{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UNAPBWDYQ3JL2KE2Q52LLBBAIJ","short_pith_number":"pith:UNAPBWDY","canonical_record":{"source":{"id":"2105.13783","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-27T11:56:13Z","cross_cats_sorted":[],"title_canon_sha256":"9adc48d45452233de7fcdbc86db338959816827dcec8f7536e4a52c848cef6d9","abstract_canon_sha256":"12f48f7b7daaf648bcf5793d29dc53bde572dd028f613fe1459ad144feebe0ce"},"schema_version":"1.0"},"canonical_sha256":"a340f0d87886d2bd289a8774b5842042459e816f362b9572a15d813abd6bd5a1","source":{"kind":"arxiv","id":"2105.13783","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.13783","created_at":"2026-07-05T02:54:56Z"},{"alias_kind":"arxiv_version","alias_value":"2105.13783v2","created_at":"2026-07-05T02:54:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13783","created_at":"2026-07-05T02:54:56Z"},{"alias_kind":"pith_short_12","alias_value":"UNAPBWDYQ3JL","created_at":"2026-07-05T02:54:56Z"},{"alias_kind":"pith_short_16","alias_value":"UNAPBWDYQ3JL2KE2","created_at":"2026-07-05T02:54:56Z"},{"alias_kind":"pith_short_8","alias_value":"UNAPBWDY","created_at":"2026-07-05T02:54:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UNAPBWDYQ3JL2KE2Q52LLBBAIJ","target":"record","payload":{"canonical_record":{"source":{"id":"2105.13783","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-27T11:56:13Z","cross_cats_sorted":[],"title_canon_sha256":"9adc48d45452233de7fcdbc86db338959816827dcec8f7536e4a52c848cef6d9","abstract_canon_sha256":"12f48f7b7daaf648bcf5793d29dc53bde572dd028f613fe1459ad144feebe0ce"},"schema_version":"1.0"},"canonical_sha256":"a340f0d87886d2bd289a8774b5842042459e816f362b9572a15d813abd6bd5a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:56.215172Z","signature_b64":"9CkFjGnO/9dRYrXyrTqZnr0WVtoEoRkAlHmN/QNT4pi7pZKBQqoHP2WZlDSxzwdwTpOLaeWcnubmSZqJKPXuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a340f0d87886d2bd289a8774b5842042459e816f362b9572a15d813abd6bd5a1","last_reissued_at":"2026-07-05T02:54:56.214776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:56.214776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.13783","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:54:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MuhFy+6nfQOAA5CvHy6fGiUtQqna9QVZRMPeeG0cV/jXbt91c8jYKRpDbQ6MQ0bklSYrQ0laWq6P/fdEgTdrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T15:55:11.976779Z"},"content_sha256":"0b0fcb85b30e2b7c3a060adb707eb27044fd8c3e4125363a7f5a9f3c82926e4e","schema_version":"1.0","event_id":"sha256:0b0fcb85b30e2b7c3a060adb707eb27044fd8c3e4125363a7f5a9f3c82926e4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UNAPBWDYQ3JL2KE2Q52LLBBAIJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantile Encoder: Tackling High Cardinality Categorical Features in Regression Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlos Mougan, David Masip, Jordi Nin, Oriol Pujol","submitted_at":"2021-05-27T11:56:13Z","abstract_excerpt":"Regression problems have been widely studied in machinelearning literature resulting in a plethora of regression models and performance measures. However, there are few techniques specially dedicated to solve the problem of how to incorporate categorical features to regression problems. Usually, categorical feature encoders are general enough to cover both classification and regression problems. This lack of specificity results in underperforming regression models. In this paper,we provide an in-depth analysis of how to tackle high cardinality categor-ical features with the quantile. Our propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13783","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/2105.13783/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:54:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0sZDKcSqEh2ydOe9O2QSHZApeN6SiJ15SJbfhAgQpopGBZR/88CYoW+cBh7MHwXT+zl0AwdF+PPGdu+TrJibCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T15:55:11.977141Z"},"content_sha256":"5fcfb649ea2c7dcc7b3115373a2a87d3acf9b5544663234f7230bb5f62a95a97","schema_version":"1.0","event_id":"sha256:5fcfb649ea2c7dcc7b3115373a2a87d3acf9b5544663234f7230bb5f62a95a97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UNAPBWDYQ3JL2KE2Q52LLBBAIJ/bundle.json","state_url":"https://pith.science/pith/UNAPBWDYQ3JL2KE2Q52LLBBAIJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UNAPBWDYQ3JL2KE2Q52LLBBAIJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-14T15:55:11Z","links":{"resolver":"https://pith.science/pith/UNAPBWDYQ3JL2KE2Q52LLBBAIJ","bundle":"https://pith.science/pith/UNAPBWDYQ3JL2KE2Q52LLBBAIJ/bundle.json","state":"https://pith.science/pith/UNAPBWDYQ3JL2KE2Q52LLBBAIJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UNAPBWDYQ3JL2KE2Q52LLBBAIJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UNAPBWDYQ3JL2KE2Q52LLBBAIJ","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":"12f48f7b7daaf648bcf5793d29dc53bde572dd028f613fe1459ad144feebe0ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-27T11:56:13Z","title_canon_sha256":"9adc48d45452233de7fcdbc86db338959816827dcec8f7536e4a52c848cef6d9"},"schema_version":"1.0","source":{"id":"2105.13783","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.13783","created_at":"2026-07-05T02:54:56Z"},{"alias_kind":"arxiv_version","alias_value":"2105.13783v2","created_at":"2026-07-05T02:54:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13783","created_at":"2026-07-05T02:54:56Z"},{"alias_kind":"pith_short_12","alias_value":"UNAPBWDYQ3JL","created_at":"2026-07-05T02:54:56Z"},{"alias_kind":"pith_short_16","alias_value":"UNAPBWDYQ3JL2KE2","created_at":"2026-07-05T02:54:56Z"},{"alias_kind":"pith_short_8","alias_value":"UNAPBWDY","created_at":"2026-07-05T02:54:56Z"}],"graph_snapshots":[{"event_id":"sha256:5fcfb649ea2c7dcc7b3115373a2a87d3acf9b5544663234f7230bb5f62a95a97","target":"graph","created_at":"2026-07-05T02:54:56Z","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/2105.13783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Regression problems have been widely studied in machinelearning literature resulting in a plethora of regression models and performance measures. However, there are few techniques specially dedicated to solve the problem of how to incorporate categorical features to regression problems. Usually, categorical feature encoders are general enough to cover both classification and regression problems. This lack of specificity results in underperforming regression models. In this paper,we provide an in-depth analysis of how to tackle high cardinality categor-ical features with the quantile. Our propo","authors_text":"Carlos Mougan, David Masip, Jordi Nin, Oriol Pujol","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-27T11:56:13Z","title":"Quantile Encoder: Tackling High Cardinality Categorical Features in Regression Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13783","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":"sha256:0b0fcb85b30e2b7c3a060adb707eb27044fd8c3e4125363a7f5a9f3c82926e4e","target":"record","created_at":"2026-07-05T02:54:56Z","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":"12f48f7b7daaf648bcf5793d29dc53bde572dd028f613fe1459ad144feebe0ce","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-27T11:56:13Z","title_canon_sha256":"9adc48d45452233de7fcdbc86db338959816827dcec8f7536e4a52c848cef6d9"},"schema_version":"1.0","source":{"id":"2105.13783","kind":"arxiv","version":2}},"canonical_sha256":"a340f0d87886d2bd289a8774b5842042459e816f362b9572a15d813abd6bd5a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a340f0d87886d2bd289a8774b5842042459e816f362b9572a15d813abd6bd5a1","first_computed_at":"2026-07-05T02:54:56.214776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:54:56.214776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9CkFjGnO/9dRYrXyrTqZnr0WVtoEoRkAlHmN/QNT4pi7pZKBQqoHP2WZlDSxzwdwTpOLaeWcnubmSZqJKPXuCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:54:56.215172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.13783","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b0fcb85b30e2b7c3a060adb707eb27044fd8c3e4125363a7f5a9f3c82926e4e","sha256:5fcfb649ea2c7dcc7b3115373a2a87d3acf9b5544663234f7230bb5f62a95a97"],"state_sha256":"7081f093f6d75901ae6f60218e4237349f653d3d1b1a75bc1d6978fa328cb74f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A2s0lfdVwQ4fqvuEk9q4/oRAH+kI864J3wIeJ2/00pv4vTgteCDHMn73QnEH5cn7S11o/bX3lbJle3GoRXkmCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T15:55:11.979195Z","bundle_sha256":"0f9af5e39b76a7ea5dae0865797fbc202c5e24e02a2e78cf32e53aaaf21934f8"}}