{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YQ53KB2WZUZKT2LQ2RJ7V2KXO2","short_pith_number":"pith:YQ53KB2W","schema_version":"1.0","canonical_sha256":"c43bb50756cd32a9e970d453fae95776b2b03eaacae37f337e89defc9bb0bd49","source":{"kind":"arxiv","id":"2010.01732","version":1},"attestation_state":"computed","paper":{"title":"Lipschitz Bounded Equilibrium Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ian R. Manchester, Max Revay, Ruigang Wang","submitted_at":"2020-10-05T01:00:40Z","abstract_excerpt":"This paper introduces new parameterizations of equilibrium neural networks, i.e. networks defined by implicit equations. This model class includes standard multilayer and residual networks as special cases. The new parameterization admits a Lipschitz bound during training via unconstrained optimization: no projections or barrier functions are required. Lipschitz bounds are a common proxy for robustness and appear in many generalization bounds. Furthermore, compared to previous works we show well-posedness (existence of solutions) under less restrictive conditions on the network weights and mor"},"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":"2010.01732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-05T01:00:40Z","cross_cats_sorted":["cs.CV","cs.SY","eess.SY","math.OC","stat.ML"],"title_canon_sha256":"d5264f2b50c3b8e84070ca5e5a581c0aa131b656206f651306bae2909caee461","abstract_canon_sha256":"cae418a9c8fd5f100092b5800f933174d9be36cb577363633aa934e967f87e89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:08.845202Z","signature_b64":"Fb2Aftp+eJwIYA7LYHFIyca8GALnzdZPMdg1T/ScoFVS0qROUAmXMjPdTywbkJHe40vdb1crZtk0fBbp4IMKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c43bb50756cd32a9e970d453fae95776b2b03eaacae37f337e89defc9bb0bd49","last_reissued_at":"2026-07-05T01:40:08.844830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:08.844830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lipschitz Bounded Equilibrium Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ian R. Manchester, Max Revay, Ruigang Wang","submitted_at":"2020-10-05T01:00:40Z","abstract_excerpt":"This paper introduces new parameterizations of equilibrium neural networks, i.e. networks defined by implicit equations. This model class includes standard multilayer and residual networks as special cases. The new parameterization admits a Lipschitz bound during training via unconstrained optimization: no projections or barrier functions are required. Lipschitz bounds are a common proxy for robustness and appear in many generalization bounds. Furthermore, compared to previous works we show well-posedness (existence of solutions) under less restrictive conditions on the network weights and mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01732","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/2010.01732/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":"2010.01732","created_at":"2026-07-05T01:40:08.844889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01732v1","created_at":"2026-07-05T01:40:08.844889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01732","created_at":"2026-07-05T01:40:08.844889+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQ53KB2WZUZK","created_at":"2026-07-05T01:40:08.844889+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQ53KB2WZUZKT2LQ","created_at":"2026-07-05T01:40:08.844889+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQ53KB2W","created_at":"2026-07-05T01:40:08.844889+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.22258","citing_title":"LipKernel: Lipschitz-Bounded Convolutional Neural Networks via Dissipative Layers","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12203","citing_title":"Efficient Learning of Affine and Rational Dependency LPV Models With Linear Fractional Representation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07277","citing_title":"Bifurcation Models: Learning Set-Valued Solution Maps with Weight-Tied Dynamics","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15238","citing_title":"A Nonlinear Separation Principle via Contraction Theory: Applications to Neural Networks, Control, and Learning","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQ53KB2WZUZKT2LQ2RJ7V2KXO2","json":"https://pith.science/pith/YQ53KB2WZUZKT2LQ2RJ7V2KXO2.json","graph_json":"https://pith.science/api/pith-number/YQ53KB2WZUZKT2LQ2RJ7V2KXO2/graph.json","events_json":"https://pith.science/api/pith-number/YQ53KB2WZUZKT2LQ2RJ7V2KXO2/events.json","paper":"https://pith.science/paper/YQ53KB2W"},"agent_actions":{"view_html":"https://pith.science/pith/YQ53KB2WZUZKT2LQ2RJ7V2KXO2","download_json":"https://pith.science/pith/YQ53KB2WZUZKT2LQ2RJ7V2KXO2.json","view_paper":"https://pith.science/paper/YQ53KB2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01732&json=true","fetch_graph":"https://pith.science/api/pith-number/YQ53KB2WZUZKT2LQ2RJ7V2KXO2/graph.json","fetch_events":"https://pith.science/api/pith-number/YQ53KB2WZUZKT2LQ2RJ7V2KXO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQ53KB2WZUZKT2LQ2RJ7V2KXO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQ53KB2WZUZKT2LQ2RJ7V2KXO2/action/storage_attestation","attest_author":"https://pith.science/pith/YQ53KB2WZUZKT2LQ2RJ7V2KXO2/action/author_attestation","sign_citation":"https://pith.science/pith/YQ53KB2WZUZKT2LQ2RJ7V2KXO2/action/citation_signature","submit_replication":"https://pith.science/pith/YQ53KB2WZUZKT2LQ2RJ7V2KXO2/action/replication_record"}},"created_at":"2026-07-05T01:40:08.844889+00:00","updated_at":"2026-07-05T01:40:08.844889+00:00"}