{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MXKGKT5AJ55TEVA2XJSY6JLKDI","short_pith_number":"pith:MXKGKT5A","schema_version":"1.0","canonical_sha256":"65d4654fa04f7b32541aba658f256a1a07624205ab16e7781a6bd3d746b5d9ee","source":{"kind":"arxiv","id":"2502.06685","version":2},"attestation_state":"computed","paper":{"title":"No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carla Gomes, Dinghuai Zhang, Francisco Vargas, Jiajun He, Jos\\'e Miguel Hern\\'andez-Lobato, RuiKang OuYang, Shreyas Padhy, Yuanqi Du","submitted_at":"2025-02-10T17:13:11Z","abstract_excerpt":"We consider the sampling problem, where the aim is to draw samples from a distribution whose density is known only up to a normalization constant. Recent breakthroughs in generative modeling to approximate a high-dimensional data distribution have sparked significant interest in developing neural network-based methods for this challenging problem. However, neural samplers typically incur heavy computational overhead due to simulating trajectories during training. This motivates the pursuit of simulation-free training procedures of neural samplers. In this work, we propose an elegant modificati"},"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":"2502.06685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T17:13:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7f1ad91d004091d2c3ca540a88a16c39e94de6c58b6a47f51b5df07ca57df525","abstract_canon_sha256":"76f3f4c4a4bc88e3c06426d25af3ff658782ca3a1ff232c6d84ee36cb5f8d4c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:00.414145Z","signature_b64":"u05M7vKW7Hmbh5HgEhNJMQ+jdQSAXEsCPWV/GoigTTlFMrfDTdMH5k8uZMcHjAu3tScPLwpwE4wXR/vFerT9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65d4654fa04f7b32541aba658f256a1a07624205ab16e7781a6bd3d746b5d9ee","last_reissued_at":"2026-07-05T10:47:00.413634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:00.413634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carla Gomes, Dinghuai Zhang, Francisco Vargas, Jiajun He, Jos\\'e Miguel Hern\\'andez-Lobato, RuiKang OuYang, Shreyas Padhy, Yuanqi Du","submitted_at":"2025-02-10T17:13:11Z","abstract_excerpt":"We consider the sampling problem, where the aim is to draw samples from a distribution whose density is known only up to a normalization constant. Recent breakthroughs in generative modeling to approximate a high-dimensional data distribution have sparked significant interest in developing neural network-based methods for this challenging problem. However, neural samplers typically incur heavy computational overhead due to simulating trajectories during training. This motivates the pursuit of simulation-free training procedures of neural samplers. In this work, we propose an elegant modificati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06685","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/2502.06685/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":"2502.06685","created_at":"2026-07-05T10:47:00.413698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06685v2","created_at":"2026-07-05T10:47:00.413698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06685","created_at":"2026-07-05T10:47:00.413698+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXKGKT5AJ55T","created_at":"2026-07-05T10:47:00.413698+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXKGKT5AJ55TEVA2","created_at":"2026-07-05T10:47:00.413698+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXKGKT5A","created_at":"2026-07-05T10:47:00.413698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08335","citing_title":"Bayesian Experimental Design via Score Matching","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08743","citing_title":"Guided Discovery of New Behaviors using Diffusion Policies","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXKGKT5AJ55TEVA2XJSY6JLKDI","json":"https://pith.science/pith/MXKGKT5AJ55TEVA2XJSY6JLKDI.json","graph_json":"https://pith.science/api/pith-number/MXKGKT5AJ55TEVA2XJSY6JLKDI/graph.json","events_json":"https://pith.science/api/pith-number/MXKGKT5AJ55TEVA2XJSY6JLKDI/events.json","paper":"https://pith.science/paper/MXKGKT5A"},"agent_actions":{"view_html":"https://pith.science/pith/MXKGKT5AJ55TEVA2XJSY6JLKDI","download_json":"https://pith.science/pith/MXKGKT5AJ55TEVA2XJSY6JLKDI.json","view_paper":"https://pith.science/paper/MXKGKT5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06685&json=true","fetch_graph":"https://pith.science/api/pith-number/MXKGKT5AJ55TEVA2XJSY6JLKDI/graph.json","fetch_events":"https://pith.science/api/pith-number/MXKGKT5AJ55TEVA2XJSY6JLKDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXKGKT5AJ55TEVA2XJSY6JLKDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXKGKT5AJ55TEVA2XJSY6JLKDI/action/storage_attestation","attest_author":"https://pith.science/pith/MXKGKT5AJ55TEVA2XJSY6JLKDI/action/author_attestation","sign_citation":"https://pith.science/pith/MXKGKT5AJ55TEVA2XJSY6JLKDI/action/citation_signature","submit_replication":"https://pith.science/pith/MXKGKT5AJ55TEVA2XJSY6JLKDI/action/replication_record"}},"created_at":"2026-07-05T10:47:00.413698+00:00","updated_at":"2026-07-05T10:47:00.413698+00:00"}