events":"https://pith.science/api/pith-number/6SZXJ7IVL7MMX5UXODRGFMWF2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SZXJ7IVL7MMX5UXODRGFMWF2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SZXJ7IVL7MMX5UXODRGFMWF2N/action/storage_attestation","attest_author":"https://pith.science/pith/6SZXJ7IVL7MMX5UXODRGFMWF2N/action/author_attestation","sign_citation":"https://pith.science/pith/6SZXJ7IVL7MMX5UXODRGFMWF2N/action/citation_signature","submit_replication":"https://pith.science/pith/6SZXJ7IVL7MMX5UXODRGFMWF2N/action/replication_record"}},"created_at":"2026-07-05T11:50:00.938706+00:00","updated_at":"2026-07-05T11:50:00.938706+00:00"}