{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3S7QFCBQM4UBVYTEMKUJMU5SCM","short_pith_number":"pith:3S7QFCBQ","schema_version":"1.0","canonical_sha256":"dcbf02883067281ae26462a89653b213393f7c99faf3c705657df2bd41a172f8","source":{"kind":"arxiv","id":"2104.09015","version":3},"attestation_state":"computed","paper":{"title":"Labels, Information, and Computation: Efficient Learning Using Sufficient Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jose C. Principe, Shiyu Duan, Spencer Chang","submitted_at":"2021-04-19T02:15:25Z","abstract_excerpt":"In supervised learning, obtaining a large set of fully-labeled training data is expensive. We show that we do not always need full label information on every single training example to train a competent classifier. Specifically, inspired by the principle of sufficiency in statistics, we present a statistic (a summary) of the fully-labeled training set that captures almost all the relevant information for classification but at the same time is easier to obtain directly. We call this statistic \"sufficiently-labeled data\" and prove its sufficiency and efficiency for finding the optimal hidden rep"},"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":"2104.09015","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-19T02:15:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e66baafe0ef06302a5627da07d34b1158bb72dcbe250b56ac9ea09569861ec1e","abstract_canon_sha256":"3614eb293bf75438fcde603021e7b8762f302f6225768cdf24b33ad3bc3fe105"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:05.135694Z","signature_b64":"kMqjE7qLCTK745+FjajotheP/ecjuAKgqG7HSvCniR+b09RQklHH3bizR3tXLrGt7DMi33WdfbMJJzmJd9bRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcbf02883067281ae26462a89653b213393f7c99faf3c705657df2bd41a172f8","last_reissued_at":"2026-07-05T05:33:05.135174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:05.135174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Labels, Information, and Computation: Efficient Learning Using Sufficient Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jose C. Principe, Shiyu Duan, Spencer Chang","submitted_at":"2021-04-19T02:15:25Z","abstract_excerpt":"In supervised learning, obtaining a large set of fully-labeled training data is expensive. We show that we do not always need full label information on every single training example to train a competent classifier. Specifically, inspired by the principle of sufficiency in statistics, we present a statistic (a summary) of the fully-labeled training set that captures almost all the relevant information for classification but at the same time is easier to obtain directly. We call this statistic \"sufficiently-labeled data\" and prove its sufficiency and efficiency for finding the optimal hidden rep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09015","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.09015/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":"2104.09015","created_at":"2026-07-05T05:33:05.135233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.09015v3","created_at":"2026-07-05T05:33:05.135233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09015","created_at":"2026-07-05T05:33:05.135233+00:00"},{"alias_kind":"pith_short_12","alias_value":"3S7QFCBQM4UB","created_at":"2026-07-05T05:33:05.135233+00:00"},{"alias_kind":"pith_short_16","alias_value":"3S7QFCBQM4UBVYTE","created_at":"2026-07-05T05:33:05.135233+00:00"},{"alias_kind":"pith_short_8","alias_value":"3S7QFCBQ","created_at":"2026-07-05T05:33:05.135233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3S7QFCBQM4UBVYTEMKUJMU5SCM","json":"https://pith.science/pith/3S7QFCBQM4UBVYTEMKUJMU5SCM.json","graph_json":"https://pith.science/api/pith-number/3S7QFCBQM4UBVYTEMKUJMU5SCM/graph.json","events_json":"https://pith.science/api/pith-number/3S7QFCBQM4UBVYTEMKUJMU5SCM/events.json","paper":"https://pith.science/paper/3S7QFCBQ"},"agent_actions":{"view_html":"https://pith.science/pith/3S7QFCBQM4UBVYTEMKUJMU5SCM","download_json":"https://pith.science/pith/3S7QFCBQM4UBVYTEMKUJMU5SCM.json","view_paper":"https://pith.science/paper/3S7QFCBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.09015&json=true","fetch_graph":"https://pith.science/api/pith-number/3S7QFCBQM4UBVYTEMKUJMU5SCM/graph.json","fetch_events":"https://pith.science/api/pith-number/3S7QFCBQM4UBVYTEMKUJMU5SCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3S7QFCBQM4UBVYTEMKUJMU5SCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3S7QFCBQM4UBVYTEMKUJMU5SCM/action/storage_attestation","attest_author":"https://pith.science/pith/3S7QFCBQM4UBVYTEMKUJMU5SCM/action/author_attestation","sign_citation":"https://pith.science/pith/3S7QFCBQM4UBVYTEMKUJMU5SCM/action/citation_signature","submit_replication":"https://pith.science/pith/3S7QFCBQM4UBVYTEMKUJMU5SCM/action/replication_record"}},"created_at":"2026-07-05T05:33:05.135233+00:00","updated_at":"2026-07-05T05:33:05.135233+00:00"}