{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MAWUB6BXJWYKTT3SAR2ELAVHUM","short_pith_number":"pith:MAWUB6BX","schema_version":"1.0","canonical_sha256":"602d40f8374db0a9cf7204744582a7a33d532f9eb97df758b89520cdd2ca2f93","source":{"kind":"arxiv","id":"2403.10175","version":2},"attestation_state":"computed","paper":{"title":"A Short Survey on Importance Weighting for Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hideitsu Hino, Masanari Kimura","submitted_at":"2024-03-15T10:31:46Z","abstract_excerpt":"Importance weighting is a fundamental procedure in statistics and machine learning that weights the objective function or probability distribution based on the importance of the instance in some sense. The simplicity and usefulness of the idea has led to many applications of importance weighting. For example, it is known that supervised learning under an assumption about the difference between the training and test distributions, called distribution shift, can guarantee statistically desirable properties through importance weighting by their density ratio. This survey summarizes the broad appl"},"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":"2403.10175","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T10:31:46Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"464f122bb249e418bc467e75b021bf23a573dea76fecd95a3a1a44c100819fce","abstract_canon_sha256":"7f4f2fe7fc6894eb3a7b896deb633038be1d380e12db8eb66accc00e3682a2a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:50.659301Z","signature_b64":"TwmnxyhDex7Ppe00onkPDacsTEqgQO7QIqyYGAv6lG0q50DaVNcCr2BQb/gIySle0PiL3a5DhWm7Zcq4HlRSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"602d40f8374db0a9cf7204744582a7a33d532f9eb97df758b89520cdd2ca2f93","last_reissued_at":"2026-07-05T08:18:50.658755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:50.658755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Short Survey on Importance Weighting for Machine Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hideitsu Hino, Masanari Kimura","submitted_at":"2024-03-15T10:31:46Z","abstract_excerpt":"Importance weighting is a fundamental procedure in statistics and machine learning that weights the objective function or probability distribution based on the importance of the instance in some sense. The simplicity and usefulness of the idea has led to many applications of importance weighting. For example, it is known that supervised learning under an assumption about the difference between the training and test distributions, called distribution shift, can guarantee statistically desirable properties through importance weighting by their density ratio. This survey summarizes the broad appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10175","kind":"arxiv","version":2},"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/2403.10175/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":"2403.10175","created_at":"2026-07-05T08:18:50.658808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10175v2","created_at":"2026-07-05T08:18:50.658808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10175","created_at":"2026-07-05T08:18:50.658808+00:00"},{"alias_kind":"pith_short_12","alias_value":"MAWUB6BXJWYK","created_at":"2026-07-05T08:18:50.658808+00:00"},{"alias_kind":"pith_short_16","alias_value":"MAWUB6BXJWYKTT3S","created_at":"2026-07-05T08:18:50.658808+00:00"},{"alias_kind":"pith_short_8","alias_value":"MAWUB6BX","created_at":"2026-07-05T08:18:50.658808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20824","citing_title":"Stabilizing In-Context Multi-Source Domain Adaptation for Biomedical Images Through Controls","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00563","citing_title":"A Practical Upper Bound on Selection Bias Effects in Medical Prediction Models","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2410.16636","citing_title":"General Frameworks for Conditional Two-Sample Testing","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08843","citing_title":"M$^3$: Reframing Training Measures for Discretized Physical Simulations","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20824","citing_title":"Stabilizing In-Context Multi-Source Domain Adaptation for Biomedical Images Through Controls","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MAWUB6BXJWYKTT3SAR2ELAVHUM","json":"https://pith.science/pith/MAWUB6BXJWYKTT3SAR2ELAVHUM.json","graph_json":"https://pith.science/api/pith-number/MAWUB6BXJWYKTT3SAR2ELAVHUM/graph.json","events_json":"https://pith.science/api/pith-number/MAWUB6BXJWYKTT3SAR2ELAVHUM/events.json","paper":"https://pith.science/paper/MAWUB6BX"},"agent_actions":{"view_html":"https://pith.science/pith/MAWUB6BXJWYKTT3SAR2ELAVHUM","download_json":"https://pith.science/pith/MAWUB6BXJWYKTT3SAR2ELAVHUM.json","view_paper":"https://pith.science/paper/MAWUB6BX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10175&json=true","fetch_graph":"https://pith.science/api/pith-number/MAWUB6BXJWYKTT3SAR2ELAVHUM/graph.json","fetch_events":"https://pith.science/api/pith-number/MAWUB6BXJWYKTT3SAR2ELAVHUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MAWUB6BXJWYKTT3SAR2ELAVHUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MAWUB6BXJWYKTT3SAR2ELAVHUM/action/storage_attestation","attest_author":"https://pith.science/pith/MAWUB6BXJWYKTT3SAR2ELAVHUM/action/author_attestation","sign_citation":"https://pith.science/pith/MAWUB6BXJWYKTT3SAR2ELAVHUM/action/citation_signature","submit_replication":"https://pith.science/pith/MAWUB6BXJWYKTT3SAR2ELAVHUM/action/replication_record"}},"created_at":"2026-07-05T08:18:50.658808+00:00","updated_at":"2026-07-05T08:18:50.658808+00:00"}