{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XFK6CQN6A42YEKMJUJBPPYPRXQ","short_pith_number":"pith:XFK6CQN6","schema_version":"1.0","canonical_sha256":"b955e141be0735822989a242f7e1f1bc02e6779394507916db44340c24e35ed1","source":{"kind":"arxiv","id":"2206.03992","version":2},"attestation_state":"computed","paper":{"title":"Neural Diffusion Processes","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alan Saul, Fergus Simpson, Vincent Dutordoir, Zoubin Ghahramani","submitted_at":"2022-06-08T16:13:04Z","abstract_excerpt":"Neural network approaches for meta-learning distributions over functions have desirable properties such as increased flexibility and a reduced complexity of inference. Building on the successes of denoising diffusion models for generative modelling, we propose Neural Diffusion Processes (NDPs), a novel approach that learns to sample from a rich distribution over functions through its finite marginals. By introducing a custom attention block we are able to incorporate properties of stochastic processes, such as exchangeability, directly into the NDP's architecture. We empirically show that NDPs"},"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":"2206.03992","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2022-06-08T16:13:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"46af5189c1b236ba0b8ad34b4c1a09db735c0a67f6ef247c3cc5a076f1dcf888","abstract_canon_sha256":"c6b72ec80d5f5236968f481753077a0fcf05c24a4ba6fb28f9bfaf02da65429e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:16.755589Z","signature_b64":"Q/QPe/GWHFLZxoBhxWJ87Er+2ZnI/AWK3YYvOYzqJwJhu5IGPVdIx1sV3x8qdkL7svOsUpkkCgvLVCCBgNjxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b955e141be0735822989a242f7e1f1bc02e6779394507916db44340c24e35ed1","last_reissued_at":"2026-07-05T06:18:16.755087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:16.755087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Diffusion Processes","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alan Saul, Fergus Simpson, Vincent Dutordoir, Zoubin Ghahramani","submitted_at":"2022-06-08T16:13:04Z","abstract_excerpt":"Neural network approaches for meta-learning distributions over functions have desirable properties such as increased flexibility and a reduced complexity of inference. Building on the successes of denoising diffusion models for generative modelling, we propose Neural Diffusion Processes (NDPs), a novel approach that learns to sample from a rich distribution over functions through its finite marginals. By introducing a custom attention block we are able to incorporate properties of stochastic processes, such as exchangeability, directly into the NDP's architecture. We empirically show that NDPs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03992","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/2206.03992/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":"2206.03992","created_at":"2026-07-05T06:18:16.755149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.03992v2","created_at":"2026-07-05T06:18:16.755149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03992","created_at":"2026-07-05T06:18:16.755149+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFK6CQN6A42Y","created_at":"2026-07-05T06:18:16.755149+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFK6CQN6A42YEKMJ","created_at":"2026-07-05T06:18:16.755149+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFK6CQN6","created_at":"2026-07-05T06:18:16.755149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31282","citing_title":"Revisiting the Volume Hypothesis","ref_index":131,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFK6CQN6A42YEKMJUJBPPYPRXQ","json":"https://pith.science/pith/XFK6CQN6A42YEKMJUJBPPYPRXQ.json","graph_json":"https://pith.science/api/pith-number/XFK6CQN6A42YEKMJUJBPPYPRXQ/graph.json","events_json":"https://pith.science/api/pith-number/XFK6CQN6A42YEKMJUJBPPYPRXQ/events.json","paper":"https://pith.science/paper/XFK6CQN6"},"agent_actions":{"view_html":"https://pith.science/pith/XFK6CQN6A42YEKMJUJBPPYPRXQ","download_json":"https://pith.science/pith/XFK6CQN6A42YEKMJUJBPPYPRXQ.json","view_paper":"https://pith.science/paper/XFK6CQN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.03992&json=true","fetch_graph":"https://pith.science/api/pith-number/XFK6CQN6A42YEKMJUJBPPYPRXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XFK6CQN6A42YEKMJUJBPPYPRXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFK6CQN6A42YEKMJUJBPPYPRXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFK6CQN6A42YEKMJUJBPPYPRXQ/action/storage_attestation","attest_author":"https://pith.science/pith/XFK6CQN6A42YEKMJUJBPPYPRXQ/action/author_attestation","sign_citation":"https://pith.science/pith/XFK6CQN6A42YEKMJUJBPPYPRXQ/action/citation_signature","submit_replication":"https://pith.science/pith/XFK6CQN6A42YEKMJUJBPPYPRXQ/action/replication_record"}},"created_at":"2026-07-05T06:18:16.755149+00:00","updated_at":"2026-07-05T06:18:16.755149+00:00"}