{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:335N6Z5GQYMMBDR6Y43GMZRF42","short_pith_number":"pith:335N6Z5G","schema_version":"1.0","canonical_sha256":"defadf67a68618c08e3ec736666625e69757124ca9fc62e12faaf004c51a0a78","source":{"kind":"arxiv","id":"2303.17015","version":1},"attestation_state":"computed","paper":{"title":"HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Angela Dai, Fangchang Ma, Matthias Nie{\\ss}ner, Qi Shan, Ziya Erko\\c{c}","submitted_at":"2023-03-29T20:44:42Z","abstract_excerpt":"Implicit neural fields, typically encoded by a multilayer perceptron (MLP) that maps from coordinates (e.g., xyz) to signals (e.g., signed distances), have shown remarkable promise as a high-fidelity and compact representation. However, the lack of a regular and explicit grid structure also makes it challenging to apply generative modeling directly on implicit neural fields in order to synthesize new data. To this end, we propose HyperDiffusion, a novel approach for unconditional generative modeling of implicit neural fields. HyperDiffusion operates directly on MLP weights and generates new ne"},"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":"2303.17015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-29T20:44:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0f93b2d51c5d85794374b937fd4bd20a57190a9eb7cea89108f25876c431e5f4","abstract_canon_sha256":"da1842cc0fdee09e9a847e2c285626bb03f564b022fbc1dcb22ce72151e22a7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:18.301962Z","signature_b64":"WMbwifSR+D7tc6mu64Yk66YeuS2NmoRtpgIikUqrVHQaa4phI+GT3W5oahx0nx/lAFI+ugdfM4aG0cSy5elzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"defadf67a68618c08e3ec736666625e69757124ca9fc62e12faaf004c51a0a78","last_reissued_at":"2026-07-05T05:56:18.301482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:18.301482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Angela Dai, Fangchang Ma, Matthias Nie{\\ss}ner, Qi Shan, Ziya Erko\\c{c}","submitted_at":"2023-03-29T20:44:42Z","abstract_excerpt":"Implicit neural fields, typically encoded by a multilayer perceptron (MLP) that maps from coordinates (e.g., xyz) to signals (e.g., signed distances), have shown remarkable promise as a high-fidelity and compact representation. However, the lack of a regular and explicit grid structure also makes it challenging to apply generative modeling directly on implicit neural fields in order to synthesize new data. To this end, we propose HyperDiffusion, a novel approach for unconditional generative modeling of implicit neural fields. HyperDiffusion operates directly on MLP weights and generates new ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17015","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/2303.17015/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":"2303.17015","created_at":"2026-07-05T05:56:18.301542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17015v1","created_at":"2026-07-05T05:56:18.301542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17015","created_at":"2026-07-05T05:56:18.301542+00:00"},{"alias_kind":"pith_short_12","alias_value":"335N6Z5GQYMM","created_at":"2026-07-05T05:56:18.301542+00:00"},{"alias_kind":"pith_short_16","alias_value":"335N6Z5GQYMMBDR6","created_at":"2026-07-05T05:56:18.301542+00:00"},{"alias_kind":"pith_short_8","alias_value":"335N6Z5G","created_at":"2026-07-05T05:56:18.301542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00522","citing_title":"Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10830","citing_title":"Predicting 3D structure by latent posterior sampling","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10830","citing_title":"Predicting 3D structure by latent posterior sampling","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2309.03453","citing_title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10830","citing_title":"Predicting 3D structure by latent posterior sampling","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/335N6Z5GQYMMBDR6Y43GMZRF42","json":"https://pith.science/pith/335N6Z5GQYMMBDR6Y43GMZRF42.json","graph_json":"https://pith.science/api/pith-number/335N6Z5GQYMMBDR6Y43GMZRF42/graph.json","events_json":"https://pith.science/api/pith-number/335N6Z5GQYMMBDR6Y43GMZRF42/events.json","paper":"https://pith.science/paper/335N6Z5G"},"agent_actions":{"view_html":"https://pith.science/pith/335N6Z5GQYMMBDR6Y43GMZRF42","download_json":"https://pith.science/pith/335N6Z5GQYMMBDR6Y43GMZRF42.json","view_paper":"https://pith.science/paper/335N6Z5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17015&json=true","fetch_graph":"https://pith.science/api/pith-number/335N6Z5GQYMMBDR6Y43GMZRF42/graph.json","fetch_events":"https://pith.science/api/pith-number/335N6Z5GQYMMBDR6Y43GMZRF42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/335N6Z5GQYMMBDR6Y43GMZRF42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/335N6Z5GQYMMBDR6Y43GMZRF42/action/storage_attestation","attest_author":"https://pith.science/pith/335N6Z5GQYMMBDR6Y43GMZRF42/action/author_attestation","sign_citation":"https://pith.science/pith/335N6Z5GQYMMBDR6Y43GMZRF42/action/citation_signature","submit_replication":"https://pith.science/pith/335N6Z5GQYMMBDR6Y43GMZRF42/action/replication_record"}},"created_at":"2026-07-05T05:56:18.301542+00:00","updated_at":"2026-07-05T05:56:18.301542+00:00"}