{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2QYMMUNNBFELVOOEN4ZEIT72UW","short_pith_number":"pith:2QYMMUNN","schema_version":"1.0","canonical_sha256":"d430c651ad0948bab9c46f32444ffaa5a97726150fb34214e7b798e678c733e0","source":{"kind":"arxiv","id":"2402.18153","version":2},"attestation_state":"computed","paper":{"title":"Diffusion-Based Neural Network Weights Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bedionita Soro, Bruno Andreis, Frank Hutter, Hayeon Lee, Song Chong, Sung Ju Hwang, Wonyong Jeong","submitted_at":"2024-02-28T08:34:23Z","abstract_excerpt":"Transfer learning has gained significant attention in recent deep learning research due to its ability to accelerate convergence and enhance performance on new tasks. However, its success is often contingent on the similarity between source and target data, and training on numerous datasets can be costly, leading to blind selection of pretrained models with limited insight into their effectiveness. To address these challenges, we introduce D2NWG, a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning, conditioned 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":"2402.18153","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-28T08:34:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f7689cee0d4f4314056c48d8b6afc9725a8d68e6dcc86a70e9a58aa86ff0650f","abstract_canon_sha256":"b870ac76272e524b456efe6eac186ae7a7dd04898e4fec0f6e0d4625f6134a28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:41.081862Z","signature_b64":"nryzBtI2Cf0tHPgQEq7T3eiywDEaTEipiGoqT8AG+XN5b4I5GmP/dTpy89ojwYoQ5oVj78kBnzhZZUhRHQYABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d430c651ad0948bab9c46f32444ffaa5a97726150fb34214e7b798e678c733e0","last_reissued_at":"2026-07-05T09:25:41.081269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:41.081269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-Based Neural Network Weights Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bedionita Soro, Bruno Andreis, Frank Hutter, Hayeon Lee, Song Chong, Sung Ju Hwang, Wonyong Jeong","submitted_at":"2024-02-28T08:34:23Z","abstract_excerpt":"Transfer learning has gained significant attention in recent deep learning research due to its ability to accelerate convergence and enhance performance on new tasks. However, its success is often contingent on the similarity between source and target data, and training on numerous datasets can be costly, leading to blind selection of pretrained models with limited insight into their effectiveness. To address these challenges, we introduce D2NWG, a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning, conditioned on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18153","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/2402.18153/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":"2402.18153","created_at":"2026-07-05T09:25:41.081338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18153v2","created_at":"2026-07-05T09:25:41.081338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18153","created_at":"2026-07-05T09:25:41.081338+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QYMMUNNBFEL","created_at":"2026-07-05T09:25:41.081338+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QYMMUNNBFELVOOE","created_at":"2026-07-05T09:25:41.081338+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QYMMUNN","created_at":"2026-07-05T09:25:41.081338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07217","citing_title":"Robotic Policy Adaptation via Weight-Space Meta-Learning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05478","citing_title":"Can We Predict The Human Preference For Text-to-Image Content Prior To Generation And Is It Even Useful To Do So?","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2505.13919","citing_title":"Generative Adaptation of Dynamics to Environmental Shifts via Weight-space Diffusion","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19929","citing_title":"RAM: Recover Any 3D Human Motion in-the-Wild","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12096","citing_title":"LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2QYMMUNNBFELVOOEN4ZEIT72UW","json":"https://pith.science/pith/2QYMMUNNBFELVOOEN4ZEIT72UW.json","graph_json":"https://pith.science/api/pith-number/2QYMMUNNBFELVOOEN4ZEIT72UW/graph.json","events_json":"https://pith.science/api/pith-number/2QYMMUNNBFELVOOEN4ZEIT72UW/events.json","paper":"https://pith.science/paper/2QYMMUNN"},"agent_actions":{"view_html":"https://pith.science/pith/2QYMMUNNBFELVOOEN4ZEIT72UW","download_json":"https://pith.science/pith/2QYMMUNNBFELVOOEN4ZEIT72UW.json","view_paper":"https://pith.science/paper/2QYMMUNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18153&json=true","fetch_graph":"https://pith.science/api/pith-number/2QYMMUNNBFELVOOEN4ZEIT72UW/graph.json","fetch_events":"https://pith.science/api/pith-number/2QYMMUNNBFELVOOEN4ZEIT72UW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QYMMUNNBFELVOOEN4ZEIT72UW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QYMMUNNBFELVOOEN4ZEIT72UW/action/storage_attestation","attest_author":"https://pith.science/pith/2QYMMUNNBFELVOOEN4ZEIT72UW/action/author_attestation","sign_citation":"https://pith.science/pith/2QYMMUNNBFELVOOEN4ZEIT72UW/action/citation_signature","submit_replication":"https://pith.science/pith/2QYMMUNNBFELVOOEN4ZEIT72UW/action/replication_record"}},"created_at":"2026-07-05T09:25:41.081338+00:00","updated_at":"2026-07-05T09:25:41.081338+00:00"}