{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:OPH7XLKKHMXUMPZKXVWVHMLMUZ","short_pith_number":"pith:OPH7XLKK","canonical_record":{"source":{"id":"1703.08619","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-24T22:54:17Z","cross_cats_sorted":[],"title_canon_sha256":"e3f77d4eb341d5c0d5ec73724fcc2985dd3deb453f695974d6ce608522510ade","abstract_canon_sha256":"b5641f93694c6ac2a7b89a96bb6b381c70248379dcdc20d3c2ca735987047a6f"},"schema_version":"1.0"},"canonical_sha256":"73cffbad4a3b2f463f2abd6d53b16ca64428469c6f34ec2ac157668391563ecc","source":{"kind":"arxiv","id":"1703.08619","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.08619","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"arxiv_version","alias_value":"1703.08619v4","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08619","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"pith_short_12","alias_value":"OPH7XLKKHMXU","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OPH7XLKKHMXUMPZK","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OPH7XLKK","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:OPH7XLKKHMXUMPZKXVWVHMLMUZ","target":"record","payload":{"canonical_record":{"source":{"id":"1703.08619","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-24T22:54:17Z","cross_cats_sorted":[],"title_canon_sha256":"e3f77d4eb341d5c0d5ec73724fcc2985dd3deb453f695974d6ce608522510ade","abstract_canon_sha256":"b5641f93694c6ac2a7b89a96bb6b381c70248379dcdc20d3c2ca735987047a6f"},"schema_version":"1.0"},"canonical_sha256":"73cffbad4a3b2f463f2abd6d53b16ca64428469c6f34ec2ac157668391563ecc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:43.200597Z","signature_b64":"6n7dYpyhe6WrEmm5+DRF4j24wGMTsLquIUDHeR6sqPcxNrJ6qvk+UsjKr7mDxG3/7N5OevsTpgp8QQOZaC3mAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73cffbad4a3b2f463f2abd6d53b16ca64428469c6f34ec2ac157668391563ecc","last_reissued_at":"2026-05-17T23:56:43.200211Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:43.200211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.08619","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WpIeZxCDQDQ2bWoHil4/VjVBHfnuGRbDgPW16BKuR/qM0OhuMbUT/9aAUHLy7CEebJSfxBrfAcp0OlGgwye1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T14:15:45.294363Z"},"content_sha256":"50d9a5e29907cb74e55e823ad652b38e9fe073e974c3cfff0f17416b1f460b09","schema_version":"1.0","event_id":"sha256:50d9a5e29907cb74e55e823ad652b38e9fe073e974c3cfff0f17416b1f460b09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:OPH7XLKKHMXUMPZKXVWVHMLMUZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Binarsity: a penalization for one-hot encoded features in linear supervised learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Agathe Guilloux, Mokhtar Z. Alaya, Simon Bussy, St\\'ephane Ga\\\"iffas","submitted_at":"2017-03-24T22:54:17Z","abstract_excerpt":"This paper deals with the problem of large-scale linear supervised learning in settings where a large number of continuous features are available. We propose to combine the well-known trick of one-hot encoding of continuous features with a new penalization called \\emph{binarsity}. In each group of binary features coming from the one-hot encoding of a single raw continuous feature, this penalization uses total-variation regularization together with an extra linear constraint. This induces two interesting properties on the model weights of the one-hot encoded features: they are piecewise constan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08619","kind":"arxiv","version":4},"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":"2026-05-17T23:56:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nAzAdb97jU1EL+U0QBlIlgmCkTObggk7ol5L1uDzXl7HHWqTqFZ6JAhEoceTzDDn+3jfEeManz4SaJhyG8UUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T14:15:45.294899Z"},"content_sha256":"3abb4691bf6269a2bf6baa36e8519ad39f07294c215da3072bb714eab4ae2f63","schema_version":"1.0","event_id":"sha256:3abb4691bf6269a2bf6baa36e8519ad39f07294c215da3072bb714eab4ae2f63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ/bundle.json","state_url":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ/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":"2026-06-02T14:15:45Z","links":{"resolver":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ","bundle":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ/bundle.json","state":"https://pith.science/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OPH7XLKKHMXUMPZKXVWVHMLMUZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:OPH7XLKKHMXUMPZKXVWVHMLMUZ","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":"b5641f93694c6ac2a7b89a96bb6b381c70248379dcdc20d3c2ca735987047a6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-24T22:54:17Z","title_canon_sha256":"e3f77d4eb341d5c0d5ec73724fcc2985dd3deb453f695974d6ce608522510ade"},"schema_version":"1.0","source":{"id":"1703.08619","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.08619","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"arxiv_version","alias_value":"1703.08619v4","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08619","created_at":"2026-05-17T23:56:43Z"},{"alias_kind":"pith_short_12","alias_value":"OPH7XLKKHMXU","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OPH7XLKKHMXUMPZK","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OPH7XLKK","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:3abb4691bf6269a2bf6baa36e8519ad39f07294c215da3072bb714eab4ae2f63","target":"graph","created_at":"2026-05-17T23:56:43Z","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":"This paper deals with the problem of large-scale linear supervised learning in settings where a large number of continuous features are available. We propose to combine the well-known trick of one-hot encoding of continuous features with a new penalization called \\emph{binarsity}. In each group of binary features coming from the one-hot encoding of a single raw continuous feature, this penalization uses total-variation regularization together with an extra linear constraint. This induces two interesting properties on the model weights of the one-hot encoded features: they are piecewise constan","authors_text":"Agathe Guilloux, Mokhtar Z. Alaya, Simon Bussy, St\\'ephane Ga\\\"iffas","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-24T22:54:17Z","title":"Binarsity: a penalization for one-hot encoded features in linear supervised learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08619","kind":"arxiv","version":4},"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":"sha256:50d9a5e29907cb74e55e823ad652b38e9fe073e974c3cfff0f17416b1f460b09","target":"record","created_at":"2026-05-17T23:56:43Z","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":"b5641f93694c6ac2a7b89a96bb6b381c70248379dcdc20d3c2ca735987047a6f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-24T22:54:17Z","title_canon_sha256":"e3f77d4eb341d5c0d5ec73724fcc2985dd3deb453f695974d6ce608522510ade"},"schema_version":"1.0","source":{"id":"1703.08619","kind":"arxiv","version":4}},"canonical_sha256":"73cffbad4a3b2f463f2abd6d53b16ca64428469c6f34ec2ac157668391563ecc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73cffbad4a3b2f463f2abd6d53b16ca64428469c6f34ec2ac157668391563ecc","first_computed_at":"2026-05-17T23:56:43.200211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:43.200211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6n7dYpyhe6WrEmm5+DRF4j24wGMTsLquIUDHeR6sqPcxNrJ6qvk+UsjKr7mDxG3/7N5OevsTpgp8QQOZaC3mAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:43.200597Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.08619","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50d9a5e29907cb74e55e823ad652b38e9fe073e974c3cfff0f17416b1f460b09","sha256:3abb4691bf6269a2bf6baa36e8519ad39f07294c215da3072bb714eab4ae2f63"],"state_sha256":"46bf245a40bf1ec0ef105a59dc48816f9e50e860f87ad42888fa477e0a25d8ed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ML7DhTo+SujQnTS25Rt/N6UOZmloDMmZUYONcU4wetJ4aU0cWh4rJ6pPvtcafFmE1kiT/nz0pHBVuQ5LCh+mAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T14:15:45.297424Z","bundle_sha256":"6cd1dd6dd4946f73c15a9bbed0affb9cbad8eabe95c049c46759b9fb6451a757"}}