{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7KJ3PMQ6BNPQ7VLYGVM4VK5ME2","short_pith_number":"pith:7KJ3PMQ6","schema_version":"1.0","canonical_sha256":"fa93b7b21e0b5f0fd5783559caabac26a94f31e311297d8dd98fb06c3dae3045","source":{"kind":"arxiv","id":"2508.12048","version":1},"attestation_state":"computed","paper":{"title":"Robust Data Fusion via Subsampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Haiying Wang, Jing Wang, Kun Chen","submitted_at":"2025-08-16T13:49:26Z","abstract_excerpt":"Data fusion and transfer learning are rapidly growing fields that enhance model performance for a target population by leveraging other related data sources or tasks. The challenges lie in the various potential heterogeneities between the target and external data, as well as various practical concerns that prevent a na\\\"ive data integration. We consider a realistic scenario where the target data is limited in size while the external data is large but contaminated with outliers; such data contamination, along with other computational and operational constraints, necessitates proper selection or"},"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":"2508.12048","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-16T13:49:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d9eeee10b271868839762fce6b99feaafde1b191871085b4a2c5fc79a91027ec","abstract_canon_sha256":"3263b521b7753746ea314f7fbf1d69a648c564e257bbd866b20f32992e41b8e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:59.329861Z","signature_b64":"QHF7RO+WSlNx/TMIk8MgmJvu2ds1hzGQzJYiPqFvJG0NdWU9623DTDd70Mts9U9PogrJ0lUxhDOBQfZYNMruBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa93b7b21e0b5f0fd5783559caabac26a94f31e311297d8dd98fb06c3dae3045","last_reissued_at":"2026-07-05T11:54:59.329395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:59.329395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Data Fusion via Subsampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Haiying Wang, Jing Wang, Kun Chen","submitted_at":"2025-08-16T13:49:26Z","abstract_excerpt":"Data fusion and transfer learning are rapidly growing fields that enhance model performance for a target population by leveraging other related data sources or tasks. The challenges lie in the various potential heterogeneities between the target and external data, as well as various practical concerns that prevent a na\\\"ive data integration. We consider a realistic scenario where the target data is limited in size while the external data is large but contaminated with outliers; such data contamination, along with other computational and operational constraints, necessitates proper selection or"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12048","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/2508.12048/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":"2508.12048","created_at":"2026-07-05T11:54:59.329454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12048v1","created_at":"2026-07-05T11:54:59.329454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12048","created_at":"2026-07-05T11:54:59.329454+00:00"},{"alias_kind":"pith_short_12","alias_value":"7KJ3PMQ6BNPQ","created_at":"2026-07-05T11:54:59.329454+00:00"},{"alias_kind":"pith_short_16","alias_value":"7KJ3PMQ6BNPQ7VLY","created_at":"2026-07-05T11:54:59.329454+00:00"},{"alias_kind":"pith_short_8","alias_value":"7KJ3PMQ6","created_at":"2026-07-05T11:54:59.329454+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00376","citing_title":"Distributed Prediction under Heterogeneity with Unidentifiable Parameter","ref_index":163,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2","json":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2.json","graph_json":"https://pith.science/api/pith-number/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/graph.json","events_json":"https://pith.science/api/pith-number/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/events.json","paper":"https://pith.science/paper/7KJ3PMQ6"},"agent_actions":{"view_html":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2","download_json":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2.json","view_paper":"https://pith.science/paper/7KJ3PMQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12048&json=true","fetch_graph":"https://pith.science/api/pith-number/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/graph.json","fetch_events":"https://pith.science/api/pith-number/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/action/storage_attestation","attest_author":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/action/author_attestation","sign_citation":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/action/citation_signature","submit_replication":"https://pith.science/pith/7KJ3PMQ6BNPQ7VLYGVM4VK5ME2/action/replication_record"}},"created_at":"2026-07-05T11:54:59.329454+00:00","updated_at":"2026-07-05T11:54:59.329454+00:00"}