{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AGJWS35VRAJPQTRFYGPKKJXXGF","short_pith_number":"pith:AGJWS35V","schema_version":"1.0","canonical_sha256":"0193696fb58812f84e25c19ea526f7317dfa9b602781661ec899df8825bbc617","source":{"kind":"arxiv","id":"2506.05088","version":1},"attestation_state":"computed","paper":{"title":"Semi-Implicit Variational Inference via Kernelized Path Gradient Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"cs.LG","authors_text":"Bernd Bischl, David R\\\"ugamer, Tobias Pielok","submitted_at":"2025-06-05T14:34:37Z","abstract_excerpt":"Semi-implicit variational inference (SIVI) is a powerful framework for approximating complex posterior distributions, but training with the Kullback-Leibler (KL) divergence can be challenging due to high variance and bias in high-dimensional settings. While current state-of-the-art semi-implicit variational inference methods, particularly Kernel Semi-Implicit Variational Inference (KSIVI), have been shown to work in high dimensions, training remains moderately expensive. In this work, we propose a kernelized KL divergence estimator that stabilizes training through nonparametric smoothing. To f"},"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":"2506.05088","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T14:34:37Z","cross_cats_sorted":["stat.CO"],"title_canon_sha256":"6aba400642d428d44979a6e16524199033cfda3c40f7f0068e47107f0b06bcc8","abstract_canon_sha256":"3b12572a865f488cf9ecc03c9ae145d795ea94502a311f68e189e5349ce0aae3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:42.042199Z","signature_b64":"H8yVk7b1zTChdKuY5wGCM+LK7Zl8SUCZfFRB4EG10oZ8XHx++F67g1FFbC9E30Ba0R9E3DB1gApHJrxBPeziDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0193696fb58812f84e25c19ea526f7317dfa9b602781661ec899df8825bbc617","last_reissued_at":"2026-07-05T11:16:42.041601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:42.041601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Implicit Variational Inference via Kernelized Path Gradient Descent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.CO"],"primary_cat":"cs.LG","authors_text":"Bernd Bischl, David R\\\"ugamer, Tobias Pielok","submitted_at":"2025-06-05T14:34:37Z","abstract_excerpt":"Semi-implicit variational inference (SIVI) is a powerful framework for approximating complex posterior distributions, but training with the Kullback-Leibler (KL) divergence can be challenging due to high variance and bias in high-dimensional settings. While current state-of-the-art semi-implicit variational inference methods, particularly Kernel Semi-Implicit Variational Inference (KSIVI), have been shown to work in high dimensions, training remains moderately expensive. In this work, we propose a kernelized KL divergence estimator that stabilizes training through nonparametric smoothing. To f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05088","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/2506.05088/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":"2506.05088","created_at":"2026-07-05T11:16:42.041691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05088v1","created_at":"2026-07-05T11:16:42.041691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05088","created_at":"2026-07-05T11:16:42.041691+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGJWS35VRAJP","created_at":"2026-07-05T11:16:42.041691+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGJWS35VRAJPQTRF","created_at":"2026-07-05T11:16:42.041691+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGJWS35V","created_at":"2026-07-05T11:16:42.041691+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/AGJWS35VRAJPQTRFYGPKKJXXGF","json":"https://pith.science/pith/AGJWS35VRAJPQTRFYGPKKJXXGF.json","graph_json":"https://pith.science/api/pith-number/AGJWS35VRAJPQTRFYGPKKJXXGF/graph.json","events_json":"https://pith.science/api/pith-number/AGJWS35VRAJPQTRFYGPKKJXXGF/events.json","paper":"https://pith.science/paper/AGJWS35V"},"agent_actions":{"view_html":"https://pith.science/pith/AGJWS35VRAJPQTRFYGPKKJXXGF","download_json":"https://pith.science/pith/AGJWS35VRAJPQTRFYGPKKJXXGF.json","view_paper":"https://pith.science/paper/AGJWS35V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05088&json=true","fetch_graph":"https://pith.science/api/pith-number/AGJWS35VRAJPQTRFYGPKKJXXGF/graph.json","fetch_events":"https://pith.science/api/pith-number/AGJWS35VRAJPQTRFYGPKKJXXGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGJWS35VRAJPQTRFYGPKKJXXGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGJWS35VRAJPQTRFYGPKKJXXGF/action/storage_attestation","attest_author":"https://pith.science/pith/AGJWS35VRAJPQTRFYGPKKJXXGF/action/author_attestation","sign_citation":"https://pith.science/pith/AGJWS35VRAJPQTRFYGPKKJXXGF/action/citation_signature","submit_replication":"https://pith.science/pith/AGJWS35VRAJPQTRFYGPKKJXXGF/action/replication_record"}},"created_at":"2026-07-05T11:16:42.041691+00:00","updated_at":"2026-07-05T11:16:42.041691+00:00"}