{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ML44A5Z5EHWPUS2LGWR6EH45OT","short_pith_number":"pith:ML44A5Z5","canonical_record":{"source":{"id":"2002.08676","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T11:11:32Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"9486deac8df1520c91fb011153cbe8a822751431a7f5629b51773b201bcbd8f9","abstract_canon_sha256":"6e2ff22ed6c25503473439cc5cd77d9ad63d9ab1a6a29396d14338ba5b29c8c3"},"schema_version":"1.0"},"canonical_sha256":"62f9c0773d21ecfa4b4b35a3e21f9d74dbb01ba058a1eaa76eef9e2743c9cfd8","source":{"kind":"arxiv","id":"2002.08676","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.08676","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"arxiv_version","alias_value":"2002.08676v2","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.08676","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"pith_short_12","alias_value":"ML44A5Z5EHWP","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"pith_short_16","alias_value":"ML44A5Z5EHWPUS2L","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"pith_short_8","alias_value":"ML44A5Z5","created_at":"2026-07-05T01:09:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ML44A5Z5EHWPUS2LGWR6EH45OT","target":"record","payload":{"canonical_record":{"source":{"id":"2002.08676","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T11:11:32Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"9486deac8df1520c91fb011153cbe8a822751431a7f5629b51773b201bcbd8f9","abstract_canon_sha256":"6e2ff22ed6c25503473439cc5cd77d9ad63d9ab1a6a29396d14338ba5b29c8c3"},"schema_version":"1.0"},"canonical_sha256":"62f9c0773d21ecfa4b4b35a3e21f9d74dbb01ba058a1eaa76eef9e2743c9cfd8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:03.947761Z","signature_b64":"28aOv7X6SKH2twzYzKDNRHzCaBjcS8vk94/vWSuG70jb+xK5vvj4fbYbW8nBo6OhyNH8h2wPle5c/0L7SaPkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62f9c0773d21ecfa4b4b35a3e21f9d74dbb01ba058a1eaa76eef9e2743c9cfd8","last_reissued_at":"2026-07-05T01:09:03.947285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:03.947285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.08676","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":"2026-07-05T01:09:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qg6GtcRPbJppU9r1kXbvgbo0WMbeQ42P/1nx9wD95ZMEEvs8I4C5IBC7fbsTZ/P/CUKSPyeO+GEkCg3pkjrKDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:20:07.383994Z"},"content_sha256":"7c784f7726aae47592c2e6021ede453f5a4dc27c0bc7fdf5b1d72c9d2af9c794","schema_version":"1.0","event_id":"sha256:7c784f7726aae47592c2e6021ede453f5a4dc27c0bc7fdf5b1d72c9d2af9c794"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ML44A5Z5EHWPUS2LGWR6EH45OT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning with Differentiable Perturbed Optimizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Francis Bach, Jean-Philippe Vert, Marco Cuturi, Mathieu Blondel, Olivier Teboul, Quentin Berthet","submitted_at":"2020-02-20T11:11:32Z","abstract_excerpt":"Machine learning pipelines often rely on optimization procedures to make discrete decisions (e.g., sorting, picking closest neighbors, or shortest paths). Although these discrete decisions are easily computed, they break the back-propagation of computational graphs. In order to expand the scope of learning problems that can be solved in an end-to-end fashion, we propose a systematic method to transform optimizers into operations that are differentiable and never locally constant. Our approach relies on stochastically perturbed optimizers, and can be used readily together with existing solvers."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.08676","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/2002.08676/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:09:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VP7jwn1LzSWLmdGt/x350faSZYu13RloJnnesbUEgcxpJ8PDKYM4PFDt/v+BMet67uBTdMzLwCjfEqoQvCA8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:20:07.384826Z"},"content_sha256":"558111d6ff4ddf660af0be56f937c4adaee08e7f59a7af6908190b026f7bbea3","schema_version":"1.0","event_id":"sha256:558111d6ff4ddf660af0be56f937c4adaee08e7f59a7af6908190b026f7bbea3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ML44A5Z5EHWPUS2LGWR6EH45OT/bundle.json","state_url":"https://pith.science/pith/ML44A5Z5EHWPUS2LGWR6EH45OT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ML44A5Z5EHWPUS2LGWR6EH45OT/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":"2026-08-09T03:20:07Z","links":{"resolver":"https://pith.science/pith/ML44A5Z5EHWPUS2LGWR6EH45OT","bundle":"https://pith.science/pith/ML44A5Z5EHWPUS2LGWR6EH45OT/bundle.json","state":"https://pith.science/pith/ML44A5Z5EHWPUS2LGWR6EH45OT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ML44A5Z5EHWPUS2LGWR6EH45OT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ML44A5Z5EHWPUS2LGWR6EH45OT","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":"6e2ff22ed6c25503473439cc5cd77d9ad63d9ab1a6a29396d14338ba5b29c8c3","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T11:11:32Z","title_canon_sha256":"9486deac8df1520c91fb011153cbe8a822751431a7f5629b51773b201bcbd8f9"},"schema_version":"1.0","source":{"id":"2002.08676","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.08676","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"arxiv_version","alias_value":"2002.08676v2","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.08676","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"pith_short_12","alias_value":"ML44A5Z5EHWP","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"pith_short_16","alias_value":"ML44A5Z5EHWPUS2L","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"pith_short_8","alias_value":"ML44A5Z5","created_at":"2026-07-05T01:09:03Z"}],"graph_snapshots":[{"event_id":"sha256:558111d6ff4ddf660af0be56f937c4adaee08e7f59a7af6908190b026f7bbea3","target":"graph","created_at":"2026-07-05T01:09:03Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.08676/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine learning pipelines often rely on optimization procedures to make discrete decisions (e.g., sorting, picking closest neighbors, or shortest paths). Although these discrete decisions are easily computed, they break the back-propagation of computational graphs. In order to expand the scope of learning problems that can be solved in an end-to-end fashion, we propose a systematic method to transform optimizers into operations that are differentiable and never locally constant. Our approach relies on stochastically perturbed optimizers, and can be used readily together with existing solvers.","authors_text":"Francis Bach, Jean-Philippe Vert, Marco Cuturi, Mathieu Blondel, Olivier Teboul, Quentin Berthet","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T11:11:32Z","title":"Learning with Differentiable Perturbed Optimizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.08676","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":"sha256:7c784f7726aae47592c2e6021ede453f5a4dc27c0bc7fdf5b1d72c9d2af9c794","target":"record","created_at":"2026-07-05T01:09:03Z","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":"6e2ff22ed6c25503473439cc5cd77d9ad63d9ab1a6a29396d14338ba5b29c8c3","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T11:11:32Z","title_canon_sha256":"9486deac8df1520c91fb011153cbe8a822751431a7f5629b51773b201bcbd8f9"},"schema_version":"1.0","source":{"id":"2002.08676","kind":"arxiv","version":2}},"canonical_sha256":"62f9c0773d21ecfa4b4b35a3e21f9d74dbb01ba058a1eaa76eef9e2743c9cfd8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62f9c0773d21ecfa4b4b35a3e21f9d74dbb01ba058a1eaa76eef9e2743c9cfd8","first_computed_at":"2026-07-05T01:09:03.947285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:03.947285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"28aOv7X6SKH2twzYzKDNRHzCaBjcS8vk94/vWSuG70jb+xK5vvj4fbYbW8nBo6OhyNH8h2wPle5c/0L7SaPkDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:03.947761Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.08676","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c784f7726aae47592c2e6021ede453f5a4dc27c0bc7fdf5b1d72c9d2af9c794","sha256:558111d6ff4ddf660af0be56f937c4adaee08e7f59a7af6908190b026f7bbea3"],"state_sha256":"e09db37e454d58b1a7d5c86be1c63850404dfbcc6409f19fdf4018901f0958a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p9ppLu/gBr1+a1WzeROzCd9yjLul09UyZjFsbKIDsDpxFW08ZaZSivnN3OWO5uD7MiyXC3we6TwxfamvVhk9Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:20:07.389774Z","bundle_sha256":"093f4afedc2aaee796499518ea6e3d91a924d7e6db5678dde50e32c78183d048"}}