{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3GSZX4R3TSBSVA3QFJUKEAF4U7","short_pith_number":"pith:3GSZX4R3","schema_version":"1.0","canonical_sha256":"d9a59bf23b9c832a83702a68a200bca7f8fb00becb77ff0814426aca0aa449bd","source":{"kind":"arxiv","id":"1909.01377","version":2},"attestation_state":"computed","paper":{"title":"Deep Equilibrium Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"J. Zico Kolter, Shaojie Bai, Vladlen Koltun","submitted_at":"2019-09-03T18:02:50Z","abstract_excerpt":"We present a new approach to modeling sequential data: the deep equilibrium model (DEQ). Motivated by an observation that the hidden layers of many existing deep sequence models converge towards some fixed point, we propose the DEQ approach that directly finds these equilibrium points via root-finding. Such a method is equivalent to running an infinite depth (weight-tied) feedforward network, but has the notable advantage that we can analytically backpropagate through the equilibrium point using implicit differentiation. Using this approach, training and prediction in these networks require on"},"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":"1909.01377","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-03T18:02:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bd1b2590c2d8b5b3109ad8039aae3b1e2a49c76957fa2e6e6c28ff1085154467","abstract_canon_sha256":"3ddbf9ce64bed0f66395a28b6496da62ac73c5ddbd3e93a8251e68455b71e4b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:24.085060Z","signature_b64":"mEQhHz5/9H97yRtTry6l7c6URJwIHUBoSOFzytNrSa5WX/fCzXjQMM6hpnx3sYj8NPfcQG6lYqKVb00K1y/jAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9a59bf23b9c832a83702a68a200bca7f8fb00becb77ff0814426aca0aa449bd","last_reissued_at":"2026-07-05T00:15:24.084656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:24.084656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Equilibrium Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"J. Zico Kolter, Shaojie Bai, Vladlen Koltun","submitted_at":"2019-09-03T18:02:50Z","abstract_excerpt":"We present a new approach to modeling sequential data: the deep equilibrium model (DEQ). Motivated by an observation that the hidden layers of many existing deep sequence models converge towards some fixed point, we propose the DEQ approach that directly finds these equilibrium points via root-finding. Such a method is equivalent to running an infinite depth (weight-tied) feedforward network, but has the notable advantage that we can analytically backpropagate through the equilibrium point using implicit differentiation. Using this approach, training and prediction in these networks require on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.01377","kind":"arxiv","version":2},"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/1909.01377/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":"1909.01377","created_at":"2026-07-05T00:15:24.084715+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.01377v2","created_at":"2026-07-05T00:15:24.084715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.01377","created_at":"2026-07-05T00:15:24.084715+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GSZX4R3TSBS","created_at":"2026-07-05T00:15:24.084715+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GSZX4R3TSBSVA3Q","created_at":"2026-07-05T00:15:24.084715+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GSZX4R3","created_at":"2026-07-05T00:15:24.084715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31215","citing_title":"Fixed-Point Masked Generative Modeling","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23155","citing_title":"Neural Parameter Calibration for Finite-State Mean Field Games","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15985","citing_title":"Thermodynamic Networks: Harnessing Non-Equilibrium Steady States for Computation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2509.04154","citing_title":"Robust Filter Attention: Self-Attention as Precision-Weighted State Estimation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05171","citing_title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09226","citing_title":"Quantum Injection Pathways for Implicit Graph Neural Networks","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00206","citing_title":"State Stream Transformer (SST) V2: Parallel Training of Nonlinear Recurrence for Latent Space Reasoning","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12946","citing_title":"Parcae: Scaling Laws For Stable Looped Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09168","citing_title":"ELT: Elastic Looped Transformers for Visual Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15259","citing_title":"Stability and Generalization in Looped Transformers","ref_index":2,"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":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GSZX4R3TSBSVA3QFJUKEAF4U7","json":"https://pith.science/pith/3GSZX4R3TSBSVA3QFJUKEAF4U7.json","graph_json":"https://pith.science/api/pith-number/3GSZX4R3TSBSVA3QFJUKEAF4U7/graph.json","events_json":"https://pith.science/api/pith-number/3GSZX4R3TSBSVA3QFJUKEAF4U7/events.json","paper":"https://pith.science/paper/3GSZX4R3"},"agent_actions":{"view_html":"https://pith.science/pith/3GSZX4R3TSBSVA3QFJUKEAF4U7","download_json":"https://pith.science/pith/3GSZX4R3TSBSVA3QFJUKEAF4U7.json","view_paper":"https://pith.science/paper/3GSZX4R3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.01377&json=true","fetch_graph":"https://pith.science/api/pith-number/3GSZX4R3TSBSVA3QFJUKEAF4U7/graph.json","fetch_events":"https://pith.science/api/pith-number/3GSZX4R3TSBSVA3QFJUKEAF4U7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GSZX4R3TSBSVA3QFJUKEAF4U7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GSZX4R3TSBSVA3QFJUKEAF4U7/action/storage_attestation","attest_author":"https://pith.science/pith/3GSZX4R3TSBSVA3QFJUKEAF4U7/action/author_attestation","sign_citation":"https://pith.science/pith/3GSZX4R3TSBSVA3QFJUKEAF4U7/action/citation_signature","submit_replication":"https://pith.science/pith/3GSZX4R3TSBSVA3QFJUKEAF4U7/action/replication_record"}},"created_at":"2026-07-05T00:15:24.084715+00:00","updated_at":"2026-07-05T00:15:24.084715+00:00"}