{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GCNJVQZCK7PNUHIJV6P324PUPN","short_pith_number":"pith:GCNJVQZC","schema_version":"1.0","canonical_sha256":"309a9ac32257deda1d09af9fbd71f47b7ddda49f6c79fb92bd428ff9ba9c2ece","source":{"kind":"arxiv","id":"2606.22433","version":1},"attestation_state":"computed","paper":{"title":"Escaping the Variance Trap: Jacobian-Free Dynamics for Root-Finding Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Davide Carbone, Xi Xuan, Zhiyu Li","submitted_at":"2026-06-21T10:53:32Z","abstract_excerpt":"Many central machine learning tasks, from entropy tuning in reinforcement learning to equilibrating generative adversarial networks, are fundamentally stochastic root-finding problems rather than loss minimization. Yet, they are frequently forced into a minimization framework via squared residuals, introducing a critical flaw we identify as the Variance Trap. Standard bilevel minimization algorithms require estimating hypergradients involving implicit Jacobians; in stochastic settings, these terms act as noise amplifiers, destabilizing convergence. We formalize Root-Finding Bilevel Optimizatio"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.22433","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T10:53:32Z","cross_cats_sorted":[],"title_canon_sha256":"cca93da6a3ec248ecdefe3e4b72e9468f4334c63c5b05487452a7e0210605ca4","abstract_canon_sha256":"94674f5a7a3ff9251e07b5bd928e4e754712c4c9b9a5a494c56c059cde0301ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:38.336694Z","signature_b64":"vm5/Kzd+njkAJcWeHfF6tXdBm0/2DnKr+/kFSx2oHB4eg715WLDMNPUO2pc/dpdh0+ol5MDGaqqmr2RjZKCNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"309a9ac32257deda1d09af9fbd71f47b7ddda49f6c79fb92bd428ff9ba9c2ece","last_reissued_at":"2026-06-23T02:13:38.336299Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:38.336299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Escaping the Variance Trap: Jacobian-Free Dynamics for Root-Finding Bilevel Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Davide Carbone, Xi Xuan, Zhiyu Li","submitted_at":"2026-06-21T10:53:32Z","abstract_excerpt":"Many central machine learning tasks, from entropy tuning in reinforcement learning to equilibrating generative adversarial networks, are fundamentally stochastic root-finding problems rather than loss minimization. Yet, they are frequently forced into a minimization framework via squared residuals, introducing a critical flaw we identify as the Variance Trap. Standard bilevel minimization algorithms require estimating hypergradients involving implicit Jacobians; in stochastic settings, these terms act as noise amplifiers, destabilizing convergence. We formalize Root-Finding Bilevel Optimizatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22433","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/2606.22433/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.22433","created_at":"2026-06-23T02:13:38.336377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22433v1","created_at":"2026-06-23T02:13:38.336377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22433","created_at":"2026-06-23T02:13:38.336377+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCNJVQZCK7PN","created_at":"2026-06-23T02:13:38.336377+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCNJVQZCK7PNUHIJ","created_at":"2026-06-23T02:13:38.336377+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCNJVQZC","created_at":"2026-06-23T02:13:38.336377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCNJVQZCK7PNUHIJV6P324PUPN","json":"https://pith.science/pith/GCNJVQZCK7PNUHIJV6P324PUPN.json","graph_json":"https://pith.science/api/pith-number/GCNJVQZCK7PNUHIJV6P324PUPN/graph.json","events_json":"https://pith.science/api/pith-number/GCNJVQZCK7PNUHIJV6P324PUPN/events.json","paper":"https://pith.science/paper/GCNJVQZC"},"agent_actions":{"view_html":"https://pith.science/pith/GCNJVQZCK7PNUHIJV6P324PUPN","download_json":"https://pith.science/pith/GCNJVQZCK7PNUHIJV6P324PUPN.json","view_paper":"https://pith.science/paper/GCNJVQZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22433&json=true","fetch_graph":"https://pith.science/api/pith-number/GCNJVQZCK7PNUHIJV6P324PUPN/graph.json","fetch_events":"https://pith.science/api/pith-number/GCNJVQZCK7PNUHIJV6P324PUPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCNJVQZCK7PNUHIJV6P324PUPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCNJVQZCK7PNUHIJV6P324PUPN/action/storage_attestation","attest_author":"https://pith.science/pith/GCNJVQZCK7PNUHIJV6P324PUPN/action/author_attestation","sign_citation":"https://pith.science/pith/GCNJVQZCK7PNUHIJV6P324PUPN/action/citation_signature","submit_replication":"https://pith.science/pith/GCNJVQZCK7PNUHIJV6P324PUPN/action/replication_record"}},"created_at":"2026-06-23T02:13:38.336377+00:00","updated_at":"2026-06-23T02:13:38.336377+00:00"}