{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:25SLZ7J7EML3S7ZLLZHPH37UHK","short_pith_number":"pith:25SLZ7J7","schema_version":"1.0","canonical_sha256":"d764bcfd3f2317b97f2b5e4ef3eff43a91e839f4667b00c7460639190ec9de90","source":{"kind":"arxiv","id":"2506.02306","version":1},"attestation_state":"computed","paper":{"title":"CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Gorla, Ryan Wang, Sriram Sankararaman, Ulzee An, Zhengtong Liu","submitted_at":"2025-06-02T22:50:22Z","abstract_excerpt":"We present CACTI, a masked autoencoding approach for imputing tabular data that leverages the structure in missingness patterns and contextual information. Our approach employs a novel median truncated copy masking training strategy that encourages the model to learn from empirical patterns of missingness while incorporating semantic relationships between features - captured by column names and text descriptions - to better represent feature dependence. These dual sources of inductive bias enable CACTI to outperform state-of-the-art methods - an average $R^2$ gain of 7.8% over the next best me"},"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":"2506.02306","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T22:50:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"87f52107ab2debce81a456c1fe7983d01746f716828c23856a87e93af5048af9","abstract_canon_sha256":"843df5815c7f31860e714d92cfdb5127a4bbf0fe5e03182ab8e05769ee91b41a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:36.097960Z","signature_b64":"iV5qddqiuUSrCmjqGC4RDgLeR9BZENKmwuR7+x7Ah/bX2ChZ7CIrVyhBqPIF/hmRoVjDPRb9RFm1T208jTQ5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d764bcfd3f2317b97f2b5e4ef3eff43a91e839f4667b00c7460639190ec9de90","last_reissued_at":"2026-07-05T11:14:36.097499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:36.097499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Gorla, Ryan Wang, Sriram Sankararaman, Ulzee An, Zhengtong Liu","submitted_at":"2025-06-02T22:50:22Z","abstract_excerpt":"We present CACTI, a masked autoencoding approach for imputing tabular data that leverages the structure in missingness patterns and contextual information. Our approach employs a novel median truncated copy masking training strategy that encourages the model to learn from empirical patterns of missingness while incorporating semantic relationships between features - captured by column names and text descriptions - to better represent feature dependence. These dual sources of inductive bias enable CACTI to outperform state-of-the-art methods - an average $R^2$ gain of 7.8% over the next best me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02306","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/2506.02306/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":"2506.02306","created_at":"2026-07-05T11:14:36.097564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02306v1","created_at":"2026-07-05T11:14:36.097564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02306","created_at":"2026-07-05T11:14:36.097564+00:00"},{"alias_kind":"pith_short_12","alias_value":"25SLZ7J7EML3","created_at":"2026-07-05T11:14:36.097564+00:00"},{"alias_kind":"pith_short_16","alias_value":"25SLZ7J7EML3S7ZL","created_at":"2026-07-05T11:14:36.097564+00:00"},{"alias_kind":"pith_short_8","alias_value":"25SLZ7J7","created_at":"2026-07-05T11:14:36.097564+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/25SLZ7J7EML3S7ZLLZHPH37UHK","json":"https://pith.science/pith/25SLZ7J7EML3S7ZLLZHPH37UHK.json","graph_json":"https://pith.science/api/pith-number/25SLZ7J7EML3S7ZLLZHPH37UHK/graph.json","events_json":"https://pith.science/api/pith-number/25SLZ7J7EML3S7ZLLZHPH37UHK/events.json","paper":"https://pith.science/paper/25SLZ7J7"},"agent_actions":{"view_html":"https://pith.science/pith/25SLZ7J7EML3S7ZLLZHPH37UHK","download_json":"https://pith.science/pith/25SLZ7J7EML3S7ZLLZHPH37UHK.json","view_paper":"https://pith.science/paper/25SLZ7J7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02306&json=true","fetch_graph":"https://pith.science/api/pith-number/25SLZ7J7EML3S7ZLLZHPH37UHK/graph.json","fetch_events":"https://pith.science/api/pith-number/25SLZ7J7EML3S7ZLLZHPH37UHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25SLZ7J7EML3S7ZLLZHPH37UHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25SLZ7J7EML3S7ZLLZHPH37UHK/action/storage_attestation","attest_author":"https://pith.science/pith/25SLZ7J7EML3S7ZLLZHPH37UHK/action/author_attestation","sign_citation":"https://pith.science/pith/25SLZ7J7EML3S7ZLLZHPH37UHK/action/citation_signature","submit_replication":"https://pith.science/pith/25SLZ7J7EML3S7ZLLZHPH37UHK/action/replication_record"}},"created_at":"2026-07-05T11:14:36.097564+00:00","updated_at":"2026-07-05T11:14:36.097564+00:00"}