{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HN4RIII5L35XOEXLCCYPH3ED2U","short_pith_number":"pith:HN4RIII5","schema_version":"1.0","canonical_sha256":"3b7914211d5efb7712eb10b0f3ec83d528384c41d15f226a484c3bb9c3ac37f2","source":{"kind":"arxiv","id":"2605.23434","version":1},"attestation_state":"computed","paper":{"title":"Onsager-Machlup Posterior Transport for Deep Gaussian Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Delu Zeng, Jian Xu, John Paisley, Qibin Zhao","submitted_at":"2026-05-22T09:45:52Z","abstract_excerpt":"Approximate inference over inducing variables is the central computational bottleneck of Deep Gaussian Processes (DGPs). Existing methods either fit an explicit density $q_\\phi(\\bU)$ by an ELBO (DSVI, IPVI, DDVI, DBVI) or sample by MCMC (SGHMC). We instead frame DGP inference as \\emph{posterior transport}: learn a deterministic sampler that maps a tractable reference measure to posterior-relevant inducing variables, regularised by a path prior derived from the Doob-bridged reference diffusion. Our realisation, \\textbf{OM-Path} (formally FBVI-bridge-Path), uses Song's probability-flow ODE appli"},"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":"2605.23434","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-22T09:45:52Z","cross_cats_sorted":[],"title_canon_sha256":"dbe3c4e6f925ad7647860467ed647fd9718f2ae9772545612736b3564b7e3ef1","abstract_canon_sha256":"13ec062dac45012260245802d9d43bdf53e9f5e1e7f22c72b7af468b710a7483"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:54.139706Z","signature_b64":"Ur6JuycWQJsKG8hS2eLzzTUqDoUQDluiLFDIWm2GahwdfVS4UiPTcH7lkydYANPa+YOQrIve/DDeyO23zQY5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b7914211d5efb7712eb10b0f3ec83d528384c41d15f226a484c3bb9c3ac37f2","last_reissued_at":"2026-05-25T02:01:54.138930Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:54.138930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Onsager-Machlup Posterior Transport for Deep Gaussian Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Delu Zeng, Jian Xu, John Paisley, Qibin Zhao","submitted_at":"2026-05-22T09:45:52Z","abstract_excerpt":"Approximate inference over inducing variables is the central computational bottleneck of Deep Gaussian Processes (DGPs). Existing methods either fit an explicit density $q_\\phi(\\bU)$ by an ELBO (DSVI, IPVI, DDVI, DBVI) or sample by MCMC (SGHMC). We instead frame DGP inference as \\emph{posterior transport}: learn a deterministic sampler that maps a tractable reference measure to posterior-relevant inducing variables, regularised by a path prior derived from the Doob-bridged reference diffusion. Our realisation, \\textbf{OM-Path} (formally FBVI-bridge-Path), uses Song's probability-flow ODE appli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23434","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/2605.23434/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":"2605.23434","created_at":"2026-05-25T02:01:54.139056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23434v1","created_at":"2026-05-25T02:01:54.139056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23434","created_at":"2026-05-25T02:01:54.139056+00:00"},{"alias_kind":"pith_short_12","alias_value":"HN4RIII5L35X","created_at":"2026-05-25T02:01:54.139056+00:00"},{"alias_kind":"pith_short_16","alias_value":"HN4RIII5L35XOEXL","created_at":"2026-05-25T02:01:54.139056+00:00"},{"alias_kind":"pith_short_8","alias_value":"HN4RIII5","created_at":"2026-05-25T02:01:54.139056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HN4RIII5L35XOEXLCCYPH3ED2U","json":"https://pith.science/pith/HN4RIII5L35XOEXLCCYPH3ED2U.json","graph_json":"https://pith.science/api/pith-number/HN4RIII5L35XOEXLCCYPH3ED2U/graph.json","events_json":"https://pith.science/api/pith-number/HN4RIII5L35XOEXLCCYPH3ED2U/events.json","paper":"https://pith.science/paper/HN4RIII5"},"agent_actions":{"view_html":"https://pith.science/pith/HN4RIII5L35XOEXLCCYPH3ED2U","download_json":"https://pith.science/pith/HN4RIII5L35XOEXLCCYPH3ED2U.json","view_paper":"https://pith.science/paper/HN4RIII5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23434&json=true","fetch_graph":"https://pith.science/api/pith-number/HN4RIII5L35XOEXLCCYPH3ED2U/graph.json","fetch_events":"https://pith.science/api/pith-number/HN4RIII5L35XOEXLCCYPH3ED2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HN4RIII5L35XOEXLCCYPH3ED2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HN4RIII5L35XOEXLCCYPH3ED2U/action/storage_attestation","attest_author":"https://pith.science/pith/HN4RIII5L35XOEXLCCYPH3ED2U/action/author_attestation","sign_citation":"https://pith.science/pith/HN4RIII5L35XOEXLCCYPH3ED2U/action/citation_signature","submit_replication":"https://pith.science/pith/HN4RIII5L35XOEXLCCYPH3ED2U/action/replication_record"}},"created_at":"2026-05-25T02:01:54.139056+00:00","updated_at":"2026-05-25T02:01:54.139056+00:00"}