{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:KX3JBMJF7WCMD4E5WMSV2HJ22B","short_pith_number":"pith:KX3JBMJF","canonical_record":{"source":{"id":"1806.00979","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-04T06:46:22Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8fac2d789d2447b8133e38f1b948bf729b58d8a1d074df3d26811809ae9db0ec","abstract_canon_sha256":"231f60f8162f38fda2aaf34796c49bb9eed2ff27f05d53f0333749bf47981643"},"schema_version":"1.0"},"canonical_sha256":"55f690b125fd84c1f09db3255d1d3ad06666ab09f63d72e2a10c5b0bca9b1e4e","source":{"kind":"arxiv","id":"1806.00979","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.00979","created_at":"2026-05-18T00:14:17Z"},{"alias_kind":"arxiv_version","alias_value":"1806.00979v1","created_at":"2026-05-18T00:14:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00979","created_at":"2026-05-18T00:14:17Z"},{"alias_kind":"pith_short_12","alias_value":"KX3JBMJF7WCM","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KX3JBMJF7WCMD4E5","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KX3JBMJF","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:KX3JBMJF7WCMD4E5WMSV2HJ22B","target":"record","payload":{"canonical_record":{"source":{"id":"1806.00979","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-04T06:46:22Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8fac2d789d2447b8133e38f1b948bf729b58d8a1d074df3d26811809ae9db0ec","abstract_canon_sha256":"231f60f8162f38fda2aaf34796c49bb9eed2ff27f05d53f0333749bf47981643"},"schema_version":"1.0"},"canonical_sha256":"55f690b125fd84c1f09db3255d1d3ad06666ab09f63d72e2a10c5b0bca9b1e4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:17.836572Z","signature_b64":"Vg2SBEos4Dx8jq0m7xzDv+CXO3i4+jOj5GsXc2rEDX4+JWbg4KFXvZVqRyEBGVYIbxpn9M49977S4HmP/OaMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55f690b125fd84c1f09db3255d1d3ad06666ab09f63d72e2a10c5b0bca9b1e4e","last_reissued_at":"2026-05-18T00:14:17.835994Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:17.835994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.00979","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":"2026-05-18T00:14:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AiRy7DH8CXYy8FL0wkDjD3GWGe2uc9pVlDCBzbZjRp1iCxoF3+d0yT0lxCp3omfoW5vOwkH+L4jgoIBSVW/WBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T06:44:23.541696Z"},"content_sha256":"bc401be4fa95e6373f9b330946bb658e2e9102a3e8f297ad19c1fc28c32424ad","schema_version":"1.0","event_id":"sha256:bc401be4fa95e6373f9b330946bb658e2e9102a3e8f297ad19c1fc28c32424ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:KX3JBMJF7WCMD4E5WMSV2HJ22B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Similarity encoding for learning with dirty categorical variables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bal\\'azs K\\'egl (LAL, CNRS), Ga\\\"el Varoquaux (Parietal), Patricio Cerda (PARIETAL)","submitted_at":"2018-06-04T06:46:22Z","abstract_excerpt":"For statistical learning, categorical variables in a table are usually considered as discrete entities and encoded separately to feature vectors, e.g., with one-hot encoding. \"Dirty\" non-curated data gives rise to categorical variables with a very high cardinality but redundancy: several categories reflect the same entity. In databases, this issue is typically solved with a deduplication step. We show that a simple approach that exposes the redundancy to the learning algorithm brings significant gains. We study a generalization of one-hot encoding, similarity encoding, that builds feature vect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00979","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":"2026-05-18T00:14:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mKZBAumTIl8uZdFBr4M2e3q99eRnjj3s54uNVoU6oacPb7aS4VI0zSxZK1YqBm19wlJBsoXSfLmpBFBFfMVoAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T06:44:23.542502Z"},"content_sha256":"8aac960618ee99df86d27880e31e03ef5b456309723801195abe9509942e6785","schema_version":"1.0","event_id":"sha256:8aac960618ee99df86d27880e31e03ef5b456309723801195abe9509942e6785"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B/bundle.json","state_url":"https://pith.science/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B/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":"2026-06-06T06:44:23Z","links":{"resolver":"https://pith.science/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B","bundle":"https://pith.science/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B/bundle.json","state":"https://pith.science/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KX3JBMJF7WCMD4E5WMSV2HJ22B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KX3JBMJF7WCMD4E5WMSV2HJ22B","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":"231f60f8162f38fda2aaf34796c49bb9eed2ff27f05d53f0333749bf47981643","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-04T06:46:22Z","title_canon_sha256":"8fac2d789d2447b8133e38f1b948bf729b58d8a1d074df3d26811809ae9db0ec"},"schema_version":"1.0","source":{"id":"1806.00979","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.00979","created_at":"2026-05-18T00:14:17Z"},{"alias_kind":"arxiv_version","alias_value":"1806.00979v1","created_at":"2026-05-18T00:14:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00979","created_at":"2026-05-18T00:14:17Z"},{"alias_kind":"pith_short_12","alias_value":"KX3JBMJF7WCM","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KX3JBMJF7WCMD4E5","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KX3JBMJF","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:8aac960618ee99df86d27880e31e03ef5b456309723801195abe9509942e6785","target":"graph","created_at":"2026-05-18T00:14:17Z","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":"For statistical learning, categorical variables in a table are usually considered as discrete entities and encoded separately to feature vectors, e.g., with one-hot encoding. \"Dirty\" non-curated data gives rise to categorical variables with a very high cardinality but redundancy: several categories reflect the same entity. In databases, this issue is typically solved with a deduplication step. We show that a simple approach that exposes the redundancy to the learning algorithm brings significant gains. We study a generalization of one-hot encoding, similarity encoding, that builds feature vect","authors_text":"Bal\\'azs K\\'egl (LAL, CNRS), Ga\\\"el Varoquaux (Parietal), Patricio Cerda (PARIETAL)","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-04T06:46:22Z","title":"Similarity encoding for learning with dirty categorical variables"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00979","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:bc401be4fa95e6373f9b330946bb658e2e9102a3e8f297ad19c1fc28c32424ad","target":"record","created_at":"2026-05-18T00:14:17Z","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":"231f60f8162f38fda2aaf34796c49bb9eed2ff27f05d53f0333749bf47981643","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-04T06:46:22Z","title_canon_sha256":"8fac2d789d2447b8133e38f1b948bf729b58d8a1d074df3d26811809ae9db0ec"},"schema_version":"1.0","source":{"id":"1806.00979","kind":"arxiv","version":1}},"canonical_sha256":"55f690b125fd84c1f09db3255d1d3ad06666ab09f63d72e2a10c5b0bca9b1e4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55f690b125fd84c1f09db3255d1d3ad06666ab09f63d72e2a10c5b0bca9b1e4e","first_computed_at":"2026-05-18T00:14:17.835994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:17.835994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vg2SBEos4Dx8jq0m7xzDv+CXO3i4+jOj5GsXc2rEDX4+JWbg4KFXvZVqRyEBGVYIbxpn9M49977S4HmP/OaMBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:17.836572Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.00979","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc401be4fa95e6373f9b330946bb658e2e9102a3e8f297ad19c1fc28c32424ad","sha256:8aac960618ee99df86d27880e31e03ef5b456309723801195abe9509942e6785"],"state_sha256":"5fd2f7f55f41ff55eee8b684543242e3d22ce44b7c57fade7be15d7abe1de618"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ng2CCVaDvRYXLQobsprqa1XjLjnxC4jO8L7EAIC8j+nfpcvFT/er5pp7hMkgpE9HtYHudLW1CWL+BmSqb+tIBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T06:44:23.546540Z","bundle_sha256":"2508994c519a2563f4caeefa4b9328a2411a8c04846c744d8f762bc1f1a1c776"}}