{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FEIWNNZUZSZ2ZBA6Q7AZ56EJKM","short_pith_number":"pith:FEIWNNZU","schema_version":"1.0","canonical_sha256":"291166b734ccb3ac841e87c19ef8895304880ed1d2d7c2dc68cd9aaf405f345e","source":{"kind":"arxiv","id":"2209.09389","version":1},"attestation_state":"computed","paper":{"title":"State-driven Implicit Modeling for Sparsity and Robustness in Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Alicia Y. Tsai, Alper Atamt\\\"urk, Juliette Decugis, Laurent El Ghaoui","submitted_at":"2022-09-19T23:58:48Z","abstract_excerpt":"Implicit models are a general class of learning models that forgo the hierarchical layer structure typical in neural networks and instead define the internal states based on an ``equilibrium'' equation, offering competitive performance and reduced memory consumption. However, training such models usually relies on expensive implicit differentiation for backward propagation. In this work, we present a new approach to training implicit models, called State-driven Implicit Modeling (SIM), where we constrain the internal states and outputs to match that of a baseline model, circumventing costly ba"},"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":"2209.09389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-19T23:58:48Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"6eb61b1347f8b386a5d52b6f15b38b5a13829f1918ae3264b83b077b428e664f","abstract_canon_sha256":"490c6215d7936166e425f19cb1ce67733a61ca71d980d1b231cefd2c1bda98e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:59.270988Z","signature_b64":"0pWlWrWUEY1T3TPBFRPgNglfS3Su5MhOsvLpnxXPjgZBzsDjtpnHymicltuuTOcMM0NplOTPSSelQZ3AHpRZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"291166b734ccb3ac841e87c19ef8895304880ed1d2d7c2dc68cd9aaf405f345e","last_reissued_at":"2026-07-05T04:58:59.270511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:59.270511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"State-driven Implicit Modeling for Sparsity and Robustness in Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Alicia Y. Tsai, Alper Atamt\\\"urk, Juliette Decugis, Laurent El Ghaoui","submitted_at":"2022-09-19T23:58:48Z","abstract_excerpt":"Implicit models are a general class of learning models that forgo the hierarchical layer structure typical in neural networks and instead define the internal states based on an ``equilibrium'' equation, offering competitive performance and reduced memory consumption. However, training such models usually relies on expensive implicit differentiation for backward propagation. In this work, we present a new approach to training implicit models, called State-driven Implicit Modeling (SIM), where we constrain the internal states and outputs to match that of a baseline model, circumventing costly ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.09389","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/2209.09389/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":"2209.09389","created_at":"2026-07-05T04:58:59.270570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.09389v1","created_at":"2026-07-05T04:58:59.270570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.09389","created_at":"2026-07-05T04:58:59.270570+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEIWNNZUZSZ2","created_at":"2026-07-05T04:58:59.270570+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEIWNNZUZSZ2ZBA6","created_at":"2026-07-05T04:58:59.270570+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEIWNNZU","created_at":"2026-07-05T04:58:59.270570+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/FEIWNNZUZSZ2ZBA6Q7AZ56EJKM","json":"https://pith.science/pith/FEIWNNZUZSZ2ZBA6Q7AZ56EJKM.json","graph_json":"https://pith.science/api/pith-number/FEIWNNZUZSZ2ZBA6Q7AZ56EJKM/graph.json","events_json":"https://pith.science/api/pith-number/FEIWNNZUZSZ2ZBA6Q7AZ56EJKM/events.json","paper":"https://pith.science/paper/FEIWNNZU"},"agent_actions":{"view_html":"https://pith.science/pith/FEIWNNZUZSZ2ZBA6Q7AZ56EJKM","download_json":"https://pith.science/pith/FEIWNNZUZSZ2ZBA6Q7AZ56EJKM.json","view_paper":"https://pith.science/paper/FEIWNNZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.09389&json=true","fetch_graph":"https://pith.science/api/pith-number/FEIWNNZUZSZ2ZBA6Q7AZ56EJKM/graph.json","fetch_events":"https://pith.science/api/pith-number/FEIWNNZUZSZ2ZBA6Q7AZ56EJKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEIWNNZUZSZ2ZBA6Q7AZ56EJKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEIWNNZUZSZ2ZBA6Q7AZ56EJKM/action/storage_attestation","attest_author":"https://pith.science/pith/FEIWNNZUZSZ2ZBA6Q7AZ56EJKM/action/author_attestation","sign_citation":"https://pith.science/pith/FEIWNNZUZSZ2ZBA6Q7AZ56EJKM/action/citation_signature","submit_replication":"https://pith.science/pith/FEIWNNZUZSZ2ZBA6Q7AZ56EJKM/action/replication_record"}},"created_at":"2026-07-05T04:58:59.270570+00:00","updated_at":"2026-07-05T04:58:59.270570+00:00"}