{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:42WALJTUHZ6TPYUZXQFK7ZR2JU","short_pith_number":"pith:42WALJTU","schema_version":"1.0","canonical_sha256":"e6ac05a6743e7d37e299bc0aafe63a4d0820d999b37d3654fd729f5887e2e667","source":{"kind":"arxiv","id":"1709.04108","version":1},"attestation_state":"computed","paper":{"title":"Co-training for Demographic Classification Using Deep Learning from Label Proportions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Aron Culotta, Ehsan Mohammady Ardehaly","submitted_at":"2017-09-13T02:06:19Z","abstract_excerpt":"Deep learning algorithms have recently produced state-of-the-art accuracy in many classification tasks, but this success is typically dependent on access to many annotated training examples. For domains without such data, an attractive alternative is to train models with light, or distant supervision. In this paper, we introduce a deep neural network for the Learning from Label Proportion (LLP) setting, in which the training data consist of bags of unlabeled instances with associated label distributions for each bag. We introduce a new regularization layer, Batch Averager, that can be appended"},"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":"1709.04108","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-13T02:06:19Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ba8366ed124072cbd55d27875c3a2c8e128b8f9089fcb46fd9e45af39d0a3913","abstract_canon_sha256":"4c3941ebadc8d87ea6a3e2017369aae60331459341868d12df3bf8a0ea5c1225"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:04.464449Z","signature_b64":"JXpmwA+WSM2EEV+e/H7O9TeKUrEgGbaXJ2EWL6b9pbPgp212fLGhhidGLxS1HwOwzxlGHBraMI2lhqOKfuo0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6ac05a6743e7d37e299bc0aafe63a4d0820d999b37d3654fd729f5887e2e667","last_reissued_at":"2026-05-18T00:27:04.463660Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:04.463660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Co-training for Demographic Classification Using Deep Learning from Label Proportions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Aron Culotta, Ehsan Mohammady Ardehaly","submitted_at":"2017-09-13T02:06:19Z","abstract_excerpt":"Deep learning algorithms have recently produced state-of-the-art accuracy in many classification tasks, but this success is typically dependent on access to many annotated training examples. For domains without such data, an attractive alternative is to train models with light, or distant supervision. In this paper, we introduce a deep neural network for the Learning from Label Proportion (LLP) setting, in which the training data consist of bags of unlabeled instances with associated label distributions for each bag. We introduce a new regularization layer, Batch Averager, that can be appended"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04108","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":""},"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":"1709.04108","created_at":"2026-05-18T00:27:04.463779+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.04108v1","created_at":"2026-05-18T00:27:04.463779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04108","created_at":"2026-05-18T00:27:04.463779+00:00"},{"alias_kind":"pith_short_12","alias_value":"42WALJTUHZ6T","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"42WALJTUHZ6TPYUZ","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"42WALJTU","created_at":"2026-05-18T12:30:58.224056+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/42WALJTUHZ6TPYUZXQFK7ZR2JU","json":"https://pith.science/pith/42WALJTUHZ6TPYUZXQFK7ZR2JU.json","graph_json":"https://pith.science/api/pith-number/42WALJTUHZ6TPYUZXQFK7ZR2JU/graph.json","events_json":"https://pith.science/api/pith-number/42WALJTUHZ6TPYUZXQFK7ZR2JU/events.json","paper":"https://pith.science/paper/42WALJTU"},"agent_actions":{"view_html":"https://pith.science/pith/42WALJTUHZ6TPYUZXQFK7ZR2JU","download_json":"https://pith.science/pith/42WALJTUHZ6TPYUZXQFK7ZR2JU.json","view_paper":"https://pith.science/paper/42WALJTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.04108&json=true","fetch_graph":"https://pith.science/api/pith-number/42WALJTUHZ6TPYUZXQFK7ZR2JU/graph.json","fetch_events":"https://pith.science/api/pith-number/42WALJTUHZ6TPYUZXQFK7ZR2JU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42WALJTUHZ6TPYUZXQFK7ZR2JU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42WALJTUHZ6TPYUZXQFK7ZR2JU/action/storage_attestation","attest_author":"https://pith.science/pith/42WALJTUHZ6TPYUZXQFK7ZR2JU/action/author_attestation","sign_citation":"https://pith.science/pith/42WALJTUHZ6TPYUZXQFK7ZR2JU/action/citation_signature","submit_replication":"https://pith.science/pith/42WALJTUHZ6TPYUZXQFK7ZR2JU/action/replication_record"}},"created_at":"2026-05-18T00:27:04.463779+00:00","updated_at":"2026-05-18T00:27:04.463779+00:00"}