{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZRKQM7MN7GS7S2VVIPQ7VRD6YG","short_pith_number":"pith:ZRKQM7MN","schema_version":"1.0","canonical_sha256":"cc55067d8df9a5f96ab543e1fac47ec1b43fe83c7074b63e205d7ea7005425b5","source":{"kind":"arxiv","id":"2105.15183","version":5},"attestation_state":"computed","paper":{"title":"Efficient and Modular Implicit Differentiation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabian Pedregosa, Felipe Llinares-L\\'opez, Jean-Philippe Vert, Marco Cuturi, Mathieu Blondel, Quentin Berthet, Roy Frostig, Stephan Hoyer","submitted_at":"2021-05-31T17:45:58Z","abstract_excerpt":"Automatic differentiation (autodiff) has revolutionized machine learning. It allows to express complex computations by composing elementary ones in creative ways and removes the burden of computing their derivatives by hand. More recently, differentiation of optimization problem solutions has attracted widespread attention with applications such as optimization layers, and in bi-level problems such as hyper-parameter optimization and meta-learning. However, so far, implicit differentiation remained difficult to use for practitioners, as it often required case-by-case tedious mathematical deriv"},"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":"2105.15183","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-31T17:45:58Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"d92ff0f98a2224ee29b26434791d703f0610965bcefb2d5831a434795394d89b","abstract_canon_sha256":"464375ff1d5601aef905d4034d895fa5d23ed7eecea2457d560ee5d526938a82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:43.642445Z","signature_b64":"2FSr6xV9Zvh+wr8QqouR54S/pLu7xQjhYHr0cTrbIKzL/wljHPRZ1o3GrmPcWxku72TwZ/q2NG76lvS5O5zuAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc55067d8df9a5f96ab543e1fac47ec1b43fe83c7074b63e205d7ea7005425b5","last_reissued_at":"2026-07-05T05:05:43.641937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:43.641937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient and Modular Implicit Differentiation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabian Pedregosa, Felipe Llinares-L\\'opez, Jean-Philippe Vert, Marco Cuturi, Mathieu Blondel, Quentin Berthet, Roy Frostig, Stephan Hoyer","submitted_at":"2021-05-31T17:45:58Z","abstract_excerpt":"Automatic differentiation (autodiff) has revolutionized machine learning. It allows to express complex computations by composing elementary ones in creative ways and removes the burden of computing their derivatives by hand. More recently, differentiation of optimization problem solutions has attracted widespread attention with applications such as optimization layers, and in bi-level problems such as hyper-parameter optimization and meta-learning. However, so far, implicit differentiation remained difficult to use for practitioners, as it often required case-by-case tedious mathematical deriv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.15183","kind":"arxiv","version":5},"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/2105.15183/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":"2105.15183","created_at":"2026-07-05T05:05:43.641994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.15183v5","created_at":"2026-07-05T05:05:43.641994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.15183","created_at":"2026-07-05T05:05:43.641994+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRKQM7MN7GS7","created_at":"2026-07-05T05:05:43.641994+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRKQM7MN7GS7S2VV","created_at":"2026-07-05T05:05:43.641994+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRKQM7MN","created_at":"2026-07-05T05:05:43.641994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26341","citing_title":"Scaling Nonlinear Optimization: Many Problems One GPU","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11983","citing_title":"Calibration of an Analog-to-Digital Conversion Nonlinearity in JWST/NIRISS","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06868","citing_title":"The mass of TOI-1883 b: A low density super-Neptune in the ridge regime transiting an early-M dwarf","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06641","citing_title":"Accelerated Fourier SAT (AFSAT): Fully Realising a GPU-based Symmetric Pseudo-Boolean SAT Solver","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06656","citing_title":"A Study of Parallel Continuous Local Search","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31620","citing_title":"Designing bistable nanostructures for target behavior","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03542","citing_title":"Random test functions, $H^{-1}$ norm equivalence, and stochastic variational physics-informed neural networks","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28757","citing_title":"Learning Approximate Solutions to Multiparametric Generalized Nash Equilibrium Problems","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02294","citing_title":"Regularized Large Neighborhood Search","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23155","citing_title":"Neural Parameter Calibration for Finite-State Mean Field Games","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2501.04776","citing_title":"IQPopt: Fast optimization of instantaneous quantum polynomial circuits in JAX","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08666","citing_title":"Stochastic gravitational-wave background search using data from five pulsar timing arrays","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03542","citing_title":"Random test functions, $H^{-1}$ norm equivalence, and stochastic variational physics-informed neural networks","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRKQM7MN7GS7S2VVIPQ7VRD6YG","json":"https://pith.science/pith/ZRKQM7MN7GS7S2VVIPQ7VRD6YG.json","graph_json":"https://pith.science/api/pith-number/ZRKQM7MN7GS7S2VVIPQ7VRD6YG/graph.json","events_json":"https://pith.science/api/pith-number/ZRKQM7MN7GS7S2VVIPQ7VRD6YG/events.json","paper":"https://pith.science/paper/ZRKQM7MN"},"agent_actions":{"view_html":"https://pith.science/pith/ZRKQM7MN7GS7S2VVIPQ7VRD6YG","download_json":"https://pith.science/pith/ZRKQM7MN7GS7S2VVIPQ7VRD6YG.json","view_paper":"https://pith.science/paper/ZRKQM7MN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.15183&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRKQM7MN7GS7S2VVIPQ7VRD6YG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRKQM7MN7GS7S2VVIPQ7VRD6YG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRKQM7MN7GS7S2VVIPQ7VRD6YG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRKQM7MN7GS7S2VVIPQ7VRD6YG/action/storage_attestation","attest_author":"https://pith.science/pith/ZRKQM7MN7GS7S2VVIPQ7VRD6YG/action/author_attestation","sign_citation":"https://pith.science/pith/ZRKQM7MN7GS7S2VVIPQ7VRD6YG/action/citation_signature","submit_replication":"https://pith.science/pith/ZRKQM7MN7GS7S2VVIPQ7VRD6YG/action/replication_record"}},"created_at":"2026-07-05T05:05:43.641994+00:00","updated_at":"2026-07-05T05:05:43.641994+00:00"}