{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JLDIDQLY7IFFZUVSL7BMNPAKFA","short_pith_number":"pith:JLDIDQLY","schema_version":"1.0","canonical_sha256":"4ac681c178fa0a5cd2b25fc2c6bc0a280ac13285a29aa1af108ca7162850b15d","source":{"kind":"arxiv","id":"2410.11275","version":1},"attestation_state":"computed","paper":{"title":"Shallow diffusion networks provably learn hidden low-dimensional structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Jacot, Ingvar Ziemann, Nicholas M. Boffi, Stephen Tu","submitted_at":"2024-10-15T04:55:56Z","abstract_excerpt":"Diffusion-based generative models provide a powerful framework for learning to sample from a complex target distribution. The remarkable empirical success of these models applied to high-dimensional signals, including images and video, stands in stark contrast to classical results highlighting the curse of dimensionality for distribution recovery. In this work, we take a step towards understanding this gap through a careful analysis of learning diffusion models over the Barron space of single layer neural networks. In particular, we show that these shallow models provably adapt to simple forms"},"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":"2410.11275","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T04:55:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0ba003589571769067c9fa2a80da24882378ca08de4462488eb7d9642ff8fc44","abstract_canon_sha256":"1e120e15ca70cc189a0a9bca1c3babf8464193ae897ca3e680e785953a347bfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:50.968523Z","signature_b64":"ybcbFu9XSVLgMd1aRUkgr3jAWSCmmcfNcY2mOZhUXGGIj5ffVd/d5mwVDITXSlQ5guT5jt7rynlqrt5IulTDBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ac681c178fa0a5cd2b25fc2c6bc0a280ac13285a29aa1af108ca7162850b15d","last_reissued_at":"2026-07-05T09:20:50.968030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:50.968030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shallow diffusion networks provably learn hidden low-dimensional structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arthur Jacot, Ingvar Ziemann, Nicholas M. Boffi, Stephen Tu","submitted_at":"2024-10-15T04:55:56Z","abstract_excerpt":"Diffusion-based generative models provide a powerful framework for learning to sample from a complex target distribution. The remarkable empirical success of these models applied to high-dimensional signals, including images and video, stands in stark contrast to classical results highlighting the curse of dimensionality for distribution recovery. In this work, we take a step towards understanding this gap through a careful analysis of learning diffusion models over the Barron space of single layer neural networks. In particular, we show that these shallow models provably adapt to simple forms"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11275","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/2410.11275/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":"2410.11275","created_at":"2026-07-05T09:20:50.968084+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11275v1","created_at":"2026-07-05T09:20:50.968084+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11275","created_at":"2026-07-05T09:20:50.968084+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLDIDQLY7IFF","created_at":"2026-07-05T09:20:50.968084+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLDIDQLY7IFFZUVS","created_at":"2026-07-05T09:20:50.968084+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLDIDQLY","created_at":"2026-07-05T09:20:50.968084+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08041","citing_title":"An exact information theory of generalization phase transitions in Bayesian diffusion models","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20235","citing_title":"Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JLDIDQLY7IFFZUVSL7BMNPAKFA","json":"https://pith.science/pith/JLDIDQLY7IFFZUVSL7BMNPAKFA.json","graph_json":"https://pith.science/api/pith-number/JLDIDQLY7IFFZUVSL7BMNPAKFA/graph.json","events_json":"https://pith.science/api/pith-number/JLDIDQLY7IFFZUVSL7BMNPAKFA/events.json","paper":"https://pith.science/paper/JLDIDQLY"},"agent_actions":{"view_html":"https://pith.science/pith/JLDIDQLY7IFFZUVSL7BMNPAKFA","download_json":"https://pith.science/pith/JLDIDQLY7IFFZUVSL7BMNPAKFA.json","view_paper":"https://pith.science/paper/JLDIDQLY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11275&json=true","fetch_graph":"https://pith.science/api/pith-number/JLDIDQLY7IFFZUVSL7BMNPAKFA/graph.json","fetch_events":"https://pith.science/api/pith-number/JLDIDQLY7IFFZUVSL7BMNPAKFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLDIDQLY7IFFZUVSL7BMNPAKFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLDIDQLY7IFFZUVSL7BMNPAKFA/action/storage_attestation","attest_author":"https://pith.science/pith/JLDIDQLY7IFFZUVSL7BMNPAKFA/action/author_attestation","sign_citation":"https://pith.science/pith/JLDIDQLY7IFFZUVSL7BMNPAKFA/action/citation_signature","submit_replication":"https://pith.science/pith/JLDIDQLY7IFFZUVSL7BMNPAKFA/action/replication_record"}},"created_at":"2026-07-05T09:20:50.968084+00:00","updated_at":"2026-07-05T09:20:50.968084+00:00"}