{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ESKLYIEDNKGRSV35VMAWFJLN3A","short_pith_number":"pith:ESKLYIED","schema_version":"1.0","canonical_sha256":"2494bc20836a8d19577dab0162a56dd8083669bb32ef35b5bce37ab2daafc939","source":{"kind":"arxiv","id":"2312.08598","version":2},"attestation_state":"computed","paper":{"title":"MotherNet: Fast Training and Inference via Hyper-Network Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas M\\\"uller, Carlo Curino, Raghu Ramakrishnan","submitted_at":"2023-12-14T01:48:58Z","abstract_excerpt":"Foundation models are transforming machine learning across many modalities, with in-context learning replacing classical model training. Recent work on tabular data hints at a similar opportunity to build foundation models for classification for numerical data. However, existing meta-learning approaches can not compete with tree-based methods in terms of inference time. In this paper, we propose MotherNet, a hypernetwork architecture trained on synthetic classification tasks that, once prompted with a never-seen-before training set generates the weights of a trained ``child'' neural-network by"},"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":"2312.08598","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-14T01:48:58Z","cross_cats_sorted":[],"title_canon_sha256":"da9901da0b16382626b2c359c033b77203cdb54856e000b5792104eaf89128ba","abstract_canon_sha256":"3e86c3127feb15db00f2b53f92b391baff89fbd46d2b9516d338a36d0b2abc14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:35.847929Z","signature_b64":"Z3tdnF70QG+bzmsemkU73wd05pAduoYgojMzwVz1ZuFuqa5eFn4SaYhR+GJvLN6Z5Z5PjTbB3NLHfsejVrxdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2494bc20836a8d19577dab0162a56dd8083669bb32ef35b5bce37ab2daafc939","last_reissued_at":"2026-07-05T11:00:35.847446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:35.847446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MotherNet: Fast Training and Inference via Hyper-Network Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas M\\\"uller, Carlo Curino, Raghu Ramakrishnan","submitted_at":"2023-12-14T01:48:58Z","abstract_excerpt":"Foundation models are transforming machine learning across many modalities, with in-context learning replacing classical model training. Recent work on tabular data hints at a similar opportunity to build foundation models for classification for numerical data. However, existing meta-learning approaches can not compete with tree-based methods in terms of inference time. In this paper, we propose MotherNet, a hypernetwork architecture trained on synthetic classification tasks that, once prompted with a never-seen-before training set generates the weights of a trained ``child'' neural-network by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08598","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/2312.08598/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":"2312.08598","created_at":"2026-07-05T11:00:35.847503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08598v2","created_at":"2026-07-05T11:00:35.847503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08598","created_at":"2026-07-05T11:00:35.847503+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESKLYIEDNKGR","created_at":"2026-07-05T11:00:35.847503+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESKLYIEDNKGRSV35","created_at":"2026-07-05T11:00:35.847503+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESKLYIED","created_at":"2026-07-05T11:00:35.847503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23720","citing_title":"Quasi-Equivariant Metanetworks","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ESKLYIEDNKGRSV35VMAWFJLN3A","json":"https://pith.science/pith/ESKLYIEDNKGRSV35VMAWFJLN3A.json","graph_json":"https://pith.science/api/pith-number/ESKLYIEDNKGRSV35VMAWFJLN3A/graph.json","events_json":"https://pith.science/api/pith-number/ESKLYIEDNKGRSV35VMAWFJLN3A/events.json","paper":"https://pith.science/paper/ESKLYIED"},"agent_actions":{"view_html":"https://pith.science/pith/ESKLYIEDNKGRSV35VMAWFJLN3A","download_json":"https://pith.science/pith/ESKLYIEDNKGRSV35VMAWFJLN3A.json","view_paper":"https://pith.science/paper/ESKLYIED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08598&json=true","fetch_graph":"https://pith.science/api/pith-number/ESKLYIEDNKGRSV35VMAWFJLN3A/graph.json","fetch_events":"https://pith.science/api/pith-number/ESKLYIEDNKGRSV35VMAWFJLN3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESKLYIEDNKGRSV35VMAWFJLN3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESKLYIEDNKGRSV35VMAWFJLN3A/action/storage_attestation","attest_author":"https://pith.science/pith/ESKLYIEDNKGRSV35VMAWFJLN3A/action/author_attestation","sign_citation":"https://pith.science/pith/ESKLYIEDNKGRSV35VMAWFJLN3A/action/citation_signature","submit_replication":"https://pith.science/pith/ESKLYIEDNKGRSV35VMAWFJLN3A/action/replication_record"}},"created_at":"2026-07-05T11:00:35.847503+00:00","updated_at":"2026-07-05T11:00:35.847503+00:00"}