{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3DDR7LZZQHCQN4AVIHYTMLKI63","short_pith_number":"pith:3DDR7LZZ","schema_version":"1.0","canonical_sha256":"d8c71faf3981c506f01541f1362d48f6ff6b18f971659fc83bc765c8a8084f85","source":{"kind":"arxiv","id":"2406.18902","version":2},"attestation_state":"computed","paper":{"title":"Statistical Test for Feature Selection Pipelines by Selective Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ichiro Takeuchi, Shuichi Nishino, Tatsuya Matsukawa, Tomohiro Shiraishi","submitted_at":"2024-06-27T05:30:08Z","abstract_excerpt":"A data analysis pipeline is a structured sequence of steps that transforms raw data into meaningful insights by integrating various analysis algorithms. In this paper, we propose a novel statistical test to assess the significance of data analysis pipelines in feature selection problems. Our approach enables the systematic development of valid statistical tests applicable to any feature selection pipeline composed of predefined components. We develop this framework based on selective inference, a statistical technique that has recently gained attention for data-driven hypotheses. As a proof of"},"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":"2406.18902","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-06-27T05:30:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8dcbd84c38d242a3c0e23366fcddf97070ad2b1b55fd7a385262d71f8371d0b3","abstract_canon_sha256":"489a77d842a6ffdabd347512a3419b8caa4c23ae23f320393d3611f72ba9bcac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:00.411285Z","signature_b64":"/UVLE2BU66vDcBL9JTrqD/Mq1+yXBav+2Hl02nWuXjS/gd+38dkRXe8yEObgQ58V6YWx3E3rtrN9DKc006zoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8c71faf3981c506f01541f1362d48f6ff6b18f971659fc83bc765c8a8084f85","last_reissued_at":"2026-07-05T09:20:00.410807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:00.410807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical Test for Feature Selection Pipelines by Selective Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ichiro Takeuchi, Shuichi Nishino, Tatsuya Matsukawa, Tomohiro Shiraishi","submitted_at":"2024-06-27T05:30:08Z","abstract_excerpt":"A data analysis pipeline is a structured sequence of steps that transforms raw data into meaningful insights by integrating various analysis algorithms. In this paper, we propose a novel statistical test to assess the significance of data analysis pipelines in feature selection problems. Our approach enables the systematic development of valid statistical tests applicable to any feature selection pipeline composed of predefined components. We develop this framework based on selective inference, a statistical technique that has recently gained attention for data-driven hypotheses. As a proof of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18902","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/2406.18902/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":"2406.18902","created_at":"2026-07-05T09:20:00.410865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18902v2","created_at":"2026-07-05T09:20:00.410865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18902","created_at":"2026-07-05T09:20:00.410865+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DDR7LZZQHCQ","created_at":"2026-07-05T09:20:00.410865+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DDR7LZZQHCQN4AV","created_at":"2026-07-05T09:20:00.410865+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DDR7LZZ","created_at":"2026-07-05T09:20:00.410865+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.01097","citing_title":"Understanding LoRA as Knowledge Memory: An Empirical Analysis","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DDR7LZZQHCQN4AVIHYTMLKI63","json":"https://pith.science/pith/3DDR7LZZQHCQN4AVIHYTMLKI63.json","graph_json":"https://pith.science/api/pith-number/3DDR7LZZQHCQN4AVIHYTMLKI63/graph.json","events_json":"https://pith.science/api/pith-number/3DDR7LZZQHCQN4AVIHYTMLKI63/events.json","paper":"https://pith.science/paper/3DDR7LZZ"},"agent_actions":{"view_html":"https://pith.science/pith/3DDR7LZZQHCQN4AVIHYTMLKI63","download_json":"https://pith.science/pith/3DDR7LZZQHCQN4AVIHYTMLKI63.json","view_paper":"https://pith.science/paper/3DDR7LZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18902&json=true","fetch_graph":"https://pith.science/api/pith-number/3DDR7LZZQHCQN4AVIHYTMLKI63/graph.json","fetch_events":"https://pith.science/api/pith-number/3DDR7LZZQHCQN4AVIHYTMLKI63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DDR7LZZQHCQN4AVIHYTMLKI63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DDR7LZZQHCQN4AVIHYTMLKI63/action/storage_attestation","attest_author":"https://pith.science/pith/3DDR7LZZQHCQN4AVIHYTMLKI63/action/author_attestation","sign_citation":"https://pith.science/pith/3DDR7LZZQHCQN4AVIHYTMLKI63/action/citation_signature","submit_replication":"https://pith.science/pith/3DDR7LZZQHCQN4AVIHYTMLKI63/action/replication_record"}},"created_at":"2026-07-05T09:20:00.410865+00:00","updated_at":"2026-07-05T09:20:00.410865+00:00"}