{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:IWP46PDJUKU2LKJK7ZY77NKYNI","short_pith_number":"pith:IWP46PDJ","canonical_record":{"source":{"id":"2110.00604","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-10-01T18:20:14Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"52a990667e1ebb1e169693b70f4c409ef425e17d3fccccf31f5f8b2081a3cd26","abstract_canon_sha256":"b55be099e384806e9b07070d36b2ce66a00d88df35e4f9dbfb81f5d83c3299bb"},"schema_version":"1.0"},"canonical_sha256":"459fcf3c69a2a9a5a92afe71ffb5586a258bde7a6b08d0d49565606e4d47be90","source":{"kind":"arxiv","id":"2110.00604","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00604","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00604v3","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00604","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"IWP46PDJUKU2","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"IWP46PDJUKU2LKJK","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"IWP46PDJ","created_at":"2026-07-05T07:09:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:IWP46PDJUKU2LKJK7ZY77NKYNI","target":"record","payload":{"canonical_record":{"source":{"id":"2110.00604","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-10-01T18:20:14Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"52a990667e1ebb1e169693b70f4c409ef425e17d3fccccf31f5f8b2081a3cd26","abstract_canon_sha256":"b55be099e384806e9b07070d36b2ce66a00d88df35e4f9dbfb81f5d83c3299bb"},"schema_version":"1.0"},"canonical_sha256":"459fcf3c69a2a9a5a92afe71ffb5586a258bde7a6b08d0d49565606e4d47be90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:41.748863Z","signature_b64":"7halIOPUom4BqbeCaS75SXQeXm8iL0midPAf5ud2A52+w6erjbTjZilot+3SowXWnjRUM3vkiWggptedjHeoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"459fcf3c69a2a9a5a92afe71ffb5586a258bde7a6b08d0d49565606e4d47be90","last_reissued_at":"2026-07-05T07:09:41.748371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:41.748371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.00604","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HblIxQhGtkyNjPi68geyzjB/ox5GZN2yKRV+T7kBByvZw9boGE70a+pUUhfJDHDaksJraNbJZdyAYyNXCoM5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:31:36.052070Z"},"content_sha256":"c3d6fc9cdb888d25387ba3f827ade6565c52fa5795becddda0f92a8b7bec3931","schema_version":"1.0","event_id":"sha256:c3d6fc9cdb888d25387ba3f827ade6565c52fa5795becddda0f92a8b7bec3931"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:IWP46PDJUKU2LKJK7ZY77NKYNI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Inexact bilevel stochastic gradient methods for constrained and unconstrained lower-level problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Griffin Dean Kent, Luis Nunes Vicente, Tommaso Giovannelli","submitted_at":"2021-10-01T18:20:14Z","abstract_excerpt":"Two-level stochastic optimization formulations have become instrumental in a number of machine learning contexts such as continual learning, neural architecture search, adversarial learning, and hyperparameter tuning. Practical stochastic bilevel optimization problems become challenging in optimization or learning scenarios where the number of variables is high or there are constraints.\n  In this paper, we introduce a bilevel stochastic gradient method for bilevel problems with nonlinear and possibly nonconvex lower-level constraints. We also present a comprehensive convergence theory that add"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00604","kind":"arxiv","version":3},"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/2110.00604/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":"2026-07-05T07:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PLtK9w/69M425g/agYdOUVK2ScmcYtucj9t8XfktDKz4rD5woe7Rfj2249qgyMxaOdpyXFC/rXUEZDVADwoxBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:31:36.052619Z"},"content_sha256":"18c9325577d6cb30403d8c9a6bdbbd117cd6ed2e7bc875494f0fb92fdf1ab580","schema_version":"1.0","event_id":"sha256:18c9325577d6cb30403d8c9a6bdbbd117cd6ed2e7bc875494f0fb92fdf1ab580"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IWP46PDJUKU2LKJK7ZY77NKYNI/bundle.json","state_url":"https://pith.science/pith/IWP46PDJUKU2LKJK7ZY77NKYNI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IWP46PDJUKU2LKJK7ZY77NKYNI/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":"2026-08-10T11:31:36Z","links":{"resolver":"https://pith.science/pith/IWP46PDJUKU2LKJK7ZY77NKYNI","bundle":"https://pith.science/pith/IWP46PDJUKU2LKJK7ZY77NKYNI/bundle.json","state":"https://pith.science/pith/IWP46PDJUKU2LKJK7ZY77NKYNI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IWP46PDJUKU2LKJK7ZY77NKYNI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IWP46PDJUKU2LKJK7ZY77NKYNI","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":"b55be099e384806e9b07070d36b2ce66a00d88df35e4f9dbfb81f5d83c3299bb","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-10-01T18:20:14Z","title_canon_sha256":"52a990667e1ebb1e169693b70f4c409ef425e17d3fccccf31f5f8b2081a3cd26"},"schema_version":"1.0","source":{"id":"2110.00604","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00604","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00604v3","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00604","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"IWP46PDJUKU2","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"IWP46PDJUKU2LKJK","created_at":"2026-07-05T07:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"IWP46PDJ","created_at":"2026-07-05T07:09:41Z"}],"graph_snapshots":[{"event_id":"sha256:18c9325577d6cb30403d8c9a6bdbbd117cd6ed2e7bc875494f0fb92fdf1ab580","target":"graph","created_at":"2026-07-05T07:09:41Z","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/2110.00604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Two-level stochastic optimization formulations have become instrumental in a number of machine learning contexts such as continual learning, neural architecture search, adversarial learning, and hyperparameter tuning. Practical stochastic bilevel optimization problems become challenging in optimization or learning scenarios where the number of variables is high or there are constraints.\n  In this paper, we introduce a bilevel stochastic gradient method for bilevel problems with nonlinear and possibly nonconvex lower-level constraints. We also present a comprehensive convergence theory that add","authors_text":"Griffin Dean Kent, Luis Nunes Vicente, Tommaso Giovannelli","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-10-01T18:20:14Z","title":"Inexact bilevel stochastic gradient methods for constrained and unconstrained lower-level problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00604","kind":"arxiv","version":3},"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:c3d6fc9cdb888d25387ba3f827ade6565c52fa5795becddda0f92a8b7bec3931","target":"record","created_at":"2026-07-05T07:09:41Z","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":"b55be099e384806e9b07070d36b2ce66a00d88df35e4f9dbfb81f5d83c3299bb","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-10-01T18:20:14Z","title_canon_sha256":"52a990667e1ebb1e169693b70f4c409ef425e17d3fccccf31f5f8b2081a3cd26"},"schema_version":"1.0","source":{"id":"2110.00604","kind":"arxiv","version":3}},"canonical_sha256":"459fcf3c69a2a9a5a92afe71ffb5586a258bde7a6b08d0d49565606e4d47be90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"459fcf3c69a2a9a5a92afe71ffb5586a258bde7a6b08d0d49565606e4d47be90","first_computed_at":"2026-07-05T07:09:41.748371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:41.748371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7halIOPUom4BqbeCaS75SXQeXm8iL0midPAf5ud2A52+w6erjbTjZilot+3SowXWnjRUM3vkiWggptedjHeoCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:41.748863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.00604","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3d6fc9cdb888d25387ba3f827ade6565c52fa5795becddda0f92a8b7bec3931","sha256:18c9325577d6cb30403d8c9a6bdbbd117cd6ed2e7bc875494f0fb92fdf1ab580"],"state_sha256":"9389071d3d0b16cad38e22b8a123ff8788348f74d250bbc4c21141cf75166ee4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eQHWTXiHIvLo9aSoC+Rk1OY51H6PmWZo3oqvS0PiGjb/wgWxP+5vceyfYSu+8AfdjIcIMYn2Ey4nGbdc9zS3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:31:36.057777Z","bundle_sha256":"b78ac6c02390be30c2bd9513d952c7b663f7f7811cb103ff12f58c4f809949dd"}}