{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R3LCBVNSYMFCTBEN6KP75LZBBQ","short_pith_number":"pith:R3LCBVNS","schema_version":"1.0","canonical_sha256":"8ed620d5b2c30a29848df29ffeaf210c05b6cd66ad854decfd2bfb7d24e4a944","source":{"kind":"arxiv","id":"2305.16261","version":2},"attestation_state":"computed","paper":{"title":"Trans-Dimensional Generative Modeling via Jump Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew Campbell, Arnaud Doucet, Christian Weilbach, Tom Rainforth, Valentin De Bortoli, William Harvey","submitted_at":"2023-05-25T17:15:00Z","abstract_excerpt":"We propose a new class of generative models that naturally handle data of varying dimensionality by jointly modeling the state and dimension of each datapoint. The generative process is formulated as a jump diffusion process that makes jumps between different dimensional spaces. We first define a dimension destroying forward noising process, before deriving the dimension creating time-reversed generative process along with a novel evidence lower bound training objective for learning to approximate it. Simulating our learned approximation to the time-reversed generative process then provides an"},"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":"2305.16261","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-05-25T17:15:00Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"1e57677e5e74de4d0617005745226422cff88deab59f136bfc3eaa69501f0f97","abstract_canon_sha256":"28058fc24882cfe3240f617bc0733e39731b4da7e3280d6b5caf842672332093"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:27.860079Z","signature_b64":"1Ped+HiZ9qc8iy4uyL/XYQ/HrVLE567F9fnHKQLKjQgN6G8CwhCF3kEwfXl8rw9MZrtZxnEiGPK3SyfDmpqDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ed620d5b2c30a29848df29ffeaf210c05b6cd66ad854decfd2bfb7d24e4a944","last_reissued_at":"2026-07-05T07:06:27.859227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:27.859227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trans-Dimensional Generative Modeling via Jump Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andrew Campbell, Arnaud Doucet, Christian Weilbach, Tom Rainforth, Valentin De Bortoli, William Harvey","submitted_at":"2023-05-25T17:15:00Z","abstract_excerpt":"We propose a new class of generative models that naturally handle data of varying dimensionality by jointly modeling the state and dimension of each datapoint. The generative process is formulated as a jump diffusion process that makes jumps between different dimensional spaces. We first define a dimension destroying forward noising process, before deriving the dimension creating time-reversed generative process along with a novel evidence lower bound training objective for learning to approximate it. Simulating our learned approximation to the time-reversed generative process then provides an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16261","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/2305.16261/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":"2305.16261","created_at":"2026-07-05T07:06:27.859309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16261v2","created_at":"2026-07-05T07:06:27.859309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16261","created_at":"2026-07-05T07:06:27.859309+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3LCBVNSYMFC","created_at":"2026-07-05T07:06:27.859309+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3LCBVNSYMFCTBEN","created_at":"2026-07-05T07:06:27.859309+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3LCBVNS","created_at":"2026-07-05T07:06:27.859309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07239","citing_title":"Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2511.03015","citing_title":"Discrete Bayesian Sample Inference for Graph Generation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2511.09465","citing_title":"Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletions","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R3LCBVNSYMFCTBEN6KP75LZBBQ","json":"https://pith.science/pith/R3LCBVNSYMFCTBEN6KP75LZBBQ.json","graph_json":"https://pith.science/api/pith-number/R3LCBVNSYMFCTBEN6KP75LZBBQ/graph.json","events_json":"https://pith.science/api/pith-number/R3LCBVNSYMFCTBEN6KP75LZBBQ/events.json","paper":"https://pith.science/paper/R3LCBVNS"},"agent_actions":{"view_html":"https://pith.science/pith/R3LCBVNSYMFCTBEN6KP75LZBBQ","download_json":"https://pith.science/pith/R3LCBVNSYMFCTBEN6KP75LZBBQ.json","view_paper":"https://pith.science/paper/R3LCBVNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16261&json=true","fetch_graph":"https://pith.science/api/pith-number/R3LCBVNSYMFCTBEN6KP75LZBBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/R3LCBVNSYMFCTBEN6KP75LZBBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3LCBVNSYMFCTBEN6KP75LZBBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3LCBVNSYMFCTBEN6KP75LZBBQ/action/storage_attestation","attest_author":"https://pith.science/pith/R3LCBVNSYMFCTBEN6KP75LZBBQ/action/author_attestation","sign_citation":"https://pith.science/pith/R3LCBVNSYMFCTBEN6KP75LZBBQ/action/citation_signature","submit_replication":"https://pith.science/pith/R3LCBVNSYMFCTBEN6KP75LZBBQ/action/replication_record"}},"created_at":"2026-07-05T07:06:27.859309+00:00","updated_at":"2026-07-05T07:06:27.859309+00:00"}