{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BCZGLZHMR277AC5UE5TVNE23ET","short_pith_number":"pith:BCZGLZHM","canonical_record":{"source":{"id":"1904.13001","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-30T00:24:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2a0027ec18d6a7490f7064493ec09578ba480e835e8ee348505a1c7cbee3c376","abstract_canon_sha256":"f1c2a89d1b22b635c54f29f12cce74e189caf7e5c893dfe514b16dd04ff33b8a"},"schema_version":"1.0"},"canonical_sha256":"08b265e4ec8ebff00bb4276756935b24fd03c9a64648c359dca4e7c61155ebad","source":{"kind":"arxiv","id":"1904.13001","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.13001","created_at":"2026-05-17T23:47:24Z"},{"alias_kind":"arxiv_version","alias_value":"1904.13001v1","created_at":"2026-05-17T23:47:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.13001","created_at":"2026-05-17T23:47:24Z"},{"alias_kind":"pith_short_12","alias_value":"BCZGLZHMR277","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BCZGLZHMR277AC5U","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BCZGLZHM","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BCZGLZHMR277AC5UE5TVNE23ET","target":"record","payload":{"canonical_record":{"source":{"id":"1904.13001","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-30T00:24:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2a0027ec18d6a7490f7064493ec09578ba480e835e8ee348505a1c7cbee3c376","abstract_canon_sha256":"f1c2a89d1b22b635c54f29f12cce74e189caf7e5c893dfe514b16dd04ff33b8a"},"schema_version":"1.0"},"canonical_sha256":"08b265e4ec8ebff00bb4276756935b24fd03c9a64648c359dca4e7c61155ebad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:24.231258Z","signature_b64":"UtzSHid3OpgOHJ4pPOaTa2VlP03HD+9+FA1ZD8K3R1d4rFKgyvEmDwme+g6kaYIOAE9LCvhGQmdBrmWguPuiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08b265e4ec8ebff00bb4276756935b24fd03c9a64648c359dca4e7c61155ebad","last_reissued_at":"2026-05-17T23:47:24.230649Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:24.230649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.13001","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NB/nugKrrdWhXPsmuVhJF6GMA1Mxh0QkyL3ShUsFqqFtfwFRsvr7VymarQyshs0vuB+e8hFYCFJXBQoObvCnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T06:54:51.334750Z"},"content_sha256":"fce99148752f70b77cf63e61302980c86d56e514ae2e8b10c05ac835863be868","schema_version":"1.0","event_id":"sha256:fce99148752f70b77cf63e61302980c86d56e514ae2e8b10c05ac835863be868"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BCZGLZHMR277AC5UE5TVNE23ET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Encoding Categorical Variables with Conjugate Bayesian Models for WeWork Lead Scoring Engine","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Austin Slakey, Daniel Salas, Yoni Schamroth","submitted_at":"2019-04-30T00:24:06Z","abstract_excerpt":"Applied Data Scientists throughout various industries are commonly faced with the challenging task of encoding high-cardinality categorical features into digestible inputs for machine learning algorithms. This paper describes a Bayesian encoding technique developed for WeWork's lead scoring engine which outputs the probability of a person touring one of our office spaces based on interaction, enrichment, and geospatial data. We present a paradigm for ensemble modeling which mitigates the need to build complicated preprocessing and encoding schemes for categorical variables. In particular, doma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.13001","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":""},"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":"2026-05-17T23:47:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VVzwayHD8khq5EnMhZWQhzP70vyHGyE90k8/CMOYLZtnBN1ZME1bRiezalZ3e/deMdEcP3yOkrMDqzYTjWyBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T06:54:51.335103Z"},"content_sha256":"cad7c3d8d2dafa7efcf0f6230fd33e43fca778c7f9397b78b1efa805ab54fc32","schema_version":"1.0","event_id":"sha256:cad7c3d8d2dafa7efcf0f6230fd33e43fca778c7f9397b78b1efa805ab54fc32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCZGLZHMR277AC5UE5TVNE23ET/bundle.json","state_url":"https://pith.science/pith/BCZGLZHMR277AC5UE5TVNE23ET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCZGLZHMR277AC5UE5TVNE23ET/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":"2026-05-30T06:54:51Z","links":{"resolver":"https://pith.science/pith/BCZGLZHMR277AC5UE5TVNE23ET","bundle":"https://pith.science/pith/BCZGLZHMR277AC5UE5TVNE23ET/bundle.json","state":"https://pith.science/pith/BCZGLZHMR277AC5UE5TVNE23ET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCZGLZHMR277AC5UE5TVNE23ET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BCZGLZHMR277AC5UE5TVNE23ET","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":"f1c2a89d1b22b635c54f29f12cce74e189caf7e5c893dfe514b16dd04ff33b8a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-30T00:24:06Z","title_canon_sha256":"2a0027ec18d6a7490f7064493ec09578ba480e835e8ee348505a1c7cbee3c376"},"schema_version":"1.0","source":{"id":"1904.13001","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.13001","created_at":"2026-05-17T23:47:24Z"},{"alias_kind":"arxiv_version","alias_value":"1904.13001v1","created_at":"2026-05-17T23:47:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.13001","created_at":"2026-05-17T23:47:24Z"},{"alias_kind":"pith_short_12","alias_value":"BCZGLZHMR277","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BCZGLZHMR277AC5U","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BCZGLZHM","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:cad7c3d8d2dafa7efcf0f6230fd33e43fca778c7f9397b78b1efa805ab54fc32","target":"graph","created_at":"2026-05-17T23:47:24Z","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"},"paper":{"abstract_excerpt":"Applied Data Scientists throughout various industries are commonly faced with the challenging task of encoding high-cardinality categorical features into digestible inputs for machine learning algorithms. This paper describes a Bayesian encoding technique developed for WeWork's lead scoring engine which outputs the probability of a person touring one of our office spaces based on interaction, enrichment, and geospatial data. We present a paradigm for ensemble modeling which mitigates the need to build complicated preprocessing and encoding schemes for categorical variables. In particular, doma","authors_text":"Austin Slakey, Daniel Salas, Yoni Schamroth","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-30T00:24:06Z","title":"Encoding Categorical Variables with Conjugate Bayesian Models for WeWork Lead Scoring Engine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.13001","kind":"arxiv","version":1},"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:fce99148752f70b77cf63e61302980c86d56e514ae2e8b10c05ac835863be868","target":"record","created_at":"2026-05-17T23:47:24Z","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":"f1c2a89d1b22b635c54f29f12cce74e189caf7e5c893dfe514b16dd04ff33b8a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-30T00:24:06Z","title_canon_sha256":"2a0027ec18d6a7490f7064493ec09578ba480e835e8ee348505a1c7cbee3c376"},"schema_version":"1.0","source":{"id":"1904.13001","kind":"arxiv","version":1}},"canonical_sha256":"08b265e4ec8ebff00bb4276756935b24fd03c9a64648c359dca4e7c61155ebad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08b265e4ec8ebff00bb4276756935b24fd03c9a64648c359dca4e7c61155ebad","first_computed_at":"2026-05-17T23:47:24.230649Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:24.230649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UtzSHid3OpgOHJ4pPOaTa2VlP03HD+9+FA1ZD8K3R1d4rFKgyvEmDwme+g6kaYIOAE9LCvhGQmdBrmWguPuiCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:24.231258Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.13001","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fce99148752f70b77cf63e61302980c86d56e514ae2e8b10c05ac835863be868","sha256:cad7c3d8d2dafa7efcf0f6230fd33e43fca778c7f9397b78b1efa805ab54fc32"],"state_sha256":"0804e8b4d06b1b2c06aac4194dc249857cc73686bb87230696215e6a94d76085"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YTVfT/nZJrPtX3JVypN8hatxo1HLXx0iwVDZzfR6T8d/5kBsaDbHKSfSthqZh9oixm2C3aY7tDYxtOI7/VC/Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T06:54:51.337251Z","bundle_sha256":"8a184917a2dfaec80c79ad4736068c9d98c0435c1046df2183d265850725df90"}}