{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EFI2JLLHBFUWCWMD7Q5OYWJ7VF","short_pith_number":"pith:EFI2JLLH","schema_version":"1.0","canonical_sha256":"2151a4ad670969615983fc3aec593fa963297b800ce1a237b63901840677874c","source":{"kind":"arxiv","id":"2410.06986","version":1},"attestation_state":"computed","paper":{"title":"Diffusion Density Estimators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akhil Premkumar","submitted_at":"2024-10-09T15:21:53Z","abstract_excerpt":"We investigate the use of diffusion models as neural density estimators. The current approach to this problem involves converting the generative process to a smooth flow, known as the Probability Flow ODE. The log density at a given sample can be obtained by solving the ODE with a black-box solver. We introduce a new, highly parallelizable method that computes log densities without the need to solve a flow. Our approach is based on estimating a path integral by Monte Carlo, in a manner identical to the simulation-free training of diffusion models. We also study how different training parameter"},"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":"2410.06986","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-09T15:21:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"383e6b08a94a25c2896aaed4791be8b843e58611d304e1b01ee0e0aa85400542","abstract_canon_sha256":"7eb94418a05c30952e55ff9984173f01ea0487e1158d08ab8204a6dc89e2ef00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:09.411486Z","signature_b64":"OBSCfQhvwRD1jBWOPLDw3mLFIWOE3unxKWZF8nb03+CibwfDDOpn3JNBMnaMbdHYAZZj5BuXHniuf53XuZKvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2151a4ad670969615983fc3aec593fa963297b800ce1a237b63901840677874c","last_reissued_at":"2026-07-05T09:18:09.411008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:09.411008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Density Estimators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akhil Premkumar","submitted_at":"2024-10-09T15:21:53Z","abstract_excerpt":"We investigate the use of diffusion models as neural density estimators. The current approach to this problem involves converting the generative process to a smooth flow, known as the Probability Flow ODE. The log density at a given sample can be obtained by solving the ODE with a black-box solver. We introduce a new, highly parallelizable method that computes log densities without the need to solve a flow. Our approach is based on estimating a path integral by Monte Carlo, in a manner identical to the simulation-free training of diffusion models. We also study how different training parameter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06986","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/2410.06986/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":"2410.06986","created_at":"2026-07-05T09:18:09.411065+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.06986v1","created_at":"2026-07-05T09:18:09.411065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06986","created_at":"2026-07-05T09:18:09.411065+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFI2JLLHBFUW","created_at":"2026-07-05T09:18:09.411065+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFI2JLLHBFUWCWMD","created_at":"2026-07-05T09:18:09.411065+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFI2JLLH","created_at":"2026-07-05T09:18:09.411065+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22429","citing_title":"Comparing Normalizing Flows with Kernel Density Estimation in Estimating Risk of Automated Driving Systems","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EFI2JLLHBFUWCWMD7Q5OYWJ7VF","json":"https://pith.science/pith/EFI2JLLHBFUWCWMD7Q5OYWJ7VF.json","graph_json":"https://pith.science/api/pith-number/EFI2JLLHBFUWCWMD7Q5OYWJ7VF/graph.json","events_json":"https://pith.science/api/pith-number/EFI2JLLHBFUWCWMD7Q5OYWJ7VF/events.json","paper":"https://pith.science/paper/EFI2JLLH"},"agent_actions":{"view_html":"https://pith.science/pith/EFI2JLLHBFUWCWMD7Q5OYWJ7VF","download_json":"https://pith.science/pith/EFI2JLLHBFUWCWMD7Q5OYWJ7VF.json","view_paper":"https://pith.science/paper/EFI2JLLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.06986&json=true","fetch_graph":"https://pith.science/api/pith-number/EFI2JLLHBFUWCWMD7Q5OYWJ7VF/graph.json","fetch_events":"https://pith.science/api/pith-number/EFI2JLLHBFUWCWMD7Q5OYWJ7VF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFI2JLLHBFUWCWMD7Q5OYWJ7VF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFI2JLLHBFUWCWMD7Q5OYWJ7VF/action/storage_attestation","attest_author":"https://pith.science/pith/EFI2JLLHBFUWCWMD7Q5OYWJ7VF/action/author_attestation","sign_citation":"https://pith.science/pith/EFI2JLLHBFUWCWMD7Q5OYWJ7VF/action/citation_signature","submit_replication":"https://pith.science/pith/EFI2JLLHBFUWCWMD7Q5OYWJ7VF/action/replication_record"}},"created_at":"2026-07-05T09:18:09.411065+00:00","updated_at":"2026-07-05T09:18:09.411065+00:00"}