{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3YQ3QBOA7E2W7QGLXY4UAME22Q","short_pith_number":"pith:3YQ3QBOA","canonical_record":{"source":{"id":"2405.18722","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2024-05-29T03:05:59Z","cross_cats_sorted":[],"title_canon_sha256":"abaca7bd56f9e15b1889a351a0d0b77f7284cc9183495deddcdb951c048bbc02","abstract_canon_sha256":"3c22cd1092d5a733936e44ab4fde7bce44272ccb87fede86297fdd9499cddb9b"},"schema_version":"1.0"},"canonical_sha256":"de21b805c0f9356fc0cbbe3940309ad4222d6d985314a2411a52193fde54bbcd","source":{"kind":"arxiv","id":"2405.18722","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18722","created_at":"2026-06-23T03:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18722v4","created_at":"2026-06-23T03:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18722","created_at":"2026-06-23T03:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"3YQ3QBOA7E2W","created_at":"2026-06-23T03:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"3YQ3QBOA7E2W7QGL","created_at":"2026-06-23T03:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"3YQ3QBOA","created_at":"2026-06-23T03:13:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3YQ3QBOA7E2W7QGLXY4UAME22Q","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18722","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2024-05-29T03:05:59Z","cross_cats_sorted":[],"title_canon_sha256":"abaca7bd56f9e15b1889a351a0d0b77f7284cc9183495deddcdb951c048bbc02","abstract_canon_sha256":"3c22cd1092d5a733936e44ab4fde7bce44272ccb87fede86297fdd9499cddb9b"},"schema_version":"1.0"},"canonical_sha256":"de21b805c0f9356fc0cbbe3940309ad4222d6d985314a2411a52193fde54bbcd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:43.368277Z","signature_b64":"l9B/8o/goDLnMi470MR8ghYozpT/Li0mYRLhUxGq4cI487/pxu01jIpUmeLKnknAbLkjNb6aP3ZkBt00kd02BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de21b805c0f9356fc0cbbe3940309ad4222d6d985314a2411a52193fde54bbcd","last_reissued_at":"2026-06-23T03:13:43.367711Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:43.367711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18722","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T03:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dMNvPdP4GVvQ0wh1wh+NHAoqK1WEatqobpkM1x8/R/d/ZCLrgCngZ5XYSh8+KqL+r0Qi+bbyw9nMtfdlyDFIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T09:15:10.409834Z"},"content_sha256":"95bf0a453ca9bb8593c1dee8531a381a19d3767c6ea86e4b570b3ee3425be901","schema_version":"1.0","event_id":"sha256:95bf0a453ca9bb8593c1dee8531a381a19d3767c6ea86e4b570b3ee3425be901"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3YQ3QBOA7E2W7QGLXY4UAME22Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive and Efficient Learning with Blockwise Missing and Semi-Supervised Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Molei Liu, Ruoyu Wang, Yiming Li, Ying Wei","submitted_at":"2024-05-29T03:05:59Z","abstract_excerpt":"Data fusion enables powerful and generalizable analyses across multiple sources. However, different data collection capacities across different sources lead to blockwise missingness (BM), which poses challenges in practice. Meanwhile, the high cost of obtaining gold-standard labels leaves the majority of samples unlabeled, known as the semi-supervised (SS) problem. In this paper, we propose a novel Data-adaptive Estimation approach for data FUsion in the SEmi-supervised setting (DEFUSE) that handles both BM and SS issues in the presence of distributional shifts across data sources under a miss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18722","kind":"arxiv","version":4},"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/2405.18722/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":"2026-06-23T03:13:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DYb6EP4UYYuz345pNNsvcKJ4TEHtbpQz+nLJhrEHaaobq6rh977nFpA6HjpOgRt7uFAGr6g9NLCYXrayi3rTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T09:15:10.410217Z"},"content_sha256":"d367383b812ef69acdc331d04febebd375e3456ba49ee29b3aad72e52b06bdd0","schema_version":"1.0","event_id":"sha256:d367383b812ef69acdc331d04febebd375e3456ba49ee29b3aad72e52b06bdd0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3YQ3QBOA7E2W7QGLXY4UAME22Q/bundle.json","state_url":"https://pith.science/pith/3YQ3QBOA7E2W7QGLXY4UAME22Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3YQ3QBOA7E2W7QGLXY4UAME22Q/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":"2026-06-25T09:15:10Z","links":{"resolver":"https://pith.science/pith/3YQ3QBOA7E2W7QGLXY4UAME22Q","bundle":"https://pith.science/pith/3YQ3QBOA7E2W7QGLXY4UAME22Q/bundle.json","state":"https://pith.science/pith/3YQ3QBOA7E2W7QGLXY4UAME22Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3YQ3QBOA7E2W7QGLXY4UAME22Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3YQ3QBOA7E2W7QGLXY4UAME22Q","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":"3c22cd1092d5a733936e44ab4fde7bce44272ccb87fede86297fdd9499cddb9b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2024-05-29T03:05:59Z","title_canon_sha256":"abaca7bd56f9e15b1889a351a0d0b77f7284cc9183495deddcdb951c048bbc02"},"schema_version":"1.0","source":{"id":"2405.18722","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18722","created_at":"2026-06-23T03:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18722v4","created_at":"2026-06-23T03:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18722","created_at":"2026-06-23T03:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"3YQ3QBOA7E2W","created_at":"2026-06-23T03:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"3YQ3QBOA7E2W7QGL","created_at":"2026-06-23T03:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"3YQ3QBOA","created_at":"2026-06-23T03:13:43Z"}],"graph_snapshots":[{"event_id":"sha256:d367383b812ef69acdc331d04febebd375e3456ba49ee29b3aad72e52b06bdd0","target":"graph","created_at":"2026-06-23T03:13:43Z","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/2405.18722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data fusion enables powerful and generalizable analyses across multiple sources. However, different data collection capacities across different sources lead to blockwise missingness (BM), which poses challenges in practice. Meanwhile, the high cost of obtaining gold-standard labels leaves the majority of samples unlabeled, known as the semi-supervised (SS) problem. In this paper, we propose a novel Data-adaptive Estimation approach for data FUsion in the SEmi-supervised setting (DEFUSE) that handles both BM and SS issues in the presence of distributional shifts across data sources under a miss","authors_text":"Molei Liu, Ruoyu Wang, Yiming Li, Ying Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2024-05-29T03:05:59Z","title":"Adaptive and Efficient Learning with Blockwise Missing and Semi-Supervised Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18722","kind":"arxiv","version":4},"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":"sha256:95bf0a453ca9bb8593c1dee8531a381a19d3767c6ea86e4b570b3ee3425be901","target":"record","created_at":"2026-06-23T03:13:43Z","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":"3c22cd1092d5a733936e44ab4fde7bce44272ccb87fede86297fdd9499cddb9b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2024-05-29T03:05:59Z","title_canon_sha256":"abaca7bd56f9e15b1889a351a0d0b77f7284cc9183495deddcdb951c048bbc02"},"schema_version":"1.0","source":{"id":"2405.18722","kind":"arxiv","version":4}},"canonical_sha256":"de21b805c0f9356fc0cbbe3940309ad4222d6d985314a2411a52193fde54bbcd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de21b805c0f9356fc0cbbe3940309ad4222d6d985314a2411a52193fde54bbcd","first_computed_at":"2026-06-23T03:13:43.367711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:13:43.367711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l9B/8o/goDLnMi470MR8ghYozpT/Li0mYRLhUxGq4cI487/pxu01jIpUmeLKnknAbLkjNb6aP3ZkBt00kd02BA==","signature_status":"signed_v1","signed_at":"2026-06-23T03:13:43.368277Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18722","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95bf0a453ca9bb8593c1dee8531a381a19d3767c6ea86e4b570b3ee3425be901","sha256:d367383b812ef69acdc331d04febebd375e3456ba49ee29b3aad72e52b06bdd0"],"state_sha256":"fc1561085f4d41a72f0671e3a21086b3f8c0a68105071ed9d069b71377458c22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dbkpm4cdEY01MLW7rA8q6Qj5UvfkpFpvY5NmH0E2ICPAVfRuq6Rkok5goyfzc4Mqoq67NzfFOaEoT8s2UCk8Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T09:15:10.412416Z","bundle_sha256":"67d10df25c3b9cc365d6b127ada3ada69409b35d49ff0a75e269ec6f97fd89ed"}}