{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YIZ2CD562H5PN54APM7LMTMOBE","short_pith_number":"pith:YIZ2CD56","schema_version":"1.0","canonical_sha256":"c233a10fbed1faf6f7807b3eb64d8e0927ad6c38059dda7baf8811cdcf5b32a3","source":{"kind":"arxiv","id":"2605.19705","version":1},"attestation_state":"computed","paper":{"title":"i-DEQ: A stable inertial deep equilibrium model for image restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Antonin Clerc, Baudouin Denis De Seneville, Marien Renaud, Nicolas Papadakis","submitted_at":"2026-05-19T11:43:18Z","abstract_excerpt":"Deep Equilibrium Models (DEQs) are an established framework for image restoration that learn a problem-adapted regularization by solving a fixed-point (i.e. equilibrium) problem. While flexible and expressive, DEQs are often hindered by high computational cost and training instability. We propose an inertial DEQ (i-DEQ) that learns an explicit nonconvex regularization within the DEQ formulation. By using momentum within the fixed-point iterations, i-DEQ has convergence guarantees and accelerated rates. Moreover, we observe that i-DEQ is significantly more stable during the training and robust "},"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":"2605.19705","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2026-05-19T11:43:18Z","cross_cats_sorted":[],"title_canon_sha256":"5a6e12391a2685af53d03acf21a2d8618cff1f71c8871f6c8533f8d62cf1e761","abstract_canon_sha256":"99a0d77778647d749a7c5b344109df60db0a0c816f78b2fa9c9a221490ba373a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:58.544379Z","signature_b64":"OHX5zkCZvJBrd5QWSzVVPbDnTg25cOZydu0JTHixJmfjexytan/A+wWf03wCdJoHEdxndbt1uNsuEWmx3TVhBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c233a10fbed1faf6f7807b3eb64d8e0927ad6c38059dda7baf8811cdcf5b32a3","last_reissued_at":"2026-05-20T01:05:58.543513Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:58.543513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"i-DEQ: A stable inertial deep equilibrium model for image restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Antonin Clerc, Baudouin Denis De Seneville, Marien Renaud, Nicolas Papadakis","submitted_at":"2026-05-19T11:43:18Z","abstract_excerpt":"Deep Equilibrium Models (DEQs) are an established framework for image restoration that learn a problem-adapted regularization by solving a fixed-point (i.e. equilibrium) problem. While flexible and expressive, DEQs are often hindered by high computational cost and training instability. We propose an inertial DEQ (i-DEQ) that learns an explicit nonconvex regularization within the DEQ formulation. By using momentum within the fixed-point iterations, i-DEQ has convergence guarantees and accelerated rates. Moreover, we observe that i-DEQ is significantly more stable during the training and robust "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19705","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/2605.19705/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":"2605.19705","created_at":"2026-05-20T01:05:58.543672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19705v1","created_at":"2026-05-20T01:05:58.543672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19705","created_at":"2026-05-20T01:05:58.543672+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIZ2CD562H5P","created_at":"2026-05-20T01:05:58.543672+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIZ2CD562H5PN54A","created_at":"2026-05-20T01:05:58.543672+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIZ2CD56","created_at":"2026-05-20T01:05:58.543672+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/YIZ2CD562H5PN54APM7LMTMOBE","json":"https://pith.science/pith/YIZ2CD562H5PN54APM7LMTMOBE.json","graph_json":"https://pith.science/api/pith-number/YIZ2CD562H5PN54APM7LMTMOBE/graph.json","events_json":"https://pith.science/api/pith-number/YIZ2CD562H5PN54APM7LMTMOBE/events.json","paper":"https://pith.science/paper/YIZ2CD56"},"agent_actions":{"view_html":"https://pith.science/pith/YIZ2CD562H5PN54APM7LMTMOBE","download_json":"https://pith.science/pith/YIZ2CD562H5PN54APM7LMTMOBE.json","view_paper":"https://pith.science/paper/YIZ2CD56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19705&json=true","fetch_graph":"https://pith.science/api/pith-number/YIZ2CD562H5PN54APM7LMTMOBE/graph.json","fetch_events":"https://pith.science/api/pith-number/YIZ2CD562H5PN54APM7LMTMOBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIZ2CD562H5PN54APM7LMTMOBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIZ2CD562H5PN54APM7LMTMOBE/action/storage_attestation","attest_author":"https://pith.science/pith/YIZ2CD562H5PN54APM7LMTMOBE/action/author_attestation","sign_citation":"https://pith.science/pith/YIZ2CD562H5PN54APM7LMTMOBE/action/citation_signature","submit_replication":"https://pith.science/pith/YIZ2CD562H5PN54APM7LMTMOBE/action/replication_record"}},"created_at":"2026-05-20T01:05:58.543672+00:00","updated_at":"2026-05-20T01:05:58.543672+00:00"}