{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:LOB3PUM64DJXI3SALOW2TUGGOO","short_pith_number":"pith:LOB3PUM6","canonical_record":{"source":{"id":"1905.12909","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T08:26:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1045851f3a679702cf8e9a40f69c8e4fbe46bee70162d0f4d69e15fd0393729a","abstract_canon_sha256":"4b047a77d908e874a33635d0e47f07d4c035d6797ac66d8c7d65a80cd170aba1"},"schema_version":"1.0"},"canonical_sha256":"5b83b7d19ee0d3746e405bada9d0c673b3c630c6c7ab76a5ce59cbf732e4078a","source":{"kind":"arxiv","id":"1905.12909","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12909","created_at":"2026-05-17T23:42:13Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12909v2","created_at":"2026-05-17T23:42:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12909","created_at":"2026-05-17T23:42:13Z"},{"alias_kind":"pith_short_12","alias_value":"LOB3PUM64DJX","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LOB3PUM64DJXI3SA","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LOB3PUM6","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:LOB3PUM64DJXI3SALOW2TUGGOO","target":"record","payload":{"canonical_record":{"source":{"id":"1905.12909","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T08:26:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1045851f3a679702cf8e9a40f69c8e4fbe46bee70162d0f4d69e15fd0393729a","abstract_canon_sha256":"4b047a77d908e874a33635d0e47f07d4c035d6797ac66d8c7d65a80cd170aba1"},"schema_version":"1.0"},"canonical_sha256":"5b83b7d19ee0d3746e405bada9d0c673b3c630c6c7ab76a5ce59cbf732e4078a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:13.404937Z","signature_b64":"LtUDnkwb6g0IixbQBaAubJ6J6az8lLaN0GpZveF+LV8Dtek1BNL1WzWp+se9gltb+5krHiFiXC9oQ85hq+TjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b83b7d19ee0d3746e405bada9d0c673b3c630c6c7ab76a5ce59cbf732e4078a","last_reissued_at":"2026-05-17T23:42:13.404468Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:13.404468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.12909","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":"2026-05-17T23:42:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TcK8h3Xe+4iwvPkJGyDEUKLcYnSwvE214b7r5aJg+kvAHA4QZtAbRbeiYshMeLfpf4QhfHJNkGJvoa5ehbnzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T14:44:23.140072Z"},"content_sha256":"10f9e06ebfb9265346c7a6908e7916432ac3085ffe8b41391b228f31bde1da6a","schema_version":"1.0","event_id":"sha256:10f9e06ebfb9265346c7a6908e7916432ac3085ffe8b41391b228f31bde1da6a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:LOB3PUM64DJXI3SALOW2TUGGOO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep multi-class learning from label proportions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gabriel Dulac-Arnold, Jean-Philippe Vert, Lucas Beyer, Marco Cuturi, Neil Zeghidour","submitted_at":"2019-05-30T08:26:47Z","abstract_excerpt":"We propose a learning algorithm capable of learning from label proportions instead of direct data labels. In this scenario, our data are arranged into various bags of a certain size, and only the proportions of each label within a given bag are known. This is a common situation in cases where per-data labeling is lengthy, but a more general label is easily accessible. Several approaches have been proposed to learn in this setting with linear models in the multiclass setting, or with nonlinear models in the binary classification setting. Here we investigate the more general nonlinear multiclass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12909","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":"2026-05-17T23:42:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ImhXOjPfCPJX37I16N5XI6/Dx6vCvVlbaUxJ7177hGxZr+HpFdXFGmlTpS5w4nhlNIIfmx0auIRNCyiFafHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T14:44:23.140526Z"},"content_sha256":"6ae830bcb32274059859103d2eb39d5dedaaa9d6d16812b48a9c721d288ce875","schema_version":"1.0","event_id":"sha256:6ae830bcb32274059859103d2eb39d5dedaaa9d6d16812b48a9c721d288ce875"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LOB3PUM64DJXI3SALOW2TUGGOO/bundle.json","state_url":"https://pith.science/pith/LOB3PUM64DJXI3SALOW2TUGGOO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LOB3PUM64DJXI3SALOW2TUGGOO/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":"2026-05-25T14:44:23Z","links":{"resolver":"https://pith.science/pith/LOB3PUM64DJXI3SALOW2TUGGOO","bundle":"https://pith.science/pith/LOB3PUM64DJXI3SALOW2TUGGOO/bundle.json","state":"https://pith.science/pith/LOB3PUM64DJXI3SALOW2TUGGOO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LOB3PUM64DJXI3SALOW2TUGGOO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LOB3PUM64DJXI3SALOW2TUGGOO","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":"4b047a77d908e874a33635d0e47f07d4c035d6797ac66d8c7d65a80cd170aba1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T08:26:47Z","title_canon_sha256":"1045851f3a679702cf8e9a40f69c8e4fbe46bee70162d0f4d69e15fd0393729a"},"schema_version":"1.0","source":{"id":"1905.12909","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12909","created_at":"2026-05-17T23:42:13Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12909v2","created_at":"2026-05-17T23:42:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12909","created_at":"2026-05-17T23:42:13Z"},{"alias_kind":"pith_short_12","alias_value":"LOB3PUM64DJX","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LOB3PUM64DJXI3SA","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LOB3PUM6","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:6ae830bcb32274059859103d2eb39d5dedaaa9d6d16812b48a9c721d288ce875","target":"graph","created_at":"2026-05-17T23:42:13Z","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":"We propose a learning algorithm capable of learning from label proportions instead of direct data labels. In this scenario, our data are arranged into various bags of a certain size, and only the proportions of each label within a given bag are known. This is a common situation in cases where per-data labeling is lengthy, but a more general label is easily accessible. Several approaches have been proposed to learn in this setting with linear models in the multiclass setting, or with nonlinear models in the binary classification setting. Here we investigate the more general nonlinear multiclass","authors_text":"Gabriel Dulac-Arnold, Jean-Philippe Vert, Lucas Beyer, Marco Cuturi, Neil Zeghidour","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T08:26:47Z","title":"Deep multi-class learning from label proportions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12909","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":"sha256:10f9e06ebfb9265346c7a6908e7916432ac3085ffe8b41391b228f31bde1da6a","target":"record","created_at":"2026-05-17T23:42:13Z","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":"4b047a77d908e874a33635d0e47f07d4c035d6797ac66d8c7d65a80cd170aba1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T08:26:47Z","title_canon_sha256":"1045851f3a679702cf8e9a40f69c8e4fbe46bee70162d0f4d69e15fd0393729a"},"schema_version":"1.0","source":{"id":"1905.12909","kind":"arxiv","version":2}},"canonical_sha256":"5b83b7d19ee0d3746e405bada9d0c673b3c630c6c7ab76a5ce59cbf732e4078a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b83b7d19ee0d3746e405bada9d0c673b3c630c6c7ab76a5ce59cbf732e4078a","first_computed_at":"2026-05-17T23:42:13.404468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:13.404468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LtUDnkwb6g0IixbQBaAubJ6J6az8lLaN0GpZveF+LV8Dtek1BNL1WzWp+se9gltb+5krHiFiXC9oQ85hq+TjCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:13.404937Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.12909","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10f9e06ebfb9265346c7a6908e7916432ac3085ffe8b41391b228f31bde1da6a","sha256:6ae830bcb32274059859103d2eb39d5dedaaa9d6d16812b48a9c721d288ce875"],"state_sha256":"80c26098c0c5bed0e549a781df349371e88c209fd355c04490d3855fb724327e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VOi6NTm1gaZae1d/jKFahg/l7nqLtq1KNYUvNTVAc82PMzXGKCl2I6jzHlXQn9usGIiGptgc5G1axvMTZkrICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T14:44:23.143923Z","bundle_sha256":"170f83d9afd797cbbece89565c896bddfa6a41c3f6a00b92da6ea569f3096b32"}}