{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FIFUCFCDDUI3RDYQGY6GORKWRJ","short_pith_number":"pith:FIFUCFCD","schema_version":"1.0","canonical_sha256":"2a0b4114431d11b88f10363c6745568a56db51becb4f59a74e435a549e96a7c9","source":{"kind":"arxiv","id":"2410.15336","version":1},"attestation_state":"computed","paper":{"title":"Diffusion-PINN Sampler","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Cheng Zhang, Longlin Yu, Tianyu Xie, Zhekun Shi","submitted_at":"2024-10-20T09:02:16Z","abstract_excerpt":"Recent success of diffusion models has inspired a surge of interest in developing sampling techniques using reverse diffusion processes. However, accurately estimating the drift term in the reverse stochastic differential equation (SDE) solely from the unnormalized target density poses significant challenges, hindering existing methods from achieving state-of-the-art performance. In this paper, we introduce the Diffusion-PINN Sampler (DPS), a novel diffusion-based sampling algorithm that estimates the drift term by solving the governing partial differential equation of the log-density of the u"},"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":"2410.15336","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-20T09:02:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2fa3d02c8fa93dab6e71bc76f1af507bca6bab6d5934197bad9d194a4a2be499","abstract_canon_sha256":"05fbdf273b336f68e11035c2ea2a26391fcdfe4ca4e1fa5a8867c581ab48c852"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:17.957925Z","signature_b64":"fAJxc1+7TozHv/qsSH4aHdtJhh1ScdeoqO2xq0SwdGQSQ4auKs4uLqBM1iIOyYFINBqpyjUpGPlKlNakNgqkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a0b4114431d11b88f10363c6745568a56db51becb4f59a74e435a549e96a7c9","last_reissued_at":"2026-07-05T09:23:17.957406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:17.957406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion-PINN Sampler","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Cheng Zhang, Longlin Yu, Tianyu Xie, Zhekun Shi","submitted_at":"2024-10-20T09:02:16Z","abstract_excerpt":"Recent success of diffusion models has inspired a surge of interest in developing sampling techniques using reverse diffusion processes. However, accurately estimating the drift term in the reverse stochastic differential equation (SDE) solely from the unnormalized target density poses significant challenges, hindering existing methods from achieving state-of-the-art performance. In this paper, we introduce the Diffusion-PINN Sampler (DPS), a novel diffusion-based sampling algorithm that estimates the drift term by solving the governing partial differential equation of the log-density of the u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15336","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/2410.15336/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":"2410.15336","created_at":"2026-07-05T09:23:17.957473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15336v1","created_at":"2026-07-05T09:23:17.957473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15336","created_at":"2026-07-05T09:23:17.957473+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIFUCFCDDUI3","created_at":"2026-07-05T09:23:17.957473+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIFUCFCDDUI3RDYQ","created_at":"2026-07-05T09:23:17.957473+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIFUCFCD","created_at":"2026-07-05T09:23:17.957473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06841","citing_title":"Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2601.21025","citing_title":"A Diffusive Classification Loss for Learning Energy-based Generative Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIFUCFCDDUI3RDYQGY6GORKWRJ","json":"https://pith.science/pith/FIFUCFCDDUI3RDYQGY6GORKWRJ.json","graph_json":"https://pith.science/api/pith-number/FIFUCFCDDUI3RDYQGY6GORKWRJ/graph.json","events_json":"https://pith.science/api/pith-number/FIFUCFCDDUI3RDYQGY6GORKWRJ/events.json","paper":"https://pith.science/paper/FIFUCFCD"},"agent_actions":{"view_html":"https://pith.science/pith/FIFUCFCDDUI3RDYQGY6GORKWRJ","download_json":"https://pith.science/pith/FIFUCFCDDUI3RDYQGY6GORKWRJ.json","view_paper":"https://pith.science/paper/FIFUCFCD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15336&json=true","fetch_graph":"https://pith.science/api/pith-number/FIFUCFCDDUI3RDYQGY6GORKWRJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FIFUCFCDDUI3RDYQGY6GORKWRJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIFUCFCDDUI3RDYQGY6GORKWRJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIFUCFCDDUI3RDYQGY6GORKWRJ/action/storage_attestation","attest_author":"https://pith.science/pith/FIFUCFCDDUI3RDYQGY6GORKWRJ/action/author_attestation","sign_citation":"https://pith.science/pith/FIFUCFCDDUI3RDYQGY6GORKWRJ/action/citation_signature","submit_replication":"https://pith.science/pith/FIFUCFCDDUI3RDYQGY6GORKWRJ/action/replication_record"}},"created_at":"2026-07-05T09:23:17.957473+00:00","updated_at":"2026-07-05T09:23:17.957473+00:00"}