{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TJ5FNXJGKWTCYJBSJWP5S62JU5","short_pith_number":"pith:TJ5FNXJG","schema_version":"1.0","canonical_sha256":"9a7a56dd2655a62c24324d9fd97b49a76d303b8bec459184211f9b55821b4fc5","source":{"kind":"arxiv","id":"2302.03115","version":2},"attestation_state":"computed","paper":{"title":"Easy Learning from Label Proportions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andres Munoz Medina, Claudio Gentile, Heejin Choi, Robert Istvan Busa-Fekete, Travis Dick","submitted_at":"2023-02-06T20:41:38Z","abstract_excerpt":"We consider the problem of Learning from Label Proportions (LLP), a weakly supervised classification setup where instances are grouped into \"bags\", and only the frequency of class labels at each bag is available. Albeit, the objective of the learner is to achieve low task loss at an individual instance level. Here we propose Easyllp: a flexible and simple-to-implement debiasing approach based on aggregate labels, which operates on arbitrary loss functions. Our technique allows us to accurately estimate the expected loss of an arbitrary model at an individual level. We showcase the flexibility "},"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":"2302.03115","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T20:41:38Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7a38080f5bc9ee93461e087ebbb8e2e92b4f88cb6d938f185eb047f0ad3631c9","abstract_canon_sha256":"1ca0bd2043cc257fc4d0dd8e5c4869b7104b5fa57a42e1abd9f11e4d08e65694"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:41:41.330305Z","signature_b64":"6PNLutJed620f0khyNek8KUkAvzi2VorRHP8UxtIPrJRKTOqF1lNsiVRl4VsYDl3kb4Uz1K31a8jDbZPkzlTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a7a56dd2655a62c24324d9fd97b49a76d303b8bec459184211f9b55821b4fc5","last_reissued_at":"2026-07-05T05:41:41.329861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:41:41.329861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Easy Learning from Label Proportions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andres Munoz Medina, Claudio Gentile, Heejin Choi, Robert Istvan Busa-Fekete, Travis Dick","submitted_at":"2023-02-06T20:41:38Z","abstract_excerpt":"We consider the problem of Learning from Label Proportions (LLP), a weakly supervised classification setup where instances are grouped into \"bags\", and only the frequency of class labels at each bag is available. Albeit, the objective of the learner is to achieve low task loss at an individual instance level. Here we propose Easyllp: a flexible and simple-to-implement debiasing approach based on aggregate labels, which operates on arbitrary loss functions. Our technique allows us to accurately estimate the expected loss of an arbitrary model at an individual level. We showcase the flexibility "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03115","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.03115/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":"2302.03115","created_at":"2026-07-05T05:41:41.329918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03115v2","created_at":"2026-07-05T05:41:41.329918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03115","created_at":"2026-07-05T05:41:41.329918+00:00"},{"alias_kind":"pith_short_12","alias_value":"TJ5FNXJGKWTC","created_at":"2026-07-05T05:41:41.329918+00:00"},{"alias_kind":"pith_short_16","alias_value":"TJ5FNXJGKWTCYJBS","created_at":"2026-07-05T05:41:41.329918+00:00"},{"alias_kind":"pith_short_8","alias_value":"TJ5FNXJG","created_at":"2026-07-05T05:41:41.329918+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19063","citing_title":"Mapping Uncharted Symmetries: Machine Discovery in Combinatorics","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TJ5FNXJGKWTCYJBSJWP5S62JU5","json":"https://pith.science/pith/TJ5FNXJGKWTCYJBSJWP5S62JU5.json","graph_json":"https://pith.science/api/pith-number/TJ5FNXJGKWTCYJBSJWP5S62JU5/graph.json","events_json":"https://pith.science/api/pith-number/TJ5FNXJGKWTCYJBSJWP5S62JU5/events.json","paper":"https://pith.science/paper/TJ5FNXJG"},"agent_actions":{"view_html":"https://pith.science/pith/TJ5FNXJGKWTCYJBSJWP5S62JU5","download_json":"https://pith.science/pith/TJ5FNXJGKWTCYJBSJWP5S62JU5.json","view_paper":"https://pith.science/paper/TJ5FNXJG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03115&json=true","fetch_graph":"https://pith.science/api/pith-number/TJ5FNXJGKWTCYJBSJWP5S62JU5/graph.json","fetch_events":"https://pith.science/api/pith-number/TJ5FNXJGKWTCYJBSJWP5S62JU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TJ5FNXJGKWTCYJBSJWP5S62JU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TJ5FNXJGKWTCYJBSJWP5S62JU5/action/storage_attestation","attest_author":"https://pith.science/pith/TJ5FNXJGKWTCYJBSJWP5S62JU5/action/author_attestation","sign_citation":"https://pith.science/pith/TJ5FNXJGKWTCYJBSJWP5S62JU5/action/citation_signature","submit_replication":"https://pith.science/pith/TJ5FNXJGKWTCYJBSJWP5S62JU5/action/replication_record"}},"created_at":"2026-07-05T05:41:41.329918+00:00","updated_at":"2026-07-05T05:41:41.329918+00:00"}