{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SHLVTORMPPJWATWM7L2CYBH5YE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c32e0a8a8570d01e57ce355c6ecba45da6cd215ee9d72548e11e4e89227472b1","cross_cats_sorted":["cs.DM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2021-05-08T18:04:09Z","title_canon_sha256":"42201c917451c61abd1af3b1a71f1474cb2faefc8ed760187654a32df78d9442"},"schema_version":"1.0","source":{"id":"2105.03753","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.03753","created_at":"2026-07-05T03:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2105.03753v2","created_at":"2026-07-05T03:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03753","created_at":"2026-07-05T03:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"SHLVTORMPPJW","created_at":"2026-07-05T03:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"SHLVTORMPPJWATWM","created_at":"2026-07-05T03:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"SHLVTORM","created_at":"2026-07-05T03:07:06Z"}],"graph_snapshots":[{"event_id":"sha256:e6d24c7fbc98a10a5f678f5d12bda0a30cde02849a529e3bbd66703766a46318","target":"graph","created_at":"2026-07-05T03:07:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2105.03753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We develop new algorithmic methods with provable guarantees for feature selection in regard to categorical data clustering. While feature selection is one of the most common approaches to reduce dimensionality in practice, most of the known feature selection methods are heuristics. We study the following mathematical model. We assume that there are some inadvertent (or undesirable) features of the input data that unnecessarily increase the cost of clustering. Consequently, we want to select a subset of the original features from the data such that there is a small-cost clustering on the select","authors_text":"Fedor V. Fomin, Kirill Simonov, Petr A. Golovach, Sayan Bandyapadhyay","cross_cats":["cs.DM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2021-05-08T18:04:09Z","title":"Parameterized Complexity of Feature Selection for Categorical Data Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03753","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:306f755bb5f2d354efba0e324e19c7bf165a7a42591ee90c7a1d847c87033494","target":"record","created_at":"2026-07-05T03:07:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c32e0a8a8570d01e57ce355c6ecba45da6cd215ee9d72548e11e4e89227472b1","cross_cats_sorted":["cs.DM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2021-05-08T18:04:09Z","title_canon_sha256":"42201c917451c61abd1af3b1a71f1474cb2faefc8ed760187654a32df78d9442"},"schema_version":"1.0","source":{"id":"2105.03753","kind":"arxiv","version":2}},"canonical_sha256":"91d759ba2c7bd3604eccfaf42c04fdc116d9cda5589c5ffa9a6d80429a75378e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91d759ba2c7bd3604eccfaf42c04fdc116d9cda5589c5ffa9a6d80429a75378e","first_computed_at":"2026-07-05T03:07:06.419274Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:07:06.419274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xSzzwoqPkVBXkPpOyKeazQ/OBbLI4F494UT0jekBUu4PyU1Jd+1H+spcvZIHFkxCwS7ngzqscdJ9I/F/Gj3bAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:07:06.419688Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.03753","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:306f755bb5f2d354efba0e324e19c7bf165a7a42591ee90c7a1d847c87033494","sha256:e6d24c7fbc98a10a5f678f5d12bda0a30cde02849a529e3bbd66703766a46318"],"state_sha256":"a84e203b554876911a67158d028d316d4dc673253d9a362bfa575dfe755ab44a"}