{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N6QZUL5TSONPL2YPJ64WBMLYTT","short_pith_number":"pith:N6QZUL5T","schema_version":"1.0","canonical_sha256":"6fa19a2fb3939af5eb0f4fb960b1789cf31522108fbaa01b17d859e1d18fd7e5","source":{"kind":"arxiv","id":"2601.22367","version":2},"attestation_state":"computed","paper":{"title":"Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Geoff K. Nicholls, Jeong Eun Lee, Shiyi Sun","submitted_at":"2026-01-29T22:20:47Z","abstract_excerpt":"Generalized Bayesian Inference (GBI) tempers a loss with a temperature $\\beta > 0$ to mitigate overconfidence and improve robustness under model misspecification, but existing GBI methods typically rely on costly MCMC or SDE-based samplers and must be re-run for each new dataset and each $\\beta$ value. We give the first fully amortized variational approximation for the tempered posterior family by training a single data- and $\\beta$-conditioned neural posterior estimator that enables sampling in a single forward pass, without simulator calls or inference-time MCMC. We introduce two complementa"},"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":"2601.22367","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-01-29T22:20:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e43e7a69ae5596a3f53ab0f25c4435047a8e0843c63cebedae7d00b71321b87e","abstract_canon_sha256":"b1fdb4253f26bb7f096a519b4a70ce25cad13ae7885bbdd400153cd0c5d762db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:12.937098Z","signature_b64":"wPcNPjtWHwbU0+vsheaaLO6555w3YQ1PdryEUf4APoV+RxwllKkQL8RaDeyVx8A0vFJ4WBX44HEAljxY7aNtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fa19a2fb3939af5eb0f4fb960b1789cf31522108fbaa01b17d859e1d18fd7e5","last_reissued_at":"2026-05-25T02:02:12.936444Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:12.936444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Geoff K. Nicholls, Jeong Eun Lee, Shiyi Sun","submitted_at":"2026-01-29T22:20:47Z","abstract_excerpt":"Generalized Bayesian Inference (GBI) tempers a loss with a temperature $\\beta > 0$ to mitigate overconfidence and improve robustness under model misspecification, but existing GBI methods typically rely on costly MCMC or SDE-based samplers and must be re-run for each new dataset and each $\\beta$ value. We give the first fully amortized variational approximation for the tempered posterior family by training a single data- and $\\beta$-conditioned neural posterior estimator that enables sampling in a single forward pass, without simulator calls or inference-time MCMC. We introduce two complementa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.22367","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/2601.22367/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":"2601.22367","created_at":"2026-05-25T02:02:12.936536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.22367v2","created_at":"2026-05-25T02:02:12.936536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.22367","created_at":"2026-05-25T02:02:12.936536+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6QZUL5TSONP","created_at":"2026-05-25T02:02:12.936536+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6QZUL5TSONPL2YP","created_at":"2026-05-25T02:02:12.936536+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6QZUL5T","created_at":"2026-05-25T02:02:12.936536+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/N6QZUL5TSONPL2YPJ64WBMLYTT","json":"https://pith.science/pith/N6QZUL5TSONPL2YPJ64WBMLYTT.json","graph_json":"https://pith.science/api/pith-number/N6QZUL5TSONPL2YPJ64WBMLYTT/graph.json","events_json":"https://pith.science/api/pith-number/N6QZUL5TSONPL2YPJ64WBMLYTT/events.json","paper":"https://pith.science/paper/N6QZUL5T"},"agent_actions":{"view_html":"https://pith.science/pith/N6QZUL5TSONPL2YPJ64WBMLYTT","download_json":"https://pith.science/pith/N6QZUL5TSONPL2YPJ64WBMLYTT.json","view_paper":"https://pith.science/paper/N6QZUL5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.22367&json=true","fetch_graph":"https://pith.science/api/pith-number/N6QZUL5TSONPL2YPJ64WBMLYTT/graph.json","fetch_events":"https://pith.science/api/pith-number/N6QZUL5TSONPL2YPJ64WBMLYTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6QZUL5TSONPL2YPJ64WBMLYTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6QZUL5TSONPL2YPJ64WBMLYTT/action/storage_attestation","attest_author":"https://pith.science/pith/N6QZUL5TSONPL2YPJ64WBMLYTT/action/author_attestation","sign_citation":"https://pith.science/pith/N6QZUL5TSONPL2YPJ64WBMLYTT/action/citation_signature","submit_replication":"https://pith.science/pith/N6QZUL5TSONPL2YPJ64WBMLYTT/action/replication_record"}},"created_at":"2026-05-25T02:02:12.936536+00:00","updated_at":"2026-05-25T02:02:12.936536+00:00"}