{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:BGDHL3S7JRN6VD4GTGIWGF3HQD","short_pith_number":"pith:BGDHL3S7","canonical_record":{"source":{"id":"1311.4803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-11-19T16:56:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f45795bba45bcf327d16b4616ddc71fd15877db5198291a3f4cc5e515b130099","abstract_canon_sha256":"ce7213b788bda1828f0feb21becc172e1c7d938bb1ce2832415df24eb25de71f"},"schema_version":"1.0"},"canonical_sha256":"098675ee5f4c5bea8f86999163176780e5b689b690866607b6f32a8e26e81248","source":{"kind":"arxiv","id":"1311.4803","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1311.4803","created_at":"2026-05-18T03:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"1311.4803v2","created_at":"2026-05-18T03:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.4803","created_at":"2026-05-18T03:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"BGDHL3S7JRN6","created_at":"2026-05-18T12:27:38Z"},{"alias_kind":"pith_short_16","alias_value":"BGDHL3S7JRN6VD4G","created_at":"2026-05-18T12:27:38Z"},{"alias_kind":"pith_short_8","alias_value":"BGDHL3S7","created_at":"2026-05-18T12:27:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:BGDHL3S7JRN6VD4GTGIWGF3HQD","target":"record","payload":{"canonical_record":{"source":{"id":"1311.4803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-11-19T16:56:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f45795bba45bcf327d16b4616ddc71fd15877db5198291a3f4cc5e515b130099","abstract_canon_sha256":"ce7213b788bda1828f0feb21becc172e1c7d938bb1ce2832415df24eb25de71f"},"schema_version":"1.0"},"canonical_sha256":"098675ee5f4c5bea8f86999163176780e5b689b690866607b6f32a8e26e81248","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:00:00.412616Z","signature_b64":"M3pMIJZbzPY2npgoraC82icCO1TbORXihSyYf9zLoWpsy+RWkYxf97ApmjT4f057E+CBeRvEkZ+HJB2PPX7eDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"098675ee5f4c5bea8f86999163176780e5b689b690866607b6f32a8e26e81248","last_reissued_at":"2026-05-18T03:00:00.411677Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:00:00.411677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1311.4803","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b+iYYJ3vhn5CdCJlZ6Qvhbk46X6TStXB2Wc6iHma4IGvi5SK2qYsWmj1G3AFmL5DXbNiOeHdy10+9YhjVCujCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T16:57:11.993409Z"},"content_sha256":"8483bf9fda80fcb8a3f60eb166083b0af4d69eec5273b5d4b78d363dd6a023c5","schema_version":"1.0","event_id":"sha256:8483bf9fda80fcb8a3f60eb166083b0af4d69eec5273b5d4b78d363dd6a023c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:BGDHL3S7JRN6VD4GTGIWGF3HQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beating the Minimax Rate of Active Learning with Prior Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lijun Zhang, Mehrdad Mahdavi, Rong Jin","submitted_at":"2013-11-19T16:56:55Z","abstract_excerpt":"Active learning refers to the learning protocol where the learner is allowed to choose a subset of instances for labeling. Previous studies have shown that, compared with passive learning, active learning is able to reduce the label complexity exponentially if the data are linearly separable or satisfy the Tsybakov noise condition with parameter $\\kappa=1$. In this paper, we propose a novel active learning algorithm using a convex surrogate loss, with the goal to broaden the cases for which active learning achieves an exponential improvement. We make use of a convex loss not only because it re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.4803","kind":"arxiv","version":2},"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":"2026-05-18T03:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"adRfzTrSsujgsIlDwdLF2IDo6JAoMnuFYCgHgQWWInVQYrykRMJK3M1kIDyEq/ahcvfDxCUPRCM2juiHoRk/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T16:57:11.994072Z"},"content_sha256":"6381cacc14183ad559cb96a9bcf0d251f344fb5cd5c9cbec27e2ca49ee95f99d","schema_version":"1.0","event_id":"sha256:6381cacc14183ad559cb96a9bcf0d251f344fb5cd5c9cbec27e2ca49ee95f99d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BGDHL3S7JRN6VD4GTGIWGF3HQD/bundle.json","state_url":"https://pith.science/pith/BGDHL3S7JRN6VD4GTGIWGF3HQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BGDHL3S7JRN6VD4GTGIWGF3HQD/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":"2026-05-28T16:57:11Z","links":{"resolver":"https://pith.science/pith/BGDHL3S7JRN6VD4GTGIWGF3HQD","bundle":"https://pith.science/pith/BGDHL3S7JRN6VD4GTGIWGF3HQD/bundle.json","state":"https://pith.science/pith/BGDHL3S7JRN6VD4GTGIWGF3HQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BGDHL3S7JRN6VD4GTGIWGF3HQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:BGDHL3S7JRN6VD4GTGIWGF3HQD","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":"ce7213b788bda1828f0feb21becc172e1c7d938bb1ce2832415df24eb25de71f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-11-19T16:56:55Z","title_canon_sha256":"f45795bba45bcf327d16b4616ddc71fd15877db5198291a3f4cc5e515b130099"},"schema_version":"1.0","source":{"id":"1311.4803","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1311.4803","created_at":"2026-05-18T03:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"1311.4803v2","created_at":"2026-05-18T03:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.4803","created_at":"2026-05-18T03:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"BGDHL3S7JRN6","created_at":"2026-05-18T12:27:38Z"},{"alias_kind":"pith_short_16","alias_value":"BGDHL3S7JRN6VD4G","created_at":"2026-05-18T12:27:38Z"},{"alias_kind":"pith_short_8","alias_value":"BGDHL3S7","created_at":"2026-05-18T12:27:38Z"}],"graph_snapshots":[{"event_id":"sha256:6381cacc14183ad559cb96a9bcf0d251f344fb5cd5c9cbec27e2ca49ee95f99d","target":"graph","created_at":"2026-05-18T03:00:00Z","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":"Active learning refers to the learning protocol where the learner is allowed to choose a subset of instances for labeling. Previous studies have shown that, compared with passive learning, active learning is able to reduce the label complexity exponentially if the data are linearly separable or satisfy the Tsybakov noise condition with parameter $\\kappa=1$. In this paper, we propose a novel active learning algorithm using a convex surrogate loss, with the goal to broaden the cases for which active learning achieves an exponential improvement. We make use of a convex loss not only because it re","authors_text":"Lijun Zhang, Mehrdad Mahdavi, Rong Jin","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-11-19T16:56:55Z","title":"Beating the Minimax Rate of Active Learning with Prior Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.4803","kind":"arxiv","version":2},"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":"sha256:8483bf9fda80fcb8a3f60eb166083b0af4d69eec5273b5d4b78d363dd6a023c5","target":"record","created_at":"2026-05-18T03:00:00Z","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":"ce7213b788bda1828f0feb21becc172e1c7d938bb1ce2832415df24eb25de71f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-11-19T16:56:55Z","title_canon_sha256":"f45795bba45bcf327d16b4616ddc71fd15877db5198291a3f4cc5e515b130099"},"schema_version":"1.0","source":{"id":"1311.4803","kind":"arxiv","version":2}},"canonical_sha256":"098675ee5f4c5bea8f86999163176780e5b689b690866607b6f32a8e26e81248","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"098675ee5f4c5bea8f86999163176780e5b689b690866607b6f32a8e26e81248","first_computed_at":"2026-05-18T03:00:00.411677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:00:00.411677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M3pMIJZbzPY2npgoraC82icCO1TbORXihSyYf9zLoWpsy+RWkYxf97ApmjT4f057E+CBeRvEkZ+HJB2PPX7eDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:00:00.412616Z","signed_message":"canonical_sha256_bytes"},"source_id":"1311.4803","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8483bf9fda80fcb8a3f60eb166083b0af4d69eec5273b5d4b78d363dd6a023c5","sha256:6381cacc14183ad559cb96a9bcf0d251f344fb5cd5c9cbec27e2ca49ee95f99d"],"state_sha256":"74bc6fbcb5b56dd4a546f4b7768d91590e27aad31d09418a689b33512d34a962"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GxVqVP6sG4IfqDFkRvvP6N29sbiDG+dMYzBFjY6xqvZ+nUCXbS5Xe3uQkR2PaH+S1do3TTFmRSIsisiFSKvABw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T16:57:11.997554Z","bundle_sha256":"690f0b590a2d48a3595f9fc3e9d10d8ce7826436d13ef84588461eed463d76ee"}}