{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UVZGMTOIDCGHSFWBKWV5JLPCJN","short_pith_number":"pith:UVZGMTOI","schema_version":"1.0","canonical_sha256":"a572664dc8188c7916c155abd4ade24b714dab1638f2bee35393dae505883b60","source":{"kind":"arxiv","id":"2007.13889","version":1},"attestation_state":"computed","paper":{"title":"openXDATA: A Tool for Multi-Target Data Generation and Missing Label Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Felix Weninger, Rosalind W. Picard, Yue Zhang","submitted_at":"2020-07-27T22:05:53Z","abstract_excerpt":"A common problem in machine learning is to deal with datasets with disjoint label spaces and missing labels. In this work, we introduce the openXDATA tool that completes the missing labels in partially labelled or unlabelled datasets in order to generate multi-target data with labels in the joint label space of the datasets. To this end, we designed and implemented the cross-data label completion (CDLC) algorithm that uses a multi-task shared-hidden-layer DNN to iteratively complete the sparse label matrix of the instances from the different datasets. We apply the new tool to estimate labels a"},"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":"2007.13889","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-27T22:05:53Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d5bf16b41b582f16013ca6d92cef89aeb41387bdbfa5e1d48ec91863652fe9f3","abstract_canon_sha256":"3e6714a3656685e9307d746c1beab29be2642837eb65d95845c3b729b84c40cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:22:53.332195Z","signature_b64":"rnIxnVxHrTfqdiF1O2K9wzaXVLVrQ4UNWkKQ2uA1kpA1ug2cPAbjtHOW9Y+bONJCtRFoJEa1+auV2hz8Pd8lDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a572664dc8188c7916c155abd4ade24b714dab1638f2bee35393dae505883b60","last_reissued_at":"2026-07-05T01:22:53.331780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:22:53.331780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"openXDATA: A Tool for Multi-Target Data Generation and Missing Label Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Felix Weninger, Rosalind W. Picard, Yue Zhang","submitted_at":"2020-07-27T22:05:53Z","abstract_excerpt":"A common problem in machine learning is to deal with datasets with disjoint label spaces and missing labels. In this work, we introduce the openXDATA tool that completes the missing labels in partially labelled or unlabelled datasets in order to generate multi-target data with labels in the joint label space of the datasets. To this end, we designed and implemented the cross-data label completion (CDLC) algorithm that uses a multi-task shared-hidden-layer DNN to iteratively complete the sparse label matrix of the instances from the different datasets. We apply the new tool to estimate labels a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13889","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/2007.13889/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":"2007.13889","created_at":"2026-07-05T01:22:53.331839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.13889v1","created_at":"2026-07-05T01:22:53.331839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13889","created_at":"2026-07-05T01:22:53.331839+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVZGMTOIDCGH","created_at":"2026-07-05T01:22:53.331839+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVZGMTOIDCGHSFWB","created_at":"2026-07-05T01:22:53.331839+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVZGMTOI","created_at":"2026-07-05T01:22:53.331839+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/UVZGMTOIDCGHSFWBKWV5JLPCJN","json":"https://pith.science/pith/UVZGMTOIDCGHSFWBKWV5JLPCJN.json","graph_json":"https://pith.science/api/pith-number/UVZGMTOIDCGHSFWBKWV5JLPCJN/graph.json","events_json":"https://pith.science/api/pith-number/UVZGMTOIDCGHSFWBKWV5JLPCJN/events.json","paper":"https://pith.science/paper/UVZGMTOI"},"agent_actions":{"view_html":"https://pith.science/pith/UVZGMTOIDCGHSFWBKWV5JLPCJN","download_json":"https://pith.science/pith/UVZGMTOIDCGHSFWBKWV5JLPCJN.json","view_paper":"https://pith.science/paper/UVZGMTOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.13889&json=true","fetch_graph":"https://pith.science/api/pith-number/UVZGMTOIDCGHSFWBKWV5JLPCJN/graph.json","fetch_events":"https://pith.science/api/pith-number/UVZGMTOIDCGHSFWBKWV5JLPCJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVZGMTOIDCGHSFWBKWV5JLPCJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVZGMTOIDCGHSFWBKWV5JLPCJN/action/storage_attestation","attest_author":"https://pith.science/pith/UVZGMTOIDCGHSFWBKWV5JLPCJN/action/author_attestation","sign_citation":"https://pith.science/pith/UVZGMTOIDCGHSFWBKWV5JLPCJN/action/citation_signature","submit_replication":"https://pith.science/pith/UVZGMTOIDCGHSFWBKWV5JLPCJN/action/replication_record"}},"created_at":"2026-07-05T01:22:53.331839+00:00","updated_at":"2026-07-05T01:22:53.331839+00:00"}