{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WT6SF4OEH7TVMEEMW3FGIOCGXJ","short_pith_number":"pith:WT6SF4OE","schema_version":"1.0","canonical_sha256":"b4fd22f1c43fe756108cb6ca643846ba7c706fbf3531b56a09acc368a41e96cd","source":{"kind":"arxiv","id":"2107.10254","version":2},"attestation_state":"computed","paper":{"title":"Neural Fixed-Point Acceleration for Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Brandon Amos, Shobha Venkataraman","submitted_at":"2021-07-21T17:59:34Z","abstract_excerpt":"Fixed-point iterations are at the heart of numerical computing and are often a computational bottleneck in real-time applications that typically need a fast solution of moderate accuracy. We present neural fixed-point acceleration which combines ideas from meta-learning and classical acceleration methods to automatically learn to accelerate fixed-point problems that are drawn from a distribution. We apply our framework to SCS, the state-of-the-art solver for convex cone programming, and design models and loss functions to overcome the challenges of learning over unrolled optimization and accel"},"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":"2107.10254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-21T17:59:34Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"61780d4611a336f61718d0744b9c026d0a33251634bdc7bdf07c55036b12b306","abstract_canon_sha256":"21799f9f792802aacd4c7795112b17474c25ef44fda91ec21514b22257b729b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:10.626620Z","signature_b64":"LfVwSZOu1qqibtzIg9dwtzYD4x235RoCJFNtSaryLVCTWQU+SOHwtyucPW+I8wbI4v710ySG3b+Z+S+kWo42CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4fd22f1c43fe756108cb6ca643846ba7c706fbf3531b56a09acc368a41e96cd","last_reissued_at":"2026-07-05T03:00:10.626180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:10.626180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Fixed-Point Acceleration for Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Brandon Amos, Shobha Venkataraman","submitted_at":"2021-07-21T17:59:34Z","abstract_excerpt":"Fixed-point iterations are at the heart of numerical computing and are often a computational bottleneck in real-time applications that typically need a fast solution of moderate accuracy. We present neural fixed-point acceleration which combines ideas from meta-learning and classical acceleration methods to automatically learn to accelerate fixed-point problems that are drawn from a distribution. We apply our framework to SCS, the state-of-the-art solver for convex cone programming, and design models and loss functions to overcome the challenges of learning over unrolled optimization and accel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.10254","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/2107.10254/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":"2107.10254","created_at":"2026-07-05T03:00:10.626237+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.10254v2","created_at":"2026-07-05T03:00:10.626237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.10254","created_at":"2026-07-05T03:00:10.626237+00:00"},{"alias_kind":"pith_short_12","alias_value":"WT6SF4OEH7TV","created_at":"2026-07-05T03:00:10.626237+00:00"},{"alias_kind":"pith_short_16","alias_value":"WT6SF4OEH7TVMEEM","created_at":"2026-07-05T03:00:10.626237+00:00"},{"alias_kind":"pith_short_8","alias_value":"WT6SF4OE","created_at":"2026-07-05T03:00:10.626237+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16349","citing_title":"Neural Network Acceleration of Iterative Methods for Nonlinear Schr\\\"odinger Eigenvalue Problems","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WT6SF4OEH7TVMEEMW3FGIOCGXJ","json":"https://pith.science/pith/WT6SF4OEH7TVMEEMW3FGIOCGXJ.json","graph_json":"https://pith.science/api/pith-number/WT6SF4OEH7TVMEEMW3FGIOCGXJ/graph.json","events_json":"https://pith.science/api/pith-number/WT6SF4OEH7TVMEEMW3FGIOCGXJ/events.json","paper":"https://pith.science/paper/WT6SF4OE"},"agent_actions":{"view_html":"https://pith.science/pith/WT6SF4OEH7TVMEEMW3FGIOCGXJ","download_json":"https://pith.science/pith/WT6SF4OEH7TVMEEMW3FGIOCGXJ.json","view_paper":"https://pith.science/paper/WT6SF4OE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.10254&json=true","fetch_graph":"https://pith.science/api/pith-number/WT6SF4OEH7TVMEEMW3FGIOCGXJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WT6SF4OEH7TVMEEMW3FGIOCGXJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WT6SF4OEH7TVMEEMW3FGIOCGXJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WT6SF4OEH7TVMEEMW3FGIOCGXJ/action/storage_attestation","attest_author":"https://pith.science/pith/WT6SF4OEH7TVMEEMW3FGIOCGXJ/action/author_attestation","sign_citation":"https://pith.science/pith/WT6SF4OEH7TVMEEMW3FGIOCGXJ/action/citation_signature","submit_replication":"https://pith.science/pith/WT6SF4OEH7TVMEEMW3FGIOCGXJ/action/replication_record"}},"created_at":"2026-07-05T03:00:10.626237+00:00","updated_at":"2026-07-05T03:00:10.626237+00:00"}