{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:ZN4MZFW3R4ONVT2DBRSIXHPX62","short_pith_number":"pith:ZN4MZFW3","canonical_record":{"source":{"id":"1608.04048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-14T01:56:22Z","cross_cats_sorted":[],"title_canon_sha256":"357907d13a782508a156cd23d7b959b2011258a5bf3c574df63c66707546a923","abstract_canon_sha256":"1be1202105a3a8786f9ad4417239569079fe4bc96584118296e2dfc9d49de896"},"schema_version":"1.0"},"canonical_sha256":"cb78cc96db8f1cdacf430c648b9df7f6ab2da736574fbdb4c308c064ebc55d52","source":{"kind":"arxiv","id":"1608.04048","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.04048","created_at":"2026-05-18T01:09:04Z"},{"alias_kind":"arxiv_version","alias_value":"1608.04048v1","created_at":"2026-05-18T01:09:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04048","created_at":"2026-05-18T01:09:04Z"},{"alias_kind":"pith_short_12","alias_value":"ZN4MZFW3R4ON","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZN4MZFW3R4ONVT2D","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZN4MZFW3","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:ZN4MZFW3R4ONVT2DBRSIXHPX62","target":"record","payload":{"canonical_record":{"source":{"id":"1608.04048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-14T01:56:22Z","cross_cats_sorted":[],"title_canon_sha256":"357907d13a782508a156cd23d7b959b2011258a5bf3c574df63c66707546a923","abstract_canon_sha256":"1be1202105a3a8786f9ad4417239569079fe4bc96584118296e2dfc9d49de896"},"schema_version":"1.0"},"canonical_sha256":"cb78cc96db8f1cdacf430c648b9df7f6ab2da736574fbdb4c308c064ebc55d52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:04.378738Z","signature_b64":"XIlJyctnSflpj5Feto51HNTfCE0RcbtOybduVnD5iazC+OuU2Yyle4x8N/pgzoyiGr8+aekGjBhKtJZTB2hbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb78cc96db8f1cdacf430c648b9df7f6ab2da736574fbdb4c308c064ebc55d52","last_reissued_at":"2026-05-18T01:09:04.378299Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:04.378299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.04048","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":"2026-05-18T01:09:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WMvN+IMgbEn1FzqP6tSj4QvxniRXJGsmKmc3srJAqiJqbnjCObwzRPUGRHUCajIc8amwD/jDtpNzHKeXgk6AAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:59:10.370226Z"},"content_sha256":"e725986c04110232ffaf598205de23a83cf0a877ab859827ce8d3a4fa71d93a0","schema_version":"1.0","event_id":"sha256:e725986c04110232ffaf598205de23a83cf0a877ab859827ce8d3a4fa71d93a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:ZN4MZFW3R4ONVT2DBRSIXHPX62","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ultra High-Dimensional Nonlinear Feature Selection for Big Biological Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Avishek Saha, Cenk Sahinalp, Dawei Yin, Ermin Hodzic, Filippo Menczer, Hiroshi Mamitsuka, Hua Ouyang, Jiliang Tang, Jose Lugo-Martinez, Makoto Yamada, Predrag Radivojac, Raunak Shrestha, Yi Chang","submitted_at":"2016-08-14T01:56:22Z","abstract_excerpt":"Machine learning methods are used to discover complex nonlinear relationships in biological and medical data. However, sophisticated learning models are computationally unfeasible for data with millions of features. Here we introduce the first feature selection method for nonlinear learning problems that can scale up to large, ultra-high dimensional biological data. More specifically, we scale up the novel Hilbert-Schmidt Independence Criterion Lasso (HSIC Lasso) to handle millions of features with tens of thousand samples. The proposed method is guaranteed to find an optimal subset of maximal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04048","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":"2026-05-18T01:09:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JBlSAGmoLK73Ns0loP6fk66H3Z+adtqd2EdDPX3Jx8opU7HfTdqo1SHiQn2MFsNIF8qRKxJLKTT8HCokMPIEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:59:10.370886Z"},"content_sha256":"bd64149061514ee74033cfd6752bebad56287d55035deaccf87764e9f69e147b","schema_version":"1.0","event_id":"sha256:bd64149061514ee74033cfd6752bebad56287d55035deaccf87764e9f69e147b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZN4MZFW3R4ONVT2DBRSIXHPX62/bundle.json","state_url":"https://pith.science/pith/ZN4MZFW3R4ONVT2DBRSIXHPX62/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZN4MZFW3R4ONVT2DBRSIXHPX62/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":"2026-05-30T19:59:10Z","links":{"resolver":"https://pith.science/pith/ZN4MZFW3R4ONVT2DBRSIXHPX62","bundle":"https://pith.science/pith/ZN4MZFW3R4ONVT2DBRSIXHPX62/bundle.json","state":"https://pith.science/pith/ZN4MZFW3R4ONVT2DBRSIXHPX62/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZN4MZFW3R4ONVT2DBRSIXHPX62/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:ZN4MZFW3R4ONVT2DBRSIXHPX62","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":"1be1202105a3a8786f9ad4417239569079fe4bc96584118296e2dfc9d49de896","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-14T01:56:22Z","title_canon_sha256":"357907d13a782508a156cd23d7b959b2011258a5bf3c574df63c66707546a923"},"schema_version":"1.0","source":{"id":"1608.04048","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.04048","created_at":"2026-05-18T01:09:04Z"},{"alias_kind":"arxiv_version","alias_value":"1608.04048v1","created_at":"2026-05-18T01:09:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04048","created_at":"2026-05-18T01:09:04Z"},{"alias_kind":"pith_short_12","alias_value":"ZN4MZFW3R4ON","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZN4MZFW3R4ONVT2D","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZN4MZFW3","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:bd64149061514ee74033cfd6752bebad56287d55035deaccf87764e9f69e147b","target":"graph","created_at":"2026-05-18T01:09:04Z","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":"Machine learning methods are used to discover complex nonlinear relationships in biological and medical data. However, sophisticated learning models are computationally unfeasible for data with millions of features. Here we introduce the first feature selection method for nonlinear learning problems that can scale up to large, ultra-high dimensional biological data. More specifically, we scale up the novel Hilbert-Schmidt Independence Criterion Lasso (HSIC Lasso) to handle millions of features with tens of thousand samples. The proposed method is guaranteed to find an optimal subset of maximal","authors_text":"Avishek Saha, Cenk Sahinalp, Dawei Yin, Ermin Hodzic, Filippo Menczer, Hiroshi Mamitsuka, Hua Ouyang, Jiliang Tang, Jose Lugo-Martinez, Makoto Yamada, Predrag Radivojac, Raunak Shrestha, Yi Chang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-14T01:56:22Z","title":"Ultra High-Dimensional Nonlinear Feature Selection for Big Biological Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04048","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:e725986c04110232ffaf598205de23a83cf0a877ab859827ce8d3a4fa71d93a0","target":"record","created_at":"2026-05-18T01:09:04Z","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":"1be1202105a3a8786f9ad4417239569079fe4bc96584118296e2dfc9d49de896","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-14T01:56:22Z","title_canon_sha256":"357907d13a782508a156cd23d7b959b2011258a5bf3c574df63c66707546a923"},"schema_version":"1.0","source":{"id":"1608.04048","kind":"arxiv","version":1}},"canonical_sha256":"cb78cc96db8f1cdacf430c648b9df7f6ab2da736574fbdb4c308c064ebc55d52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb78cc96db8f1cdacf430c648b9df7f6ab2da736574fbdb4c308c064ebc55d52","first_computed_at":"2026-05-18T01:09:04.378299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:09:04.378299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XIlJyctnSflpj5Feto51HNTfCE0RcbtOybduVnD5iazC+OuU2Yyle4x8N/pgzoyiGr8+aekGjBhKtJZTB2hbAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:09:04.378738Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.04048","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e725986c04110232ffaf598205de23a83cf0a877ab859827ce8d3a4fa71d93a0","sha256:bd64149061514ee74033cfd6752bebad56287d55035deaccf87764e9f69e147b"],"state_sha256":"101ec708e34c97fa73c70fd9e1c00115c2a62a933b292bef172a8d38f9a7d4dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BmZKLzjDetceyjIb7J18+KAxUU/Pcf840wO1+xwnSVkOkqnzjzVRh23pP7RiHGS4qFzdGnrtNMPiXcOxxY+oAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T19:59:10.374558Z","bundle_sha256":"2a22e78c962b3c822b88feaca393bddf4f8439ea2d4057a2e550a0b0e115586c"}}