{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FM3E5DPBYBURFCOO7QA4723JPX","short_pith_number":"pith:FM3E5DPB","schema_version":"1.0","canonical_sha256":"2b364e8de1c0691289cefc01cfeb697df47154f2edda246aa00464a17fdda3e4","source":{"kind":"arxiv","id":"2110.07004","version":3},"attestation_state":"computed","paper":{"title":"On the Convergence Theory for Hessian-Free Bilevel Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daouda Sow, Kaiyi Ji, Yingbin Liang","submitted_at":"2021-10-13T19:36:50Z","abstract_excerpt":"Bilevel optimization has arisen as a powerful tool in modern machine learning. However, due to the nested structure of bilevel optimization, even gradient-based methods require second-order derivative approximations via Jacobian- or/and Hessian-vector computations, which can be costly and unscalable in practice. Recently, Hessian-free bilevel schemes have been proposed to resolve this issue, where the general idea is to use zeroth- or first-order methods to approximate the full hypergradient of the bilevel problem. However, we empirically observe that such approximation can lead to large varia"},"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":"2110.07004","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-13T19:36:50Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"c9858c1cca7bbd05da90cfc780725b8ba71c0a72ed74c4815392f0f1df1e4f1e","abstract_canon_sha256":"45b0eba7b6f52c7f97c3e032499ae810b1881d7142d3a084f296e5c78817bcc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:10.047713Z","signature_b64":"KdNDL/qQOzTxCJhN94FJISPa2YN0Zagp3GPIcDN9PgWGLgNPpEC2r7AoS/IbqXpyyjwYGwfJa14NCIyvN8JLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b364e8de1c0691289cefc01cfeb697df47154f2edda246aa00464a17fdda3e4","last_reissued_at":"2026-07-05T04:29:10.047250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:10.047250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Convergence Theory for Hessian-Free Bilevel Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daouda Sow, Kaiyi Ji, Yingbin Liang","submitted_at":"2021-10-13T19:36:50Z","abstract_excerpt":"Bilevel optimization has arisen as a powerful tool in modern machine learning. However, due to the nested structure of bilevel optimization, even gradient-based methods require second-order derivative approximations via Jacobian- or/and Hessian-vector computations, which can be costly and unscalable in practice. Recently, Hessian-free bilevel schemes have been proposed to resolve this issue, where the general idea is to use zeroth- or first-order methods to approximate the full hypergradient of the bilevel problem. However, we empirically observe that such approximation can lead to large varia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07004","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/2110.07004/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":"2110.07004","created_at":"2026-07-05T04:29:10.047329+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07004v3","created_at":"2026-07-05T04:29:10.047329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07004","created_at":"2026-07-05T04:29:10.047329+00:00"},{"alias_kind":"pith_short_12","alias_value":"FM3E5DPBYBUR","created_at":"2026-07-05T04:29:10.047329+00:00"},{"alias_kind":"pith_short_16","alias_value":"FM3E5DPBYBURFCOO","created_at":"2026-07-05T04:29:10.047329+00:00"},{"alias_kind":"pith_short_8","alias_value":"FM3E5DPB","created_at":"2026-07-05T04:29:10.047329+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12718","citing_title":"CHAL: Council of Hierarchical Agentic Language","ref_index":144,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FM3E5DPBYBURFCOO7QA4723JPX","json":"https://pith.science/pith/FM3E5DPBYBURFCOO7QA4723JPX.json","graph_json":"https://pith.science/api/pith-number/FM3E5DPBYBURFCOO7QA4723JPX/graph.json","events_json":"https://pith.science/api/pith-number/FM3E5DPBYBURFCOO7QA4723JPX/events.json","paper":"https://pith.science/paper/FM3E5DPB"},"agent_actions":{"view_html":"https://pith.science/pith/FM3E5DPBYBURFCOO7QA4723JPX","download_json":"https://pith.science/pith/FM3E5DPBYBURFCOO7QA4723JPX.json","view_paper":"https://pith.science/paper/FM3E5DPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07004&json=true","fetch_graph":"https://pith.science/api/pith-number/FM3E5DPBYBURFCOO7QA4723JPX/graph.json","fetch_events":"https://pith.science/api/pith-number/FM3E5DPBYBURFCOO7QA4723JPX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FM3E5DPBYBURFCOO7QA4723JPX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FM3E5DPBYBURFCOO7QA4723JPX/action/storage_attestation","attest_author":"https://pith.science/pith/FM3E5DPBYBURFCOO7QA4723JPX/action/author_attestation","sign_citation":"https://pith.science/pith/FM3E5DPBYBURFCOO7QA4723JPX/action/citation_signature","submit_replication":"https://pith.science/pith/FM3E5DPBYBURFCOO7QA4723JPX/action/replication_record"}},"created_at":"2026-07-05T04:29:10.047329+00:00","updated_at":"2026-07-05T04:29:10.047329+00:00"}