{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZYU7DYZYN2KNGBVM4S2K3EG4O2","short_pith_number":"pith:ZYU7DYZY","schema_version":"1.0","canonical_sha256":"ce29f1e3386e94d306ace4b4ad90dc76b1c1539ef70ce3c300df04783000da67","source":{"kind":"arxiv","id":"1908.06315","version":4},"attestation_state":"computed","paper":{"title":"Implicit Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alicia Y. Tsai, Armin Askari, Bertrand Travacca, Fangda Gu, Laurent El Ghaoui","submitted_at":"2019-08-17T15:36:37Z","abstract_excerpt":"Implicit deep learning prediction rules generalize the recursive rules of feedforward neural networks. Such rules are based on the solution of a fixed-point equation involving a single vector of hidden features, which is thus only implicitly defined. The implicit framework greatly simplifies the notation of deep learning, and opens up many new possibilities, in terms of novel architectures and algorithms, robustness analysis and design, interpretability, sparsity, and network architecture optimization."},"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":"1908.06315","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-17T15:36:37Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"17ebf0df2f28cf8d9e569f7142bdb02a6e2d011d44198f1db75425f4246bcd36","abstract_canon_sha256":"b595230c0d3d8bc3cb10cdbfe95b542ddafca4a7e7c19dae3424738a57daeae8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:22.353847Z","signature_b64":"HwX/RWJo2MHDWYWjCUc/ZPcgkWr+1kynHDdB2J6hwcY6aR71tQpD3GL06pfkhub1YJjC4E08MKhkPHx0eChCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce29f1e3386e94d306ace4b4ad90dc76b1c1539ef70ce3c300df04783000da67","last_reissued_at":"2026-07-05T01:25:22.353434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:22.353434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicit Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alicia Y. Tsai, Armin Askari, Bertrand Travacca, Fangda Gu, Laurent El Ghaoui","submitted_at":"2019-08-17T15:36:37Z","abstract_excerpt":"Implicit deep learning prediction rules generalize the recursive rules of feedforward neural networks. Such rules are based on the solution of a fixed-point equation involving a single vector of hidden features, which is thus only implicitly defined. The implicit framework greatly simplifies the notation of deep learning, and opens up many new possibilities, in terms of novel architectures and algorithms, robustness analysis and design, interpretability, sparsity, and network architecture optimization."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06315","kind":"arxiv","version":4},"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/1908.06315/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":"1908.06315","created_at":"2026-07-05T01:25:22.353490+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.06315v4","created_at":"2026-07-05T01:25:22.353490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06315","created_at":"2026-07-05T01:25:22.353490+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZYU7DYZYN2KN","created_at":"2026-07-05T01:25:22.353490+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZYU7DYZYN2KNGBVM","created_at":"2026-07-05T01:25:22.353490+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZYU7DYZY","created_at":"2026-07-05T01:25:22.353490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09226","citing_title":"Quantum Injection Pathways for Implicit Graph Neural Networks","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZYU7DYZYN2KNGBVM4S2K3EG4O2","json":"https://pith.science/pith/ZYU7DYZYN2KNGBVM4S2K3EG4O2.json","graph_json":"https://pith.science/api/pith-number/ZYU7DYZYN2KNGBVM4S2K3EG4O2/graph.json","events_json":"https://pith.science/api/pith-number/ZYU7DYZYN2KNGBVM4S2K3EG4O2/events.json","paper":"https://pith.science/paper/ZYU7DYZY"},"agent_actions":{"view_html":"https://pith.science/pith/ZYU7DYZYN2KNGBVM4S2K3EG4O2","download_json":"https://pith.science/pith/ZYU7DYZYN2KNGBVM4S2K3EG4O2.json","view_paper":"https://pith.science/paper/ZYU7DYZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.06315&json=true","fetch_graph":"https://pith.science/api/pith-number/ZYU7DYZYN2KNGBVM4S2K3EG4O2/graph.json","fetch_events":"https://pith.science/api/pith-number/ZYU7DYZYN2KNGBVM4S2K3EG4O2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZYU7DYZYN2KNGBVM4S2K3EG4O2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZYU7DYZYN2KNGBVM4S2K3EG4O2/action/storage_attestation","attest_author":"https://pith.science/pith/ZYU7DYZYN2KNGBVM4S2K3EG4O2/action/author_attestation","sign_citation":"https://pith.science/pith/ZYU7DYZYN2KNGBVM4S2K3EG4O2/action/citation_signature","submit_replication":"https://pith.science/pith/ZYU7DYZYN2KNGBVM4S2K3EG4O2/action/replication_record"}},"created_at":"2026-07-05T01:25:22.353490+00:00","updated_at":"2026-07-05T01:25:22.353490+00:00"}