{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JPKNYDJNYSKA3OTZNTEELZQR74","short_pith_number":"pith:JPKNYDJN","schema_version":"1.0","canonical_sha256":"4bd4dc0d2dc4940dba796cc845e611ff34337e0be8bde4ffbe100580d154385c","source":{"kind":"arxiv","id":"2502.02463","version":3},"attestation_state":"computed","paper":{"title":"Distribution Transformers: Fast Approximate Bayesian Inference With On-The-Fly Prior Adaptation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"George Whittle, Jacob Rawling, Juliusz Ziomek, Maike A. Osborne","submitted_at":"2025-02-04T16:33:12Z","abstract_excerpt":"While Bayesian inference provides a principled framework for reasoning under uncertainty, its widespread adoption is limited by the intractability of exact posterior computation, necessitating the use of approximate inference. However, existing methods are often computationally expensive, or demand costly retraining when priors change, limiting their utility, particularly in sequential inference problems such as real-time sensor fusion. To address these challenges, we introduce the Distribution Transformer -- a novel architecture that can learn arbitrary distribution-to-distribution mappings. "},"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":"2502.02463","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-04T16:33:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3d625304a78c63e377233a24da148ad25396ec5c3a5361da6f4790b69e879fb4","abstract_canon_sha256":"8a45c19e755d1fc6aa7af41c8e32820d8016b9d2cb561e40ea6237a20762b26a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:26.915589Z","signature_b64":"9x4m6e+1ucpVZpIBPfq88RHw8rF0+M6NlHxyj5sUOn6AD1h37tzZkADUw+mC08r8mAvzMD2gRK+wvAA5C/b4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bd4dc0d2dc4940dba796cc845e611ff34337e0be8bde4ffbe100580d154385c","last_reissued_at":"2026-05-20T00:05:26.914780Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:26.914780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distribution Transformers: Fast Approximate Bayesian Inference With On-The-Fly Prior Adaptation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"George Whittle, Jacob Rawling, Juliusz Ziomek, Maike A. Osborne","submitted_at":"2025-02-04T16:33:12Z","abstract_excerpt":"While Bayesian inference provides a principled framework for reasoning under uncertainty, its widespread adoption is limited by the intractability of exact posterior computation, necessitating the use of approximate inference. However, existing methods are often computationally expensive, or demand costly retraining when priors change, limiting their utility, particularly in sequential inference problems such as real-time sensor fusion. To address these challenges, we introduce the Distribution Transformer -- a novel architecture that can learn arbitrary distribution-to-distribution mappings. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02463","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/2502.02463/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":"2502.02463","created_at":"2026-05-20T00:05:26.914913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02463v3","created_at":"2026-05-20T00:05:26.914913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02463","created_at":"2026-05-20T00:05:26.914913+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPKNYDJNYSKA","created_at":"2026-05-20T00:05:26.914913+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPKNYDJNYSKA3OTZ","created_at":"2026-05-20T00:05:26.914913+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPKNYDJN","created_at":"2026-05-20T00:05:26.914913+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2510.09477","citing_title":"Efficient Autoregressive Inference for Transformer Probabilistic Models","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2512.23748","citing_title":"A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarios","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JPKNYDJNYSKA3OTZNTEELZQR74","json":"https://pith.science/pith/JPKNYDJNYSKA3OTZNTEELZQR74.json","graph_json":"https://pith.science/api/pith-number/JPKNYDJNYSKA3OTZNTEELZQR74/graph.json","events_json":"https://pith.science/api/pith-number/JPKNYDJNYSKA3OTZNTEELZQR74/events.json","paper":"https://pith.science/paper/JPKNYDJN"},"agent_actions":{"view_html":"https://pith.science/pith/JPKNYDJNYSKA3OTZNTEELZQR74","download_json":"https://pith.science/pith/JPKNYDJNYSKA3OTZNTEELZQR74.json","view_paper":"https://pith.science/paper/JPKNYDJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02463&json=true","fetch_graph":"https://pith.science/api/pith-number/JPKNYDJNYSKA3OTZNTEELZQR74/graph.json","fetch_events":"https://pith.science/api/pith-number/JPKNYDJNYSKA3OTZNTEELZQR74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPKNYDJNYSKA3OTZNTEELZQR74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPKNYDJNYSKA3OTZNTEELZQR74/action/storage_attestation","attest_author":"https://pith.science/pith/JPKNYDJNYSKA3OTZNTEELZQR74/action/author_attestation","sign_citation":"https://pith.science/pith/JPKNYDJNYSKA3OTZNTEELZQR74/action/citation_signature","submit_replication":"https://pith.science/pith/JPKNYDJNYSKA3OTZNTEELZQR74/action/replication_record"}},"created_at":"2026-05-20T00:05:26.914913+00:00","updated_at":"2026-05-20T00:05:26.914913+00:00"}