{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZLLDXAAYVMTRVDUYZMG4ONYHGM","short_pith_number":"pith:ZLLDXAAY","schema_version":"1.0","canonical_sha256":"cad63b8018ab271a8e98cb0dc7370733211aa9b7d75a93015946b4c0fc82dae8","source":{"kind":"arxiv","id":"1912.03927","version":1},"attestation_state":"computed","paper":{"title":"Large deviations for the perceptron model and consequences for active learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cond-mat.dis-nn","authors_text":"Hugo Cui, Lenka Zdeborov\\'a, Luca Saglietti","submitted_at":"2019-12-09T09:50:52Z","abstract_excerpt":"Active learning is a branch of machine learning that deals with problems where unlabeled data is abundant yet obtaining labels is expensive. The learning algorithm has the possibility of querying a limited number of samples to obtain the corresponding labels, subsequently used for supervised learning. In this work, we consider the task of choosing the subset of samples to be labeled from a fixed finite pool of samples. We assume the pool of samples to be a random matrix and the ground truth labels to be generated by a single-layer teacher random neural network. We employ replica methods to ana"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1912.03927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2019-12-09T09:50:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5c00289b907e6a0b5bf6d5ad03f5524549c6ee4f2866af40c8a8869d805bf249","abstract_canon_sha256":"8d7500efeb5b3cc0407ddbe38c6db096daa93e59ee51056e4f4a2a5a86b62825"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:32:42.622151Z","signature_b64":"1xSzLMn+F4Fe0HXwTOfS26nwo8h+EwvZ9QSvLNoXTMZj5tKjzZGcpLAI+TYZQR9Eu+btr+7q8BjS1f141TLUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cad63b8018ab271a8e98cb0dc7370733211aa9b7d75a93015946b4c0fc82dae8","last_reissued_at":"2026-07-05T01:32:42.621574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:32:42.621574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large deviations for the perceptron model and consequences for active learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cond-mat.dis-nn","authors_text":"Hugo Cui, Lenka Zdeborov\\'a, Luca Saglietti","submitted_at":"2019-12-09T09:50:52Z","abstract_excerpt":"Active learning is a branch of machine learning that deals with problems where unlabeled data is abundant yet obtaining labels is expensive. The learning algorithm has the possibility of querying a limited number of samples to obtain the corresponding labels, subsequently used for supervised learning. In this work, we consider the task of choosing the subset of samples to be labeled from a fixed finite pool of samples. We assume the pool of samples to be a random matrix and the ground truth labels to be generated by a single-layer teacher random neural network. We employ replica methods to ana"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03927","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.03927/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1912.03927","created_at":"2026-07-05T01:32:42.621631+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.03927v1","created_at":"2026-07-05T01:32:42.621631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03927","created_at":"2026-07-05T01:32:42.621631+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLLDXAAYVMTR","created_at":"2026-07-05T01:32:42.621631+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLLDXAAYVMTRVDUY","created_at":"2026-07-05T01:32:42.621631+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLLDXAAY","created_at":"2026-07-05T01:32:42.621631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04282","citing_title":"Isolating the hard core of phaseless inference: the Phase selection formulation","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZLLDXAAYVMTRVDUYZMG4ONYHGM","json":"https://pith.science/pith/ZLLDXAAYVMTRVDUYZMG4ONYHGM.json","graph_json":"https://pith.science/api/pith-number/ZLLDXAAYVMTRVDUYZMG4ONYHGM/graph.json","events_json":"https://pith.science/api/pith-number/ZLLDXAAYVMTRVDUYZMG4ONYHGM/events.json","paper":"https://pith.science/paper/ZLLDXAAY"},"agent_actions":{"view_html":"https://pith.science/pith/ZLLDXAAYVMTRVDUYZMG4ONYHGM","download_json":"https://pith.science/pith/ZLLDXAAYVMTRVDUYZMG4ONYHGM.json","view_paper":"https://pith.science/paper/ZLLDXAAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.03927&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLLDXAAYVMTRVDUYZMG4ONYHGM/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLLDXAAYVMTRVDUYZMG4ONYHGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLLDXAAYVMTRVDUYZMG4ONYHGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLLDXAAYVMTRVDUYZMG4ONYHGM/action/storage_attestation","attest_author":"https://pith.science/pith/ZLLDXAAYVMTRVDUYZMG4ONYHGM/action/author_attestation","sign_citation":"https://pith.science/pith/ZLLDXAAYVMTRVDUYZMG4ONYHGM/action/citation_signature","submit_replication":"https://pith.science/pith/ZLLDXAAYVMTRVDUYZMG4ONYHGM/action/replication_record"}},"created_at":"2026-07-05T01:32:42.621631+00:00","updated_at":"2026-07-05T01:32:42.621631+00:00"}