{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A42OAK6FNULQCO36ZMUMHLFMQZ","short_pith_number":"pith:A42OAK6F","schema_version":"1.0","canonical_sha256":"0734e02bc56d17013b7ecb28c3acac865b5335cb0da758dc1fd857b96703fcc3","source":{"kind":"arxiv","id":"2402.13144","version":3},"attestation_state":"computed","paper":{"title":"Neural Network Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Boya Zeng, Dongwen Tang, Kai Wang, Trevor Darrell, Yang You, Yida Yin, Yukun Zhou, Zelin Zang, Zhaopan Xu, Zhuang Liu","submitted_at":"2024-02-20T16:59:03Z","abstract_excerpt":"Diffusion models have achieved remarkable success in image and video generation. In this work, we demonstrate that diffusion models can also \\textit{generate high-performing neural network parameters}. Our approach is simple, utilizing an autoencoder and a diffusion model. The autoencoder extracts latent representations of a subset of the trained neural network parameters. Next, a diffusion model is trained to synthesize these latent representations from random noise. This model then generates new representations, which are passed through the autoencoder's decoder to produce new subsets of hig"},"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":"2402.13144","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-20T16:59:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1652aa2216bc2091ccca0dc8562041eda238acea04e9519903a0574c6669d280","abstract_canon_sha256":"e3bb1091df33d17b4fd83bbb646bcf312780f44deb51c882fc184b824a6bdd57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:32.730844Z","signature_b64":"7eFsAHYAn1ZKlPfrMSJKEfrDiBDQRNTHI819HoDFluXdrBDjYQ351SPnZ+i97TiF/REl5sbEZuBKLkS78uRyDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0734e02bc56d17013b7ecb28c3acac865b5335cb0da758dc1fd857b96703fcc3","last_reissued_at":"2026-07-05T09:55:32.730346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:32.730346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Network Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Boya Zeng, Dongwen Tang, Kai Wang, Trevor Darrell, Yang You, Yida Yin, Yukun Zhou, Zelin Zang, Zhaopan Xu, Zhuang Liu","submitted_at":"2024-02-20T16:59:03Z","abstract_excerpt":"Diffusion models have achieved remarkable success in image and video generation. In this work, we demonstrate that diffusion models can also \\textit{generate high-performing neural network parameters}. Our approach is simple, utilizing an autoencoder and a diffusion model. The autoencoder extracts latent representations of a subset of the trained neural network parameters. Next, a diffusion model is trained to synthesize these latent representations from random noise. This model then generates new representations, which are passed through the autoencoder's decoder to produce new subsets of hig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13144","kind":"arxiv","version":3},"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/2402.13144/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":"2402.13144","created_at":"2026-07-05T09:55:32.730405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13144v3","created_at":"2026-07-05T09:55:32.730405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13144","created_at":"2026-07-05T09:55:32.730405+00:00"},{"alias_kind":"pith_short_12","alias_value":"A42OAK6FNULQ","created_at":"2026-07-05T09:55:32.730405+00:00"},{"alias_kind":"pith_short_16","alias_value":"A42OAK6FNULQCO36","created_at":"2026-07-05T09:55:32.730405+00:00"},{"alias_kind":"pith_short_8","alias_value":"A42OAK6F","created_at":"2026-07-05T09:55:32.730405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07743","citing_title":"Architecture Generalization with MetaNCA","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26772","citing_title":"Escaping Iterative Parameter-Space Noise: Differentially Private Learning with a Hypernetwork","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23607","citing_title":"Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2410.02543","citing_title":"Diffusion Models are Evolutionary Algorithms","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2505.13919","citing_title":"Generative Adaptation of Dynamics to Environmental Shifts via Weight-space Diffusion","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18991","citing_title":"Fast Kernel-Space Diffusion for Remote Sensing Pansharpening","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13839","citing_title":"Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A42OAK6FNULQCO36ZMUMHLFMQZ","json":"https://pith.science/pith/A42OAK6FNULQCO36ZMUMHLFMQZ.json","graph_json":"https://pith.science/api/pith-number/A42OAK6FNULQCO36ZMUMHLFMQZ/graph.json","events_json":"https://pith.science/api/pith-number/A42OAK6FNULQCO36ZMUMHLFMQZ/events.json","paper":"https://pith.science/paper/A42OAK6F"},"agent_actions":{"view_html":"https://pith.science/pith/A42OAK6FNULQCO36ZMUMHLFMQZ","download_json":"https://pith.science/pith/A42OAK6FNULQCO36ZMUMHLFMQZ.json","view_paper":"https://pith.science/paper/A42OAK6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13144&json=true","fetch_graph":"https://pith.science/api/pith-number/A42OAK6FNULQCO36ZMUMHLFMQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/A42OAK6FNULQCO36ZMUMHLFMQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A42OAK6FNULQCO36ZMUMHLFMQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A42OAK6FNULQCO36ZMUMHLFMQZ/action/storage_attestation","attest_author":"https://pith.science/pith/A42OAK6FNULQCO36ZMUMHLFMQZ/action/author_attestation","sign_citation":"https://pith.science/pith/A42OAK6FNULQCO36ZMUMHLFMQZ/action/citation_signature","submit_replication":"https://pith.science/pith/A42OAK6FNULQCO36ZMUMHLFMQZ/action/replication_record"}},"created_at":"2026-07-05T09:55:32.730405+00:00","updated_at":"2026-07-05T09:55:32.730405+00:00"}