{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KB4KUBCUDFHMYHLZE4WT6PF7I6","short_pith_number":"pith:KB4KUBCU","schema_version":"1.0","canonical_sha256":"5078aa0454194ecc1d79272d3f3cbf478ed6e141c61effeb62306f9670346588","source":{"kind":"arxiv","id":"2206.13397","version":7},"attestation_state":"computed","paper":{"title":"Generative Modelling With Inverse Heat Dissipation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Arno Solin, Markus Heinonen, Severi Rissanen","submitted_at":"2022-06-21T13:40:38Z","abstract_excerpt":"While diffusion models have shown great success in image generation, their noise-inverting generative process does not explicitly consider the structure of images, such as their inherent multi-scale nature. Inspired by diffusion models and the empirical success of coarse-to-fine modelling, we propose a new diffusion-like model that generates images through stochastically reversing the heat equation, a PDE that locally erases fine-scale information when run over the 2D plane of the image. We interpret the solution of the forward heat equation with constant additive noise as a variational approx"},"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":"2206.13397","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-21T13:40:38Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"24b6efa35aa0188f5d470d6012582ca27490a2d540f653ca9c7a7a89ee43ef4e","abstract_canon_sha256":"086eab059f82ad9a031a46599c13fa31b022c9ca1a19c805d59c7f09e22a2bed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:31.312961Z","signature_b64":"yVduh62JoZtq/sE7qCR3c1ibXNpnBXEh5txWBJr5Q91L/7R6Ii3hX44P5Kof8Lbx3tNImPTLITMKYLEsd1S+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5078aa0454194ecc1d79272d3f3cbf478ed6e141c61effeb62306f9670346588","last_reissued_at":"2026-07-05T06:00:31.312544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:31.312544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Modelling With Inverse Heat Dissipation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Arno Solin, Markus Heinonen, Severi Rissanen","submitted_at":"2022-06-21T13:40:38Z","abstract_excerpt":"While diffusion models have shown great success in image generation, their noise-inverting generative process does not explicitly consider the structure of images, such as their inherent multi-scale nature. Inspired by diffusion models and the empirical success of coarse-to-fine modelling, we propose a new diffusion-like model that generates images through stochastically reversing the heat equation, a PDE that locally erases fine-scale information when run over the 2D plane of the image. We interpret the solution of the forward heat equation with constant additive noise as a variational approx"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13397","kind":"arxiv","version":7},"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/2206.13397/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":"2206.13397","created_at":"2026-07-05T06:00:31.312601+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.13397v7","created_at":"2026-07-05T06:00:31.312601+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13397","created_at":"2026-07-05T06:00:31.312601+00:00"},{"alias_kind":"pith_short_12","alias_value":"KB4KUBCUDFHM","created_at":"2026-07-05T06:00:31.312601+00:00"},{"alias_kind":"pith_short_16","alias_value":"KB4KUBCUDFHMYHLZ","created_at":"2026-07-05T06:00:31.312601+00:00"},{"alias_kind":"pith_short_8","alias_value":"KB4KUBCU","created_at":"2026-07-05T06:00:31.312601+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":211,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20299","citing_title":"Statistical Properties of Training & Generalization","ref_index":211,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24509","citing_title":"{\\Phi}-Noise: Training-Free Temporal Video Conditioning via Phase-Based Noise Manipulation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26032","citing_title":"Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27919","citing_title":"Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03393","citing_title":"Flicker-DDPM: Accelerating Denoising Diffusion via 1/f Colored Noise Injection","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2503.03206","citing_title":"An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18190","citing_title":"Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16827","citing_title":"Beyond Blur: A Fluid Perspective on Generative Diffusion Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16344","citing_title":"Diff-ANO: Towards Fast High-Resolution Ultrasound Computed Tomography via Conditional Consistency Models and Adjoint Neural Operators","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2505.05472","citing_title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13910","citing_title":"Covariance-aware sampling for Diffusion Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11506","citing_title":"Principled Design of Diffusion-based Optimizers for Inverse Problems","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07915","citing_title":"What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KB4KUBCUDFHMYHLZE4WT6PF7I6","json":"https://pith.science/pith/KB4KUBCUDFHMYHLZE4WT6PF7I6.json","graph_json":"https://pith.science/api/pith-number/KB4KUBCUDFHMYHLZE4WT6PF7I6/graph.json","events_json":"https://pith.science/api/pith-number/KB4KUBCUDFHMYHLZE4WT6PF7I6/events.json","paper":"https://pith.science/paper/KB4KUBCU"},"agent_actions":{"view_html":"https://pith.science/pith/KB4KUBCUDFHMYHLZE4WT6PF7I6","download_json":"https://pith.science/pith/KB4KUBCUDFHMYHLZE4WT6PF7I6.json","view_paper":"https://pith.science/paper/KB4KUBCU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.13397&json=true","fetch_graph":"https://pith.science/api/pith-number/KB4KUBCUDFHMYHLZE4WT6PF7I6/graph.json","fetch_events":"https://pith.science/api/pith-number/KB4KUBCUDFHMYHLZE4WT6PF7I6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KB4KUBCUDFHMYHLZE4WT6PF7I6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KB4KUBCUDFHMYHLZE4WT6PF7I6/action/storage_attestation","attest_author":"https://pith.science/pith/KB4KUBCUDFHMYHLZE4WT6PF7I6/action/author_attestation","sign_citation":"https://pith.science/pith/KB4KUBCUDFHMYHLZE4WT6PF7I6/action/citation_signature","submit_replication":"https://pith.science/pith/KB4KUBCUDFHMYHLZE4WT6PF7I6/action/replication_record"}},"created_at":"2026-07-05T06:00:31.312601+00:00","updated_at":"2026-07-05T06:00:31.312601+00:00"}