{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ONQ7P2N54ZKGIG7AY7YL43BK5Q","short_pith_number":"pith:ONQ7P2N5","schema_version":"1.0","canonical_sha256":"7361f7e9bde654641be0c7f0be6c2aec10f4a28a663a991c78d8b08402248c3f","source":{"kind":"arxiv","id":"2207.05636","version":1},"attestation_state":"computed","paper":{"title":"Neural Posterior Estimation with Differentiable Simulators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"astro-ph.IM","authors_text":"Alexandre Boucaud, Benjamin Remy, Eric Aubourg, Fran\\c{c}ois Lanusse, Justine Zeghal","submitted_at":"2022-07-12T16:08:04Z","abstract_excerpt":"Simulation-Based Inference (SBI) is a promising Bayesian inference framework that alleviates the need for analytic likelihoods to estimate posterior distributions. Recent advances using neural density estimators in SBI algorithms have demonstrated the ability to achieve high-fidelity posteriors, at the expense of a large number of simulations ; which makes their application potentially very time-consuming when using complex physical simulations. In this work we focus on boosting the sample-efficiency of posterior density estimation using the gradients of the simulator. We present a new method "},"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":"2207.05636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"astro-ph.IM","submitted_at":"2022-07-12T16:08:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fb4cde5cbdec9564556a03e7a4d938a96c3de1ed071b8e25ee3c64f47ce7e702","abstract_canon_sha256":"a3152444bc55200aa8374473d930ee48bf9a026f58ffeff96b2648a47c56c798"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:44.791061Z","signature_b64":"YINIzmhM3HSvqOdelAXQ7/8AClNA1XO08t7WiBg9tvG+eNPfurjavE41OzMcU1O+P4GBibfzGi/R24fdSdmaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7361f7e9bde654641be0c7f0be6c2aec10f4a28a663a991c78d8b08402248c3f","last_reissued_at":"2026-07-05T04:39:44.790680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:44.790680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Posterior Estimation with Differentiable Simulators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"astro-ph.IM","authors_text":"Alexandre Boucaud, Benjamin Remy, Eric Aubourg, Fran\\c{c}ois Lanusse, Justine Zeghal","submitted_at":"2022-07-12T16:08:04Z","abstract_excerpt":"Simulation-Based Inference (SBI) is a promising Bayesian inference framework that alleviates the need for analytic likelihoods to estimate posterior distributions. Recent advances using neural density estimators in SBI algorithms have demonstrated the ability to achieve high-fidelity posteriors, at the expense of a large number of simulations ; which makes their application potentially very time-consuming when using complex physical simulations. In this work we focus on boosting the sample-efficiency of posterior density estimation using the gradients of the simulator. We present a new method "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05636","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/2207.05636/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":"2207.05636","created_at":"2026-07-05T04:39:44.790736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.05636v1","created_at":"2026-07-05T04:39:44.790736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05636","created_at":"2026-07-05T04:39:44.790736+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONQ7P2N54ZKG","created_at":"2026-07-05T04:39:44.790736+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONQ7P2N54ZKGIG7A","created_at":"2026-07-05T04:39:44.790736+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONQ7P2N5","created_at":"2026-07-05T04:39:44.790736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12118","citing_title":"Keeping Score: Efficiency Improvements in Neural Likelihood Surrogate Training via Score-Augmented Loss Functions","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31988","citing_title":"Joint inference of weak lensing convergence map and cosmology with diffusion models","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12118","citing_title":"Keeping Score: Efficiency Improvements in Neural Likelihood Surrogate Training via Score-Augmented Loss Functions","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONQ7P2N54ZKGIG7AY7YL43BK5Q","json":"https://pith.science/pith/ONQ7P2N54ZKGIG7AY7YL43BK5Q.json","graph_json":"https://pith.science/api/pith-number/ONQ7P2N54ZKGIG7AY7YL43BK5Q/graph.json","events_json":"https://pith.science/api/pith-number/ONQ7P2N54ZKGIG7AY7YL43BK5Q/events.json","paper":"https://pith.science/paper/ONQ7P2N5"},"agent_actions":{"view_html":"https://pith.science/pith/ONQ7P2N54ZKGIG7AY7YL43BK5Q","download_json":"https://pith.science/pith/ONQ7P2N54ZKGIG7AY7YL43BK5Q.json","view_paper":"https://pith.science/paper/ONQ7P2N5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.05636&json=true","fetch_graph":"https://pith.science/api/pith-number/ONQ7P2N54ZKGIG7AY7YL43BK5Q/graph.json","fetch_events":"https://pith.science/api/pith-number/ONQ7P2N54ZKGIG7AY7YL43BK5Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONQ7P2N54ZKGIG7AY7YL43BK5Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONQ7P2N54ZKGIG7AY7YL43BK5Q/action/storage_attestation","attest_author":"https://pith.science/pith/ONQ7P2N54ZKGIG7AY7YL43BK5Q/action/author_attestation","sign_citation":"https://pith.science/pith/ONQ7P2N54ZKGIG7AY7YL43BK5Q/action/citation_signature","submit_replication":"https://pith.science/pith/ONQ7P2N54ZKGIG7AY7YL43BK5Q/action/replication_record"}},"created_at":"2026-07-05T04:39:44.790736+00:00","updated_at":"2026-07-05T04:39:44.790736+00:00"}