{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2009:6F44CYDGHTP2DDEZLHQ7YFIKO2","short_pith_number":"pith:6F44CYDG","schema_version":"1.0","canonical_sha256":"f179c160663cdfa18c9959e1fc150a769ae0e88ed0a826aea2faade4b18757d6","source":{"kind":"arxiv","id":"0906.4779","version":4},"attestation_state":"computed","paper":{"title":"Minimum Probability Flow Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.data-an","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jascha Sohl-Dickstein, Michael R. DeWeese, Peter Battaglino","submitted_at":"2009-06-25T19:15:44Z","abstract_excerpt":"Fitting probabilistic models to data is often difficult, due to the general intractability of the partition function and its derivatives. Here we propose a new parameter estimation technique that does not require computing an intractable normalization factor or sampling from the equilibrium distribution of the model. This is achieved by establishing dynamics that would transform the observed data distribution into the model distribution, and then setting as the objective the minimization of the KL divergence between the data distribution and the distribution produced by running the dynamics fo"},"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":"0906.4779","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2009-06-25T19:15:44Z","cross_cats_sorted":["physics.data-an","stat.ML"],"title_canon_sha256":"0084299d0bdd540324f3845d02c8e503cd752d003c47d0955528c8c5d870b131","abstract_canon_sha256":"3289e6be07a35d66942260b0c1024a2e55b0ad03ae3246a99a59ccb644bff5bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:24:55.297784Z","signature_b64":"SkGn+mGn5Mi4Y38AOBSgsrU071RABMx1wI/Z+Z8oP3byAJn2oHZkpOtnht3iB7AT4kEKSzVwX5kVwHr6evfgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f179c160663cdfa18c9959e1fc150a769ae0e88ed0a826aea2faade4b18757d6","last_reissued_at":"2026-05-18T02:24:55.296944Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:24:55.296944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minimum Probability Flow Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.data-an","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jascha Sohl-Dickstein, Michael R. DeWeese, Peter Battaglino","submitted_at":"2009-06-25T19:15:44Z","abstract_excerpt":"Fitting probabilistic models to data is often difficult, due to the general intractability of the partition function and its derivatives. Here we propose a new parameter estimation technique that does not require computing an intractable normalization factor or sampling from the equilibrium distribution of the model. This is achieved by establishing dynamics that would transform the observed data distribution into the model distribution, and then setting as the objective the minimization of the KL divergence between the data distribution and the distribution produced by running the dynamics fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0906.4779","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"0906.4779","created_at":"2026-05-18T02:24:55.297082+00:00"},{"alias_kind":"arxiv_version","alias_value":"0906.4779v4","created_at":"2026-05-18T02:24:55.297082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0906.4779","created_at":"2026-05-18T02:24:55.297082+00:00"},{"alias_kind":"pith_short_12","alias_value":"6F44CYDGHTP2","created_at":"2026-05-18T12:25:58.837520+00:00"},{"alias_kind":"pith_short_16","alias_value":"6F44CYDGHTP2DDEZ","created_at":"2026-05-18T12:25:58.837520+00:00"},{"alias_kind":"pith_short_8","alias_value":"6F44CYDG","created_at":"2026-05-18T12:25:58.837520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.05600","citing_title":"Generative Modeling by Estimating Gradients of the Data Distribution","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6F44CYDGHTP2DDEZLHQ7YFIKO2","json":"https://pith.science/pith/6F44CYDGHTP2DDEZLHQ7YFIKO2.json","graph_json":"https://pith.science/api/pith-number/6F44CYDGHTP2DDEZLHQ7YFIKO2/graph.json","events_json":"https://pith.science/api/pith-number/6F44CYDGHTP2DDEZLHQ7YFIKO2/events.json","paper":"https://pith.science/paper/6F44CYDG"},"agent_actions":{"view_html":"https://pith.science/pith/6F44CYDGHTP2DDEZLHQ7YFIKO2","download_json":"https://pith.science/pith/6F44CYDGHTP2DDEZLHQ7YFIKO2.json","view_paper":"https://pith.science/paper/6F44CYDG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=0906.4779&json=true","fetch_graph":"https://pith.science/api/pith-number/6F44CYDGHTP2DDEZLHQ7YFIKO2/graph.json","fetch_events":"https://pith.science/api/pith-number/6F44CYDGHTP2DDEZLHQ7YFIKO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6F44CYDGHTP2DDEZLHQ7YFIKO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6F44CYDGHTP2DDEZLHQ7YFIKO2/action/storage_attestation","attest_author":"https://pith.science/pith/6F44CYDGHTP2DDEZLHQ7YFIKO2/action/author_attestation","sign_citation":"https://pith.science/pith/6F44CYDGHTP2DDEZLHQ7YFIKO2/action/citation_signature","submit_replication":"https://pith.science/pith/6F44CYDGHTP2DDEZLHQ7YFIKO2/action/replication_record"}},"created_at":"2026-05-18T02:24:55.297082+00:00","updated_at":"2026-05-18T02:24:55.297082+00:00"}