{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OYR2Y7QWHJD47D4BZ54FK6KPFC","short_pith_number":"pith:OYR2Y7QW","schema_version":"1.0","canonical_sha256":"7623ac7e163a47cf8f81cf7855794f28b8e56eb437ad8122ea931b359cb126e0","source":{"kind":"arxiv","id":"2403.14404","version":4},"attestation_state":"computed","paper":{"title":"Physics-Informed Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE"],"primary_cat":"cs.LG","authors_text":"Dennis M. Kochmann, Jan-Hendrik Bastek, WaiChing Sun","submitted_at":"2024-03-21T13:52:55Z","abstract_excerpt":"Generative models such as denoising diffusion models are quickly advancing their ability to approximate highly complex data distributions. They are also increasingly leveraged in scientific machine learning, where samples from the implied data distribution are expected to adhere to specific governing equations. We present a framework that unifies generative modeling and partial differential equation fulfillment by introducing a first-principle-based loss term that enforces generated samples to fulfill the underlying physical constraints. Our approach reduces the residual error by up to two ord"},"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":"2403.14404","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-21T13:52:55Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"0d77d1354985de891ecebfb37f144626c764e524753e0920ccad078aa2cdf672","abstract_canon_sha256":"6673feb08c7461daf3309fad7408a3f5fc1203a041e78508cbf22278b666c6df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:20.165021Z","signature_b64":"DlwNTS7xs5s2HQwXH/cRZ4JE5N3eX7WcCU67idikUNuK+z0qpOAowK/ToYw2vcRixYVmI/a+OatyU5Bx85x/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7623ac7e163a47cf8f81cf7855794f28b8e56eb437ad8122ea931b359cb126e0","last_reissued_at":"2026-07-05T10:30:20.164408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:20.164408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Physics-Informed Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE"],"primary_cat":"cs.LG","authors_text":"Dennis M. Kochmann, Jan-Hendrik Bastek, WaiChing Sun","submitted_at":"2024-03-21T13:52:55Z","abstract_excerpt":"Generative models such as denoising diffusion models are quickly advancing their ability to approximate highly complex data distributions. They are also increasingly leveraged in scientific machine learning, where samples from the implied data distribution are expected to adhere to specific governing equations. We present a framework that unifies generative modeling and partial differential equation fulfillment by introducing a first-principle-based loss term that enforces generated samples to fulfill the underlying physical constraints. Our approach reduces the residual error by up to two ord"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14404","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.14404/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":"2403.14404","created_at":"2026-07-05T10:30:20.164469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14404v4","created_at":"2026-07-05T10:30:20.164469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14404","created_at":"2026-07-05T10:30:20.164469+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYR2Y7QWHJD4","created_at":"2026-07-05T10:30:20.164469+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYR2Y7QWHJD47D4B","created_at":"2026-07-05T10:30:20.164469+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYR2Y7QW","created_at":"2026-07-05T10:30:20.164469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31321","citing_title":"Surface Constraint Policy for Learning Surface-Constrained and Dynamically Feasible Robot Skills","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28368","citing_title":"LEIA: Learned Environment for Interactive Architected Materials","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20780","citing_title":"Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16818","citing_title":"Observation-Aligned Mask Priors for Learning Physical Dynamics from Authentic Occlusions","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15753","citing_title":"Algebraic Language Models for Inverse Design of Metamaterials via Diffusion Transformers","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18611","citing_title":"Flow marching for a generative PDE foundation model","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2512.19469","citing_title":"GLUE: Coordinating Pre-Trained Generative Models for System-Level Design","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12754","citing_title":"Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28932","citing_title":"A Unified Multiscale Auxiliary PINN Framework for Generalized Phonon Transport","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03409","citing_title":"Generative AI for material design: A mechanics perspective from burgers to matter","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09039","citing_title":"Diffusion Inpainting MIMO-OFDM Channels with Limited Noisy Observations","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYR2Y7QWHJD47D4BZ54FK6KPFC","json":"https://pith.science/pith/OYR2Y7QWHJD47D4BZ54FK6KPFC.json","graph_json":"https://pith.science/api/pith-number/OYR2Y7QWHJD47D4BZ54FK6KPFC/graph.json","events_json":"https://pith.science/api/pith-number/OYR2Y7QWHJD47D4BZ54FK6KPFC/events.json","paper":"https://pith.science/paper/OYR2Y7QW"},"agent_actions":{"view_html":"https://pith.science/pith/OYR2Y7QWHJD47D4BZ54FK6KPFC","download_json":"https://pith.science/pith/OYR2Y7QWHJD47D4BZ54FK6KPFC.json","view_paper":"https://pith.science/paper/OYR2Y7QW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14404&json=true","fetch_graph":"https://pith.science/api/pith-number/OYR2Y7QWHJD47D4BZ54FK6KPFC/graph.json","fetch_events":"https://pith.science/api/pith-number/OYR2Y7QWHJD47D4BZ54FK6KPFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYR2Y7QWHJD47D4BZ54FK6KPFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYR2Y7QWHJD47D4BZ54FK6KPFC/action/storage_attestation","attest_author":"https://pith.science/pith/OYR2Y7QWHJD47D4BZ54FK6KPFC/action/author_attestation","sign_citation":"https://pith.science/pith/OYR2Y7QWHJD47D4BZ54FK6KPFC/action/citation_signature","submit_replication":"https://pith.science/pith/OYR2Y7QWHJD47D4BZ54FK6KPFC/action/replication_record"}},"created_at":"2026-07-05T10:30:20.164469+00:00","updated_at":"2026-07-05T10:30:20.164469+00:00"}