{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:J73JLVDTHVOXJX7J3P7XSBRSNT","short_pith_number":"pith:J73JLVDT","canonical_record":{"source":{"id":"1905.10108","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T09:33:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"07b676663303d862089a8c320f76091b574445d5725885ed9c18c37959b4e196","abstract_canon_sha256":"24f499280f41de3c9a1c6891e3d05ac60877e693cf01645b5f7e7f01557bd5c2"},"schema_version":"1.0"},"canonical_sha256":"4ff695d4733d5d74dfe9dbff7906326cce65e2298c7ae48bfc3f9b1428ed16f3","source":{"kind":"arxiv","id":"1905.10108","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10108","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10108v1","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10108","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"J73JLVDTHVOX","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"J73JLVDTHVOXJX7J","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"J73JLVDT","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:J73JLVDTHVOXJX7J3P7XSBRSNT","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10108","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T09:33:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"07b676663303d862089a8c320f76091b574445d5725885ed9c18c37959b4e196","abstract_canon_sha256":"24f499280f41de3c9a1c6891e3d05ac60877e693cf01645b5f7e7f01557bd5c2"},"schema_version":"1.0"},"canonical_sha256":"4ff695d4733d5d74dfe9dbff7906326cce65e2298c7ae48bfc3f9b1428ed16f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:11.365075Z","signature_b64":"aGJ+YcevYUt+bpswGmxWkELtQDEVUoHDtGtC6MV4yfnMpEp/9ix7gSBQj/k7B6RG/U9dcB6+bCNZB3PopIF8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ff695d4733d5d74dfe9dbff7906326cce65e2298c7ae48bfc3f9b1428ed16f3","last_reissued_at":"2026-05-17T23:45:11.364366Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:11.364366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10108","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"asKCWNkghMpm9kJXG/66dOGlYwwVewh+Qdw67x6THVJQvl/tZLMzCSJNNptbdUIZ62MH3FtvMMLIfmbyNMz0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T23:16:57.920065Z"},"content_sha256":"88211d3f0ae37ad9763b89272db3297f64654cfa58b4b6d4ddcd791f66cd3cc1","schema_version":"1.0","event_id":"sha256:88211d3f0ae37ad9763b89272db3297f64654cfa58b4b6d4ddcd791f66cd3cc1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:J73JLVDTHVOXJX7J3P7XSBRSNT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Surrogate Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Josif Grabocka, Lars Schmidt-Thieme, Randolf Scholz","submitted_at":"2019-05-24T09:33:04Z","abstract_excerpt":"The minimization of loss functions is the heart and soul of Machine Learning. In this paper, we propose an off-the-shelf optimization approach that can minimize virtually any non-differentiable and non-decomposable loss function (e.g. Miss-classification Rate, AUC, F1, Jaccard Index, Mathew Correlation Coefficient, etc.) seamlessly. Our strategy learns smooth relaxation versions of the true losses by approximating them through a surrogate neural network. The proposed loss networks are set-wise models which are invariant to the order of mini-batch instances. Ultimately, the surrogate losses are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10108","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MyLr7aRsOXHMjUCy6a3Y+7gDaNsMuplyw/JJmHUXzlCacMOMHSQnuo64rHJ1eQjJ0Nerzg5o/5urg060dIL+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T23:16:57.920431Z"},"content_sha256":"68f0ca73a6a7a2882fbc23fe86c97550f745048f65ba5484ea4340994b0ddd27","schema_version":"1.0","event_id":"sha256:68f0ca73a6a7a2882fbc23fe86c97550f745048f65ba5484ea4340994b0ddd27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J73JLVDTHVOXJX7J3P7XSBRSNT/bundle.json","state_url":"https://pith.science/pith/J73JLVDTHVOXJX7J3P7XSBRSNT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J73JLVDTHVOXJX7J3P7XSBRSNT/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":"2026-05-30T23:16:57Z","links":{"resolver":"https://pith.science/pith/J73JLVDTHVOXJX7J3P7XSBRSNT","bundle":"https://pith.science/pith/J73JLVDTHVOXJX7J3P7XSBRSNT/bundle.json","state":"https://pith.science/pith/J73JLVDTHVOXJX7J3P7XSBRSNT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J73JLVDTHVOXJX7J3P7XSBRSNT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:J73JLVDTHVOXJX7J3P7XSBRSNT","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":"24f499280f41de3c9a1c6891e3d05ac60877e693cf01645b5f7e7f01557bd5c2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T09:33:04Z","title_canon_sha256":"07b676663303d862089a8c320f76091b574445d5725885ed9c18c37959b4e196"},"schema_version":"1.0","source":{"id":"1905.10108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10108","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10108v1","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10108","created_at":"2026-05-17T23:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"J73JLVDTHVOX","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"J73JLVDTHVOXJX7J","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"J73JLVDT","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:68f0ca73a6a7a2882fbc23fe86c97550f745048f65ba5484ea4340994b0ddd27","target":"graph","created_at":"2026-05-17T23:45:11Z","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":"The minimization of loss functions is the heart and soul of Machine Learning. In this paper, we propose an off-the-shelf optimization approach that can minimize virtually any non-differentiable and non-decomposable loss function (e.g. Miss-classification Rate, AUC, F1, Jaccard Index, Mathew Correlation Coefficient, etc.) seamlessly. Our strategy learns smooth relaxation versions of the true losses by approximating them through a surrogate neural network. The proposed loss networks are set-wise models which are invariant to the order of mini-batch instances. Ultimately, the surrogate losses are","authors_text":"Josif Grabocka, Lars Schmidt-Thieme, Randolf Scholz","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T09:33:04Z","title":"Learning Surrogate Losses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10108","kind":"arxiv","version":1},"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":"sha256:88211d3f0ae37ad9763b89272db3297f64654cfa58b4b6d4ddcd791f66cd3cc1","target":"record","created_at":"2026-05-17T23:45:11Z","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":"24f499280f41de3c9a1c6891e3d05ac60877e693cf01645b5f7e7f01557bd5c2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-24T09:33:04Z","title_canon_sha256":"07b676663303d862089a8c320f76091b574445d5725885ed9c18c37959b4e196"},"schema_version":"1.0","source":{"id":"1905.10108","kind":"arxiv","version":1}},"canonical_sha256":"4ff695d4733d5d74dfe9dbff7906326cce65e2298c7ae48bfc3f9b1428ed16f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ff695d4733d5d74dfe9dbff7906326cce65e2298c7ae48bfc3f9b1428ed16f3","first_computed_at":"2026-05-17T23:45:11.364366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:11.364366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aGJ+YcevYUt+bpswGmxWkELtQDEVUoHDtGtC6MV4yfnMpEp/9ix7gSBQj/k7B6RG/U9dcB6+bCNZB3PopIF8Cw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:11.365075Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88211d3f0ae37ad9763b89272db3297f64654cfa58b4b6d4ddcd791f66cd3cc1","sha256:68f0ca73a6a7a2882fbc23fe86c97550f745048f65ba5484ea4340994b0ddd27"],"state_sha256":"226c5f4ad67bcff81e40465e4fb429fae26223da7edfa898612fabac70afc5a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/eQhtOgNmMv3RBZJxPg3Fyur+EoVudBNwmF8olocI3rwjDSg4Eq4TQSMnIK9xKtVCmKpVuwH1+36Xk5Tr4pZDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T23:16:57.922337Z","bundle_sha256":"095b8510aa820a6eaa4266b92aa8fcbba7eee3f3416cb070c1fe4363c1d2a3c2"}}