{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:DSTGMZVUOVHU4TSEHQCCSQQBEY","short_pith_number":"pith:DSTGMZVU","canonical_record":{"source":{"id":"1212.3276","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-12-13T19:20:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c9cd6c123a8b3650fe7b2cf82b42ec722be144c59213d374de73a3bd1b2629cf","abstract_canon_sha256":"80f35d6a040d01e166b232433cd1857d81ef2b6e0171b9ce96567fe1225f57f7"},"schema_version":"1.0"},"canonical_sha256":"1ca66666b4754f4e4e443c04294201260f346a47f3102e3bac1f234091a9919a","source":{"kind":"arxiv","id":"1212.3276","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1212.3276","created_at":"2026-05-18T01:17:01Z"},{"alias_kind":"arxiv_version","alias_value":"1212.3276v3","created_at":"2026-05-18T01:17:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1212.3276","created_at":"2026-05-18T01:17:01Z"},{"alias_kind":"pith_short_12","alias_value":"DSTGMZVUOVHU","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_16","alias_value":"DSTGMZVUOVHU4TSE","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_8","alias_value":"DSTGMZVU","created_at":"2026-05-18T12:27:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:DSTGMZVUOVHU4TSEHQCCSQQBEY","target":"record","payload":{"canonical_record":{"source":{"id":"1212.3276","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-12-13T19:20:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c9cd6c123a8b3650fe7b2cf82b42ec722be144c59213d374de73a3bd1b2629cf","abstract_canon_sha256":"80f35d6a040d01e166b232433cd1857d81ef2b6e0171b9ce96567fe1225f57f7"},"schema_version":"1.0"},"canonical_sha256":"1ca66666b4754f4e4e443c04294201260f346a47f3102e3bac1f234091a9919a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:01.504574Z","signature_b64":"vBwx9U/aXvZsFeU3sAp1sOV20T/HqSu8RToxgCpBxiavBH9qwWLHqXiJDdEKUnq2+iikPqRqls4z/QyDSikAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ca66666b4754f4e4e443c04294201260f346a47f3102e3bac1f234091a9919a","last_reissued_at":"2026-05-18T01:17:01.503949Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:01.503949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1212.3276","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":"2026-05-18T01:17:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EYMOAh2b/2bQrltCkWr7G9d6tTsjBFsQVkDLQRBkpR4mrVCkb1atUY64dz9UouoJKAnmKLvI+leffAXU3HgfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:02:47.368508Z"},"content_sha256":"e328aa75e6bc3ee82ce3a3bccce5daf4d3ece22d9e3417229536d81f6d6dd57c","schema_version":"1.0","event_id":"sha256:e328aa75e6bc3ee82ce3a3bccce5daf4d3ece22d9e3417229536d81f6d6dd57c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:DSTGMZVUOVHU4TSEHQCCSQQBEY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Sparse Low-Threshold Linear Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Daniel Hsu, Nathan Srebro, Shai Shalev-Shwartz, Sivan Sabato, Tong Zhang","submitted_at":"2012-12-13T19:20:21Z","abstract_excerpt":"We consider the problem of learning a non-negative linear classifier with a $1$-norm of at most $k$, and a fixed threshold, under the hinge-loss. This problem generalizes the problem of learning a $k$-monotone disjunction. We prove that we can learn efficiently in this setting, at a rate which is linear in both $k$ and the size of the threshold, and that this is the best possible rate. We provide an efficient online learning algorithm that achieves the optimal rate, and show that in the batch case, empirical risk minimization achieves this rate as well. The rates we show are tighter than the u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1212.3276","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":"2026-05-18T01:17:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HEck9cm0oFRCj2OZb3sO6f90q3k2XK9hWWSNrheH+eZmhd9VVRBF1sGyntJRrGMG30sC3hjKKn8mxllWoS3hBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T20:02:47.368849Z"},"content_sha256":"f5889a7836a794ddf9d7caa245e330a06795e724bb2096d2a55c3e7f1d62f9f3","schema_version":"1.0","event_id":"sha256:f5889a7836a794ddf9d7caa245e330a06795e724bb2096d2a55c3e7f1d62f9f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSTGMZVUOVHU4TSEHQCCSQQBEY/bundle.json","state_url":"https://pith.science/pith/DSTGMZVUOVHU4TSEHQCCSQQBEY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSTGMZVUOVHU4TSEHQCCSQQBEY/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":"2026-06-02T20:02:47Z","links":{"resolver":"https://pith.science/pith/DSTGMZVUOVHU4TSEHQCCSQQBEY","bundle":"https://pith.science/pith/DSTGMZVUOVHU4TSEHQCCSQQBEY/bundle.json","state":"https://pith.science/pith/DSTGMZVUOVHU4TSEHQCCSQQBEY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSTGMZVUOVHU4TSEHQCCSQQBEY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:DSTGMZVUOVHU4TSEHQCCSQQBEY","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":"80f35d6a040d01e166b232433cd1857d81ef2b6e0171b9ce96567fe1225f57f7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-12-13T19:20:21Z","title_canon_sha256":"c9cd6c123a8b3650fe7b2cf82b42ec722be144c59213d374de73a3bd1b2629cf"},"schema_version":"1.0","source":{"id":"1212.3276","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1212.3276","created_at":"2026-05-18T01:17:01Z"},{"alias_kind":"arxiv_version","alias_value":"1212.3276v3","created_at":"2026-05-18T01:17:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1212.3276","created_at":"2026-05-18T01:17:01Z"},{"alias_kind":"pith_short_12","alias_value":"DSTGMZVUOVHU","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_16","alias_value":"DSTGMZVUOVHU4TSE","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_8","alias_value":"DSTGMZVU","created_at":"2026-05-18T12:27:04Z"}],"graph_snapshots":[{"event_id":"sha256:f5889a7836a794ddf9d7caa245e330a06795e724bb2096d2a55c3e7f1d62f9f3","target":"graph","created_at":"2026-05-18T01:17:01Z","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 consider the problem of learning a non-negative linear classifier with a $1$-norm of at most $k$, and a fixed threshold, under the hinge-loss. This problem generalizes the problem of learning a $k$-monotone disjunction. We prove that we can learn efficiently in this setting, at a rate which is linear in both $k$ and the size of the threshold, and that this is the best possible rate. We provide an efficient online learning algorithm that achieves the optimal rate, and show that in the batch case, empirical risk minimization achieves this rate as well. The rates we show are tighter than the u","authors_text":"Daniel Hsu, Nathan Srebro, Shai Shalev-Shwartz, Sivan Sabato, Tong Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-12-13T19:20:21Z","title":"Learning Sparse Low-Threshold Linear Classifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1212.3276","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:e328aa75e6bc3ee82ce3a3bccce5daf4d3ece22d9e3417229536d81f6d6dd57c","target":"record","created_at":"2026-05-18T01:17:01Z","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":"80f35d6a040d01e166b232433cd1857d81ef2b6e0171b9ce96567fe1225f57f7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-12-13T19:20:21Z","title_canon_sha256":"c9cd6c123a8b3650fe7b2cf82b42ec722be144c59213d374de73a3bd1b2629cf"},"schema_version":"1.0","source":{"id":"1212.3276","kind":"arxiv","version":3}},"canonical_sha256":"1ca66666b4754f4e4e443c04294201260f346a47f3102e3bac1f234091a9919a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ca66666b4754f4e4e443c04294201260f346a47f3102e3bac1f234091a9919a","first_computed_at":"2026-05-18T01:17:01.503949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:01.503949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vBwx9U/aXvZsFeU3sAp1sOV20T/HqSu8RToxgCpBxiavBH9qwWLHqXiJDdEKUnq2+iikPqRqls4z/QyDSikAAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:01.504574Z","signed_message":"canonical_sha256_bytes"},"source_id":"1212.3276","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e328aa75e6bc3ee82ce3a3bccce5daf4d3ece22d9e3417229536d81f6d6dd57c","sha256:f5889a7836a794ddf9d7caa245e330a06795e724bb2096d2a55c3e7f1d62f9f3"],"state_sha256":"cf885e3f6362a1bf633fd46fffe44c4158bb85f37e71efec324e870d5cefc4f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6v4xu+xYr2GeQNdofl5d90ECXVkL4u+bVqMQ+WrfekhQrNH43mw+TZGUD9asnNlR4VuGzQaeETjPZAayA/1JAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T20:02:47.370857Z","bundle_sha256":"0b9ba087b5bdff7ea769c0d2dae332132de03f36075131300b190076b7d50291"}}