{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H4F2RFRYT4OG5VOLYQTJQLEKOZ","short_pith_number":"pith:H4F2RFRY","schema_version":"1.0","canonical_sha256":"3f0ba896389f1c6ed5cbc426982c8a766c61ee023601354c6df194f0c094effe","source":{"kind":"arxiv","id":"2204.05389","version":1},"attestation_state":"computed","paper":{"title":"Random Similarity Forests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Dariusz Brzezinski, Maciej Piernik, Pawel Zawadzki","submitted_at":"2022-04-11T20:14:05Z","abstract_excerpt":"The wealth of data being gathered about humans and their surroundings drives new machine learning applications in various fields. Consequently, more and more often, classifiers are trained using not only numerical data but also complex data objects. For example, multi-omics analyses attempt to combine numerical descriptions with distributions, time series data, discrete sequences, and graphs. Such integration of data from different domains requires either omitting some of the data, creating separate models for different formats, or simplifying some of the data to adhere to a shared scale and f"},"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":"2204.05389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-11T20:14:05Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"d054f8c2099ad02b0bd4a4c83df810a5e237d24aa13ae94f333ba03fa13136d8","abstract_canon_sha256":"013e5588af8d69b694516a9adf60b7e95da313ec1c8d19eccb77aedd5638bc9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:57.518033Z","signature_b64":"07rGKqnYTqAD2oqMk/oI5VgEkrHVDp3l/cXWCnRbRyqYF4j4uMJKXMG+jUTRQwkwHl2RAzJIT7ISVneAwnIZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f0ba896389f1c6ed5cbc426982c8a766c61ee023601354c6df194f0c094effe","last_reissued_at":"2026-07-05T04:13:57.517660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:57.517660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random Similarity Forests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Dariusz Brzezinski, Maciej Piernik, Pawel Zawadzki","submitted_at":"2022-04-11T20:14:05Z","abstract_excerpt":"The wealth of data being gathered about humans and their surroundings drives new machine learning applications in various fields. Consequently, more and more often, classifiers are trained using not only numerical data but also complex data objects. For example, multi-omics analyses attempt to combine numerical descriptions with distributions, time series data, discrete sequences, and graphs. Such integration of data from different domains requires either omitting some of the data, creating separate models for different formats, or simplifying some of the data to adhere to a shared scale and f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.05389","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/2204.05389/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":"2204.05389","created_at":"2026-07-05T04:13:57.517716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.05389v1","created_at":"2026-07-05T04:13:57.517716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.05389","created_at":"2026-07-05T04:13:57.517716+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4F2RFRYT4OG","created_at":"2026-07-05T04:13:57.517716+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4F2RFRYT4OG5VOL","created_at":"2026-07-05T04:13:57.517716+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4F2RFRY","created_at":"2026-07-05T04:13:57.517716+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/H4F2RFRYT4OG5VOLYQTJQLEKOZ","json":"https://pith.science/pith/H4F2RFRYT4OG5VOLYQTJQLEKOZ.json","graph_json":"https://pith.science/api/pith-number/H4F2RFRYT4OG5VOLYQTJQLEKOZ/graph.json","events_json":"https://pith.science/api/pith-number/H4F2RFRYT4OG5VOLYQTJQLEKOZ/events.json","paper":"https://pith.science/paper/H4F2RFRY"},"agent_actions":{"view_html":"https://pith.science/pith/H4F2RFRYT4OG5VOLYQTJQLEKOZ","download_json":"https://pith.science/pith/H4F2RFRYT4OG5VOLYQTJQLEKOZ.json","view_paper":"https://pith.science/paper/H4F2RFRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.05389&json=true","fetch_graph":"https://pith.science/api/pith-number/H4F2RFRYT4OG5VOLYQTJQLEKOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/H4F2RFRYT4OG5VOLYQTJQLEKOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4F2RFRYT4OG5VOLYQTJQLEKOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4F2RFRYT4OG5VOLYQTJQLEKOZ/action/storage_attestation","attest_author":"https://pith.science/pith/H4F2RFRYT4OG5VOLYQTJQLEKOZ/action/author_attestation","sign_citation":"https://pith.science/pith/H4F2RFRYT4OG5VOLYQTJQLEKOZ/action/citation_signature","submit_replication":"https://pith.science/pith/H4F2RFRYT4OG5VOLYQTJQLEKOZ/action/replication_record"}},"created_at":"2026-07-05T04:13:57.517716+00:00","updated_at":"2026-07-05T04:13:57.517716+00:00"}