{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:25SLZ7J7EML3S7ZLLZHPH37UHK","short_pith_number":"pith:25SLZ7J7","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"},"canonical_sha256":"d764bcfd3f2317b97f2b5e4ef3eff43a91e839f4667b00c7460639190ec9de90","source":{"kind":"arxiv","id":"2506.02306","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02306","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02306v1","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02306","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"pith_short_12","alias_value":"25SLZ7J7EML3","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"pith_short_16","alias_value":"25SLZ7J7EML3S7ZL","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"pith_short_8","alias_value":"25SLZ7J7","created_at":"2026-07-05T11:14:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:25SLZ7J7EML3S7ZLLZHPH37UHK","target":"record","payload":{"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"},"canonical_sha256":"d764bcfd3f2317b97f2b5e4ef3eff43a91e839f4667b00c7460639190ec9de90","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"},"source_kind":"arxiv","source_id":"2506.02306","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uOvx6C7blTbYprpmyxbctdM0DG2GgIOKe/VW3vSbuw67dqfyXQmKorbz/WR0ycRYjwQrc3cJFP9kIbz2D+bGBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:13:48.915309Z"},"content_sha256":"c8bf8befca93428441f8da4331ce333caaddc8afd8e533a624a93ad66802d2fc","schema_version":"1.0","event_id":"sha256:c8bf8befca93428441f8da4331ce333caaddc8afd8e533a624a93ad66802d2fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:25SLZ7J7EML3S7ZLLZHPH37UHK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oW2vBK88D0QL6y4nuevqqcb0HX35FJIvYyXQmC6XJ4VaxeUDIAe0+tDW2MG1LBZgcRNyVu5Nj0iVnAtSsQEuCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:13:48.915822Z"},"content_sha256":"15ed94258fdc087badf7dc944b1bd1a9712432e26f7c26b63f4f5dd1de0cd6c9","schema_version":"1.0","event_id":"sha256:15ed94258fdc087badf7dc944b1bd1a9712432e26f7c26b63f4f5dd1de0cd6c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/25SLZ7J7EML3S7ZLLZHPH37UHK/bundle.json","state_url":"https://pith.science/pith/25SLZ7J7EML3S7ZLLZHPH37UHK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/25SLZ7J7EML3S7ZLLZHPH37UHK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T23:13:48Z","links":{"resolver":"https://pith.science/pith/25SLZ7J7EML3S7ZLLZHPH37UHK","bundle":"https://pith.science/pith/25SLZ7J7EML3S7ZLLZHPH37UHK/bundle.json","state":"https://pith.science/pith/25SLZ7J7EML3S7ZLLZHPH37UHK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/25SLZ7J7EML3S7ZLLZHPH37UHK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:25SLZ7J7EML3S7ZLLZHPH37UHK","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":"843df5815c7f31860e714d92cfdb5127a4bbf0fe5e03182ab8e05769ee91b41a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T22:50:22Z","title_canon_sha256":"87f52107ab2debce81a456c1fe7983d01746f716828c23856a87e93af5048af9"},"schema_version":"1.0","source":{"id":"2506.02306","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02306","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02306v1","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02306","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"pith_short_12","alias_value":"25SLZ7J7EML3","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"pith_short_16","alias_value":"25SLZ7J7EML3S7ZL","created_at":"2026-07-05T11:14:36Z"},{"alias_kind":"pith_short_8","alias_value":"25SLZ7J7","created_at":"2026-07-05T11:14:36Z"}],"graph_snapshots":[{"event_id":"sha256:15ed94258fdc087badf7dc944b1bd1a9712432e26f7c26b63f4f5dd1de0cd6c9","target":"graph","created_at":"2026-07-05T11:14:36Z","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/2506.02306/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aditya Gorla, Ryan Wang, Sriram Sankararaman, Ulzee An, Zhengtong Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T22:50:22Z","title":"CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02306","kind":"arxiv","version":1},"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:c8bf8befca93428441f8da4331ce333caaddc8afd8e533a624a93ad66802d2fc","target":"record","created_at":"2026-07-05T11:14:36Z","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":"843df5815c7f31860e714d92cfdb5127a4bbf0fe5e03182ab8e05769ee91b41a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T22:50:22Z","title_canon_sha256":"87f52107ab2debce81a456c1fe7983d01746f716828c23856a87e93af5048af9"},"schema_version":"1.0","source":{"id":"2506.02306","kind":"arxiv","version":1}},"canonical_sha256":"d764bcfd3f2317b97f2b5e4ef3eff43a91e839f4667b00c7460639190ec9de90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d764bcfd3f2317b97f2b5e4ef3eff43a91e839f4667b00c7460639190ec9de90","first_computed_at":"2026-07-05T11:14:36.097499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:36.097499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iV5qddqiuUSrCmjqGC4RDgLeR9BZENKmwuR7+x7Ah/bX2ChZ7CIrVyhBqPIF/hmRoVjDPRb9RFm1T208jTQ5Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:36.097960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02306","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8bf8befca93428441f8da4331ce333caaddc8afd8e533a624a93ad66802d2fc","sha256:15ed94258fdc087badf7dc944b1bd1a9712432e26f7c26b63f4f5dd1de0cd6c9"],"state_sha256":"953e827e1bd153a1714803188da471aba00b1120d9185ffb8b5e66448250f259"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XclZYsAxSh2v52754ClzrjwewTbfPY+4hQbXYzNsupvGariWiXr0fHrXQqSALFfgPje6rIwkjVwBTglwHGIADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T23:13:48.919446Z","bundle_sha256":"37288fa1bd18fc7cc5156694df99301591918056248d8da039cb64a9805bdf82"}}