{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TEQBKSUXMQUFKBW3E7GDJ52CFR","short_pith_number":"pith:TEQBKSUX","canonical_record":{"source":{"id":"2505.06805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-11T01:05:29Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f4e25ec25a54fe7a6bbaaf4f660c302a14d84ef8c5a6d429573c567e632093b3","abstract_canon_sha256":"c0819b1c5fa1d63a363a048e0ad54810f32d1ed3f96cb1dd86d2ebf662c11916"},"schema_version":"1.0"},"canonical_sha256":"9920154a9764285506db27cc34f7422c778c50a8d065f11f83e864e0e311f21a","source":{"kind":"arxiv","id":"2505.06805","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06805","created_at":"2026-07-05T11:01:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06805v1","created_at":"2026-07-05T11:01:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06805","created_at":"2026-07-05T11:01:16Z"},{"alias_kind":"pith_short_12","alias_value":"TEQBKSUXMQUF","created_at":"2026-07-05T11:01:16Z"},{"alias_kind":"pith_short_16","alias_value":"TEQBKSUXMQUFKBW3","created_at":"2026-07-05T11:01:16Z"},{"alias_kind":"pith_short_8","alias_value":"TEQBKSUX","created_at":"2026-07-05T11:01:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TEQBKSUXMQUFKBW3E7GDJ52CFR","target":"record","payload":{"canonical_record":{"source":{"id":"2505.06805","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-11T01:05:29Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f4e25ec25a54fe7a6bbaaf4f660c302a14d84ef8c5a6d429573c567e632093b3","abstract_canon_sha256":"c0819b1c5fa1d63a363a048e0ad54810f32d1ed3f96cb1dd86d2ebf662c11916"},"schema_version":"1.0"},"canonical_sha256":"9920154a9764285506db27cc34f7422c778c50a8d065f11f83e864e0e311f21a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:16.035717Z","signature_b64":"MB8K1CKi3SUPkqvy80qrpGRUN+vUqgehqvqBhi4gr/QK+fIENWrX1crI7HhfG9W5H9D0C4ljZ/jv3nCXZZmqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9920154a9764285506db27cc34f7422c778c50a8d065f11f83e864e0e311f21a","last_reissued_at":"2026-07-05T11:01:16.035251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:16.035251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.06805","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":"2026-07-05T11:01:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T3A++z8Td2P+6peBbT/hlXgd/jx+WqmuR1ApIEv3xXx8lFfg6HKmZsJnOE/lOiVL+z1NIIRXwVUZJ1QE3ejTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:12:20.209740Z"},"content_sha256":"b7cba27da672c00b3174d62b87d208f9bc3ed3b0fd51b4560b9d1efd2538a555","schema_version":"1.0","event_id":"sha256:b7cba27da672c00b3174d62b87d208f9bc3ed3b0fd51b4560b9d1efd2538a555"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TEQBKSUXMQUFKBW3E7GDJ52CFR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A stochastic gradient method for trilevel optimization","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":"2025-05-11T01:05:29Z","abstract_excerpt":"With the success that the field of bilevel optimization has seen in recent years, similar methodologies have started being applied to solving more difficult applications that arise in trilevel optimization. At the helm of these applications are new machine learning formulations that have been proposed in the trilevel context and, as a result, efficient and theoretically sound stochastic methods are required. In this work, we propose the first-ever stochastic gradient descent method for solving unconstrained trilevel optimization problems and provide a convergence theory that covers all forms o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06805","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.06805/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":"2026-07-05T11:01:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8qutWydmc6u6x6fyqBpgkPatzL2Vxcp4K4mWhV2kri+eszhHaF6/GR6g/k8JGf9QBuMIC1abaoojH+3X7usiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:12:20.210264Z"},"content_sha256":"c924fee326d2bc94651d80edab9e88d4b0301fa9b92f1f07f26ff0cbef7de02e","schema_version":"1.0","event_id":"sha256:c924fee326d2bc94651d80edab9e88d4b0301fa9b92f1f07f26ff0cbef7de02e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TEQBKSUXMQUFKBW3E7GDJ52CFR/bundle.json","state_url":"https://pith.science/pith/TEQBKSUXMQUFKBW3E7GDJ52CFR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TEQBKSUXMQUFKBW3E7GDJ52CFR/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":"2026-08-09T14:12:20Z","links":{"resolver":"https://pith.science/pith/TEQBKSUXMQUFKBW3E7GDJ52CFR","bundle":"https://pith.science/pith/TEQBKSUXMQUFKBW3E7GDJ52CFR/bundle.json","state":"https://pith.science/pith/TEQBKSUXMQUFKBW3E7GDJ52CFR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TEQBKSUXMQUFKBW3E7GDJ52CFR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TEQBKSUXMQUFKBW3E7GDJ52CFR","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":"c0819b1c5fa1d63a363a048e0ad54810f32d1ed3f96cb1dd86d2ebf662c11916","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-11T01:05:29Z","title_canon_sha256":"f4e25ec25a54fe7a6bbaaf4f660c302a14d84ef8c5a6d429573c567e632093b3"},"schema_version":"1.0","source":{"id":"2505.06805","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.06805","created_at":"2026-07-05T11:01:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.06805v1","created_at":"2026-07-05T11:01:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06805","created_at":"2026-07-05T11:01:16Z"},{"alias_kind":"pith_short_12","alias_value":"TEQBKSUXMQUF","created_at":"2026-07-05T11:01:16Z"},{"alias_kind":"pith_short_16","alias_value":"TEQBKSUXMQUFKBW3","created_at":"2026-07-05T11:01:16Z"},{"alias_kind":"pith_short_8","alias_value":"TEQBKSUX","created_at":"2026-07-05T11:01:16Z"}],"graph_snapshots":[{"event_id":"sha256:c924fee326d2bc94651d80edab9e88d4b0301fa9b92f1f07f26ff0cbef7de02e","target":"graph","created_at":"2026-07-05T11:01:16Z","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/2505.06805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the success that the field of bilevel optimization has seen in recent years, similar methodologies have started being applied to solving more difficult applications that arise in trilevel optimization. At the helm of these applications are new machine learning formulations that have been proposed in the trilevel context and, as a result, efficient and theoretically sound stochastic methods are required. In this work, we propose the first-ever stochastic gradient descent method for solving unconstrained trilevel optimization problems and provide a convergence theory that covers all forms o","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":"2025-05-11T01:05:29Z","title":"A stochastic gradient method for trilevel optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06805","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:b7cba27da672c00b3174d62b87d208f9bc3ed3b0fd51b4560b9d1efd2538a555","target":"record","created_at":"2026-07-05T11:01:16Z","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":"c0819b1c5fa1d63a363a048e0ad54810f32d1ed3f96cb1dd86d2ebf662c11916","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-05-11T01:05:29Z","title_canon_sha256":"f4e25ec25a54fe7a6bbaaf4f660c302a14d84ef8c5a6d429573c567e632093b3"},"schema_version":"1.0","source":{"id":"2505.06805","kind":"arxiv","version":1}},"canonical_sha256":"9920154a9764285506db27cc34f7422c778c50a8d065f11f83e864e0e311f21a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9920154a9764285506db27cc34f7422c778c50a8d065f11f83e864e0e311f21a","first_computed_at":"2026-07-05T11:01:16.035251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:16.035251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MB8K1CKi3SUPkqvy80qrpGRUN+vUqgehqvqBhi4gr/QK+fIENWrX1crI7HhfG9W5H9D0C4ljZ/jv3nCXZZmqBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:16.035717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.06805","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7cba27da672c00b3174d62b87d208f9bc3ed3b0fd51b4560b9d1efd2538a555","sha256:c924fee326d2bc94651d80edab9e88d4b0301fa9b92f1f07f26ff0cbef7de02e"],"state_sha256":"a598fd45f9a9dc08351e9ddc378e3f1e16687bf077498cc4fae4cf46085b9526"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rsyTd3qpzIt8y0Oa0Wvdqw8pb/BrAtw8wBhNlR4TVoG+StHPhNE33OhF7XkcA9/JITWbh08sVGmUJarOqHouDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:12:20.215357Z","bundle_sha256":"2ee60a9d486a1a02d2a23ad854f0b914f02ce9a10c5329ee64f50db8c8f5c3ef"}}