{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MRQ3SCDZX4OZ6USY2TLS3TIPRE","short_pith_number":"pith:MRQ3SCDZ","canonical_record":{"source":{"id":"1809.01765","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-05T23:54:33Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"639ac1e3c48f638232ed449a7bc7dba458f3d08248b7318036c5c9056fe05259","abstract_canon_sha256":"9d5b5dbe86c2e50a03949c2ab2e57b583e11b7fbbea3487388d591b8958d15b5"},"schema_version":"1.0"},"canonical_sha256":"6461b90879bf1d9f5258d4d72dcd0f891d5107264d0c405504c36a0669ab3707","source":{"kind":"arxiv","id":"1809.01765","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.01765","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"1809.01765v3","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01765","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"MRQ3SCDZX4OZ","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MRQ3SCDZX4OZ6USY","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MRQ3SCDZ","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MRQ3SCDZX4OZ6USY2TLS3TIPRE","target":"record","payload":{"canonical_record":{"source":{"id":"1809.01765","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-05T23:54:33Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"639ac1e3c48f638232ed449a7bc7dba458f3d08248b7318036c5c9056fe05259","abstract_canon_sha256":"9d5b5dbe86c2e50a03949c2ab2e57b583e11b7fbbea3487388d591b8958d15b5"},"schema_version":"1.0"},"canonical_sha256":"6461b90879bf1d9f5258d4d72dcd0f891d5107264d0c405504c36a0669ab3707","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:27.752390Z","signature_b64":"Zkp7tAlVOwbLSw9NJYKM5aNldcOWp3P0sG5Sq9cA26I0yWX7cQ+RyVNYwJ6X0+xThLp4s1F2QgRBQ+tQwfs0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6461b90879bf1d9f5258d4d72dcd0f891d5107264d0c405504c36a0669ab3707","last_reissued_at":"2026-05-17T23:59:27.751924Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:27.751924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.01765","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fCDnw7NB7TP2VsUPbTgjWX8J7bCQMpi8eYBS5WlLscRco1ni6CiEh7BwG8suSwIVOpaICnW9yWoK0qBjMY3iDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:58:09.903806Z"},"content_sha256":"50eb5f93ab6a0fa6a6e5861a7a5920318cd871b7c8d8683c5c7401d21f9c32e8","schema_version":"1.0","event_id":"sha256:50eb5f93ab6a0fa6a6e5861a7a5920318cd871b7c8d8683c5c7401d21f9c32e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MRQ3SCDZX4OZ6USY2TLS3TIPRE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Taiji Suzuki, Tomoya Murata","submitted_at":"2018-09-05T23:54:33Z","abstract_excerpt":"We develop new stochastic gradient methods for efficiently solving sparse linear regression in a partial attribute observation setting, where learners are only allowed to observe a fixed number of actively chosen attributes per example at training and prediction times. It is shown that the methods achieve essentially a sample complexity of $O(1/\\varepsilon)$ to attain an error of $\\varepsilon$ under a variant of restricted eigenvalue condition, and the rate has better dependency on the problem dimension than existing methods. Particularly, if the smallest magnitude of the non-zero components o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01765","kind":"arxiv","version":3},"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":"2026-05-17T23:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pkm8s/H/P6TB1j8TqRkB7C7f3runVrs5xHhmMEzFfjqGGMkf2Gxia7HBwODHE/98Gs92xheRTySfrcIw/+NAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T15:58:09.904545Z"},"content_sha256":"aa884ed8281812f80866916069b7d2c1acecfc15bd16127ce4a9c7d036b3da6d","schema_version":"1.0","event_id":"sha256:aa884ed8281812f80866916069b7d2c1acecfc15bd16127ce4a9c7d036b3da6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MRQ3SCDZX4OZ6USY2TLS3TIPRE/bundle.json","state_url":"https://pith.science/pith/MRQ3SCDZX4OZ6USY2TLS3TIPRE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MRQ3SCDZX4OZ6USY2TLS3TIPRE/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":"2026-05-28T15:58:09Z","links":{"resolver":"https://pith.science/pith/MRQ3SCDZX4OZ6USY2TLS3TIPRE","bundle":"https://pith.science/pith/MRQ3SCDZX4OZ6USY2TLS3TIPRE/bundle.json","state":"https://pith.science/pith/MRQ3SCDZX4OZ6USY2TLS3TIPRE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MRQ3SCDZX4OZ6USY2TLS3TIPRE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MRQ3SCDZX4OZ6USY2TLS3TIPRE","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":"9d5b5dbe86c2e50a03949c2ab2e57b583e11b7fbbea3487388d591b8958d15b5","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-05T23:54:33Z","title_canon_sha256":"639ac1e3c48f638232ed449a7bc7dba458f3d08248b7318036c5c9056fe05259"},"schema_version":"1.0","source":{"id":"1809.01765","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.01765","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"1809.01765v3","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01765","created_at":"2026-05-17T23:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"MRQ3SCDZX4OZ","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"MRQ3SCDZX4OZ6USY","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"MRQ3SCDZ","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:aa884ed8281812f80866916069b7d2c1acecfc15bd16127ce4a9c7d036b3da6d","target":"graph","created_at":"2026-05-17T23:59:27Z","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":"We develop new stochastic gradient methods for efficiently solving sparse linear regression in a partial attribute observation setting, where learners are only allowed to observe a fixed number of actively chosen attributes per example at training and prediction times. It is shown that the methods achieve essentially a sample complexity of $O(1/\\varepsilon)$ to attain an error of $\\varepsilon$ under a variant of restricted eigenvalue condition, and the rate has better dependency on the problem dimension than existing methods. Particularly, if the smallest magnitude of the non-zero components o","authors_text":"Taiji Suzuki, Tomoya Murata","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-05T23:54:33Z","title":"Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01765","kind":"arxiv","version":3},"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":"sha256:50eb5f93ab6a0fa6a6e5861a7a5920318cd871b7c8d8683c5c7401d21f9c32e8","target":"record","created_at":"2026-05-17T23:59:27Z","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":"9d5b5dbe86c2e50a03949c2ab2e57b583e11b7fbbea3487388d591b8958d15b5","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-09-05T23:54:33Z","title_canon_sha256":"639ac1e3c48f638232ed449a7bc7dba458f3d08248b7318036c5c9056fe05259"},"schema_version":"1.0","source":{"id":"1809.01765","kind":"arxiv","version":3}},"canonical_sha256":"6461b90879bf1d9f5258d4d72dcd0f891d5107264d0c405504c36a0669ab3707","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6461b90879bf1d9f5258d4d72dcd0f891d5107264d0c405504c36a0669ab3707","first_computed_at":"2026-05-17T23:59:27.751924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:27.751924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zkp7tAlVOwbLSw9NJYKM5aNldcOWp3P0sG5Sq9cA26I0yWX7cQ+RyVNYwJ6X0+xThLp4s1F2QgRBQ+tQwfs0Dw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:27.752390Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.01765","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50eb5f93ab6a0fa6a6e5861a7a5920318cd871b7c8d8683c5c7401d21f9c32e8","sha256:aa884ed8281812f80866916069b7d2c1acecfc15bd16127ce4a9c7d036b3da6d"],"state_sha256":"a8f403698f92e6a19c400ecb65713216524b4a28dd011d11a672fdbea9309193"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w5isl9WYpTYiHv1ixyhYuCVXSAVDScfnBgvXUuwO+QZpxhyQ8JeWQk+0z+9rOEe+jDuFFl1jShXpMpCIE1TdDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T15:58:09.907930Z","bundle_sha256":"bba98133a6b8172e6c30a967b4dee07d17ecb2aa656b356fbfd3789d3b373063"}}