{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:35ADFMNT5NVPRVOQ2ZM4BZKDTD","short_pith_number":"pith:35ADFMNT","canonical_record":{"source":{"id":"1612.01663","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-06T04:58:45Z","cross_cats_sorted":[],"title_canon_sha256":"c293e294c1c01f85bb9165b2f114610bcedc39f38be0b104b7da128b32ce3e5c","abstract_canon_sha256":"3d264f03905964aa4dbbea6ef8395a959b53e27ee3ba6fb380375c5efffd969e"},"schema_version":"1.0"},"canonical_sha256":"df4032b1b3eb6af8d5d0d659c0e54398f1d1347b8f5b84089fb5c48bd64b6832","source":{"kind":"arxiv","id":"1612.01663","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.01663","created_at":"2026-05-18T00:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"1612.01663v1","created_at":"2026-05-18T00:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01663","created_at":"2026-05-18T00:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"35ADFMNT5NVP","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"35ADFMNT5NVPRVOQ","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"35ADFMNT","created_at":"2026-05-18T12:29:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:35ADFMNT5NVPRVOQ2ZM4BZKDTD","target":"record","payload":{"canonical_record":{"source":{"id":"1612.01663","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-06T04:58:45Z","cross_cats_sorted":[],"title_canon_sha256":"c293e294c1c01f85bb9165b2f114610bcedc39f38be0b104b7da128b32ce3e5c","abstract_canon_sha256":"3d264f03905964aa4dbbea6ef8395a959b53e27ee3ba6fb380375c5efffd969e"},"schema_version":"1.0"},"canonical_sha256":"df4032b1b3eb6af8d5d0d659c0e54398f1d1347b8f5b84089fb5c48bd64b6832","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:47.910050Z","signature_b64":"q/GekRsvVuSoU2CyHMbQ4BSovTNUYyM6svJLpBswBMBtXEzDIPdHmeU7d/OQ3/gTsCzCZi+8inDeuibpIfzwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df4032b1b3eb6af8d5d0d659c0e54398f1d1347b8f5b84089fb5c48bd64b6832","last_reissued_at":"2026-05-18T00:55:47.909398Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:47.909398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.01663","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":"2026-05-18T00:55:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sNYDYD/i7n2n1he53xjPqBmDGrl8H70gJjLSEvqDsyKmw111Mbw+JRpIAxtv9VzJeObbNZI/HCHqVWgv2FmpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:26:56.023771Z"},"content_sha256":"274ed399ac86187e170c0934f167dc8f64d2a507f58bee351cc63abb530b1e83","schema_version":"1.0","event_id":"sha256:274ed399ac86187e170c0934f167dc8f64d2a507f58bee351cc63abb530b1e83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:35ADFMNT5NVPRVOQ2ZM4BZKDTD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Non-oblivious Randomized Reduction for Risk Minimization with Improved Excess Risk Guarantee","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haiqin Yang, Lijun Zhang, Tianbao Yang, Yi Xu","submitted_at":"2016-12-06T04:58:45Z","abstract_excerpt":"In this paper, we address learning problems for high dimensional data. Previously, oblivious random projection based approaches that project high dimensional features onto a random subspace have been used in practice for tackling high-dimensionality challenge in machine learning. Recently, various non-oblivious randomized reduction methods have been developed and deployed for solving many numerical problems such as matrix product approximation, low-rank matrix approximation, etc. However, they are less explored for the machine learning tasks, e.g., classification. More seriously, the theoretic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01663","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":"2026-05-18T00:55:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JoTBzuxvfPdpEfCTTey2T9wY6JgPl0/DZIM5U8ahseD0aizhkN9vTXfTB1nwR6d4z6Ix2saXbQXO6K1Wr3JjBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:26:56.024251Z"},"content_sha256":"f5ab2b61ecb39c89d3ec54540236fdc13d63a066e458599ee5723874817c532e","schema_version":"1.0","event_id":"sha256:f5ab2b61ecb39c89d3ec54540236fdc13d63a066e458599ee5723874817c532e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/35ADFMNT5NVPRVOQ2ZM4BZKDTD/bundle.json","state_url":"https://pith.science/pith/35ADFMNT5NVPRVOQ2ZM4BZKDTD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/35ADFMNT5NVPRVOQ2ZM4BZKDTD/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":"2026-05-26T13:26:56Z","links":{"resolver":"https://pith.science/pith/35ADFMNT5NVPRVOQ2ZM4BZKDTD","bundle":"https://pith.science/pith/35ADFMNT5NVPRVOQ2ZM4BZKDTD/bundle.json","state":"https://pith.science/pith/35ADFMNT5NVPRVOQ2ZM4BZKDTD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/35ADFMNT5NVPRVOQ2ZM4BZKDTD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:35ADFMNT5NVPRVOQ2ZM4BZKDTD","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":"3d264f03905964aa4dbbea6ef8395a959b53e27ee3ba6fb380375c5efffd969e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-06T04:58:45Z","title_canon_sha256":"c293e294c1c01f85bb9165b2f114610bcedc39f38be0b104b7da128b32ce3e5c"},"schema_version":"1.0","source":{"id":"1612.01663","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.01663","created_at":"2026-05-18T00:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"1612.01663v1","created_at":"2026-05-18T00:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.01663","created_at":"2026-05-18T00:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"35ADFMNT5NVP","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"35ADFMNT5NVPRVOQ","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"35ADFMNT","created_at":"2026-05-18T12:29:55Z"}],"graph_snapshots":[{"event_id":"sha256:f5ab2b61ecb39c89d3ec54540236fdc13d63a066e458599ee5723874817c532e","target":"graph","created_at":"2026-05-18T00:55:47Z","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":"In this paper, we address learning problems for high dimensional data. Previously, oblivious random projection based approaches that project high dimensional features onto a random subspace have been used in practice for tackling high-dimensionality challenge in machine learning. Recently, various non-oblivious randomized reduction methods have been developed and deployed for solving many numerical problems such as matrix product approximation, low-rank matrix approximation, etc. However, they are less explored for the machine learning tasks, e.g., classification. More seriously, the theoretic","authors_text":"Haiqin Yang, Lijun Zhang, Tianbao Yang, Yi Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-06T04:58:45Z","title":"Efficient Non-oblivious Randomized Reduction for Risk Minimization with Improved Excess Risk Guarantee"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.01663","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":"sha256:274ed399ac86187e170c0934f167dc8f64d2a507f58bee351cc63abb530b1e83","target":"record","created_at":"2026-05-18T00:55:47Z","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":"3d264f03905964aa4dbbea6ef8395a959b53e27ee3ba6fb380375c5efffd969e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-06T04:58:45Z","title_canon_sha256":"c293e294c1c01f85bb9165b2f114610bcedc39f38be0b104b7da128b32ce3e5c"},"schema_version":"1.0","source":{"id":"1612.01663","kind":"arxiv","version":1}},"canonical_sha256":"df4032b1b3eb6af8d5d0d659c0e54398f1d1347b8f5b84089fb5c48bd64b6832","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df4032b1b3eb6af8d5d0d659c0e54398f1d1347b8f5b84089fb5c48bd64b6832","first_computed_at":"2026-05-18T00:55:47.909398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:55:47.909398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q/GekRsvVuSoU2CyHMbQ4BSovTNUYyM6svJLpBswBMBtXEzDIPdHmeU7d/OQ3/gTsCzCZi+8inDeuibpIfzwAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:55:47.910050Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.01663","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:274ed399ac86187e170c0934f167dc8f64d2a507f58bee351cc63abb530b1e83","sha256:f5ab2b61ecb39c89d3ec54540236fdc13d63a066e458599ee5723874817c532e"],"state_sha256":"86bd2c6884307544e7e372e31a635f6d1bbe212f247933ac82d8de8c6311356b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eLM3C/cMCA60MfFuqXo4NJUuU66fM9Mww8EZ0eqTTPu27gjPXIEHAzga/AIDmZwlN+ULNbmt/dvnji/8qfNoBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T13:26:56.026988Z","bundle_sha256":"4ebe886ae713bdf8520c0ad3179c9e47d1c4df8ccd445be59b3551b2ea95fcc8"}}