{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OVHTCXM2XUZXHK5GHHNDFAMEN6","short_pith_number":"pith:OVHTCXM2","schema_version":"1.0","canonical_sha256":"754f315d9abd3373aba639da3281846f8a6dc2a23e25658506c9c507d25de62d","source":{"kind":"arxiv","id":"2505.10466","version":1},"attestation_state":"computed","paper":{"title":"FlowVAT: Normalizing Flow Variational Inference with Affine-Invariant Tempering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Christopher Tunnell, Juehang Qin, Shixiao Liang","submitted_at":"2025-05-15T16:20:36Z","abstract_excerpt":"Multi-modal and high-dimensional posteriors present significant challenges for variational inference, causing mode-seeking behavior and collapse despite the theoretical expressiveness of normalizing flows. Traditional annealing methods require temperature schedules and hyperparameter tuning, falling short of the goal of truly black-box variational inference. We introduce FlowVAT, a conditional tempering approach for normalizing flow variational inference that addresses these limitations. Our method tempers both the base and target distributions simultaneously, maintaining affine-invariance und"},"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":"2505.10466","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-15T16:20:36Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"18dff8e6fa4b2b5cd710903a7dfc1087510d0047d2cd165ad03ddec327ef87ff","abstract_canon_sha256":"8e2d2e793f21dfbe02acc655db79c4ef15b5fe6a8671e9c9914023109e23a0dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:38.708229Z","signature_b64":"sl2tRAFWBzK6hMYV0gddl/pDuMz4bZlq75L2TyAw93M1hC4Oc3RHb64y1VYaDlbsVWEmt6Ra/R5aMIzLBzkTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"754f315d9abd3373aba639da3281846f8a6dc2a23e25658506c9c507d25de62d","last_reissued_at":"2026-07-05T11:03:38.707725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:38.707725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlowVAT: Normalizing Flow Variational Inference with Affine-Invariant Tempering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Christopher Tunnell, Juehang Qin, Shixiao Liang","submitted_at":"2025-05-15T16:20:36Z","abstract_excerpt":"Multi-modal and high-dimensional posteriors present significant challenges for variational inference, causing mode-seeking behavior and collapse despite the theoretical expressiveness of normalizing flows. Traditional annealing methods require temperature schedules and hyperparameter tuning, falling short of the goal of truly black-box variational inference. We introduce FlowVAT, a conditional tempering approach for normalizing flow variational inference that addresses these limitations. Our method tempers both the base and target distributions simultaneously, maintaining affine-invariance und"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10466","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/2505.10466/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":"2505.10466","created_at":"2026-07-05T11:03:38.707795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.10466v1","created_at":"2026-07-05T11:03:38.707795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10466","created_at":"2026-07-05T11:03:38.707795+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVHTCXM2XUZX","created_at":"2026-07-05T11:03:38.707795+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVHTCXM2XUZXHK5G","created_at":"2026-07-05T11:03:38.707795+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVHTCXM2","created_at":"2026-07-05T11:03:38.707795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.03885","citing_title":"Identifying lensed gravitational waves with physics-informed posterior learning","ref_index":161,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OVHTCXM2XUZXHK5GHHNDFAMEN6","json":"https://pith.science/pith/OVHTCXM2XUZXHK5GHHNDFAMEN6.json","graph_json":"https://pith.science/api/pith-number/OVHTCXM2XUZXHK5GHHNDFAMEN6/graph.json","events_json":"https://pith.science/api/pith-number/OVHTCXM2XUZXHK5GHHNDFAMEN6/events.json","paper":"https://pith.science/paper/OVHTCXM2"},"agent_actions":{"view_html":"https://pith.science/pith/OVHTCXM2XUZXHK5GHHNDFAMEN6","download_json":"https://pith.science/pith/OVHTCXM2XUZXHK5GHHNDFAMEN6.json","view_paper":"https://pith.science/paper/OVHTCXM2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.10466&json=true","fetch_graph":"https://pith.science/api/pith-number/OVHTCXM2XUZXHK5GHHNDFAMEN6/graph.json","fetch_events":"https://pith.science/api/pith-number/OVHTCXM2XUZXHK5GHHNDFAMEN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVHTCXM2XUZXHK5GHHNDFAMEN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVHTCXM2XUZXHK5GHHNDFAMEN6/action/storage_attestation","attest_author":"https://pith.science/pith/OVHTCXM2XUZXHK5GHHNDFAMEN6/action/author_attestation","sign_citation":"https://pith.science/pith/OVHTCXM2XUZXHK5GHHNDFAMEN6/action/citation_signature","submit_replication":"https://pith.science/pith/OVHTCXM2XUZXHK5GHHNDFAMEN6/action/replication_record"}},"created_at":"2026-07-05T11:03:38.707795+00:00","updated_at":"2026-07-05T11:03:38.707795+00:00"}