{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2W3VWLBK5KNH2ONLMWUWQGAH65","short_pith_number":"pith:2W3VWLBK","schema_version":"1.0","canonical_sha256":"d5b75b2c2aea9a7d39ab65a9681807f779771e840cacca936407506f620606c9","source":{"kind":"arxiv","id":"2404.09541","version":1},"attestation_state":"computed","paper":{"title":"Application of the representative measure approach to assess the reliability of decision trees in dealing with unseen vehicle collision data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eduardo Paluzo-Hidalgo, Javier Perera-Lago, Matteo Rucco, Sara Narteni, V\\'ictor Toscano-Dur\\'an","submitted_at":"2024-04-15T08:06:54Z","abstract_excerpt":"Machine learning algorithms are fundamental components of novel data-informed Artificial Intelligence architecture. In this domain, the imperative role of representative datasets is a cornerstone in shaping the trajectory of artificial intelligence (AI) development. Representative datasets are needed to train machine learning components properly. Proper training has multiple impacts: it reduces the final model's complexity, power, and uncertainties. In this paper, we investigate the reliability of the $\\varepsilon$-representativeness method to assess the dataset similarity from a theoretical p"},"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":"2404.09541","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-15T08:06:54Z","cross_cats_sorted":[],"title_canon_sha256":"0a43f0f2b48d007d3a0ab75b1abe6e158a0fc19339700e69287a9380e700fbfc","abstract_canon_sha256":"4b3a4236dc2139367552c5e452af22b7118f35dd67ce2bcf2a5145c5380e32f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:08.194999Z","signature_b64":"ib0S/9PdzH3KP/Hm7AS0+qSDvu/FU7KzZGwwyqY06DQ5RpHut+IoY3QHI5kwaWs/1SC7/rt/v/i9JQHn0J8iDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5b75b2c2aea9a7d39ab65a9681807f779771e840cacca936407506f620606c9","last_reissued_at":"2026-07-05T08:08:08.194573Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:08.194573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Application of the representative measure approach to assess the reliability of decision trees in dealing with unseen vehicle collision data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eduardo Paluzo-Hidalgo, Javier Perera-Lago, Matteo Rucco, Sara Narteni, V\\'ictor Toscano-Dur\\'an","submitted_at":"2024-04-15T08:06:54Z","abstract_excerpt":"Machine learning algorithms are fundamental components of novel data-informed Artificial Intelligence architecture. In this domain, the imperative role of representative datasets is a cornerstone in shaping the trajectory of artificial intelligence (AI) development. Representative datasets are needed to train machine learning components properly. Proper training has multiple impacts: it reduces the final model's complexity, power, and uncertainties. In this paper, we investigate the reliability of the $\\varepsilon$-representativeness method to assess the dataset similarity from a theoretical p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09541","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/2404.09541/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":"2404.09541","created_at":"2026-07-05T08:08:08.194634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09541v1","created_at":"2026-07-05T08:08:08.194634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09541","created_at":"2026-07-05T08:08:08.194634+00:00"},{"alias_kind":"pith_short_12","alias_value":"2W3VWLBK5KNH","created_at":"2026-07-05T08:08:08.194634+00:00"},{"alias_kind":"pith_short_16","alias_value":"2W3VWLBK5KNH2ONL","created_at":"2026-07-05T08:08:08.194634+00:00"},{"alias_kind":"pith_short_8","alias_value":"2W3VWLBK","created_at":"2026-07-05T08:08:08.194634+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/2W3VWLBK5KNH2ONLMWUWQGAH65","json":"https://pith.science/pith/2W3VWLBK5KNH2ONLMWUWQGAH65.json","graph_json":"https://pith.science/api/pith-number/2W3VWLBK5KNH2ONLMWUWQGAH65/graph.json","events_json":"https://pith.science/api/pith-number/2W3VWLBK5KNH2ONLMWUWQGAH65/events.json","paper":"https://pith.science/paper/2W3VWLBK"},"agent_actions":{"view_html":"https://pith.science/pith/2W3VWLBK5KNH2ONLMWUWQGAH65","download_json":"https://pith.science/pith/2W3VWLBK5KNH2ONLMWUWQGAH65.json","view_paper":"https://pith.science/paper/2W3VWLBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09541&json=true","fetch_graph":"https://pith.science/api/pith-number/2W3VWLBK5KNH2ONLMWUWQGAH65/graph.json","fetch_events":"https://pith.science/api/pith-number/2W3VWLBK5KNH2ONLMWUWQGAH65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2W3VWLBK5KNH2ONLMWUWQGAH65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2W3VWLBK5KNH2ONLMWUWQGAH65/action/storage_attestation","attest_author":"https://pith.science/pith/2W3VWLBK5KNH2ONLMWUWQGAH65/action/author_attestation","sign_citation":"https://pith.science/pith/2W3VWLBK5KNH2ONLMWUWQGAH65/action/citation_signature","submit_replication":"https://pith.science/pith/2W3VWLBK5KNH2ONLMWUWQGAH65/action/replication_record"}},"created_at":"2026-07-05T08:08:08.194634+00:00","updated_at":"2026-07-05T08:08:08.194634+00:00"}