{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BF6N6YRRSTRRZQKU6BARCV3DMA","short_pith_number":"pith:BF6N6YRR","schema_version":"1.0","canonical_sha256":"097cdf623194e31cc154f041115763601e0fb8fa4070d39c23ceb77df52d9d0a","source":{"kind":"arxiv","id":"2510.21890","version":1},"attestation_state":"computed","paper":{"title":"The Principles of Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.LG","authors_text":"Chieh-Hsin Lai, Dongjun Kim, Stefano Ermon, Yang Song, Yuki Mitsufuji","submitted_at":"2025-10-24T02:29:02Z","abstract_excerpt":"This monograph presents the core principles that have guided the development of diffusion models, tracing their origins and showing how diverse formulations arise from shared mathematical ideas. Diffusion modeling starts by defining a forward process that gradually corrupts data into noise, linking the data distribution to a simple prior through a continuum of intermediate distributions. The goal is to learn a reverse process that transforms noise back into data while recovering the same intermediates. We describe three complementary views. The variational view, inspired by variational autoenc"},"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":"2510.21890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-10-24T02:29:02Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"cc05fe4a03541550895d8f1a521ed366aabd766a4816697ca434fe5340a4ec04","abstract_canon_sha256":"4405b3107e4c7af95828b6de08e1010f5894fc8872e257181a29d99642330a73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:27.729892Z","signature_b64":"Ra6+sdfiPPq6xmp5hr31hu+bzdOlTpN274WekbgHSFCkVfyqnCwXZT2EyEr8dZOc2InNw3ftcPKpxw3JtzDUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"097cdf623194e31cc154f041115763601e0fb8fa4070d39c23ceb77df52d9d0a","last_reissued_at":"2026-05-17T23:51:27.729192Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:27.729192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Principles of Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.LG","authors_text":"Chieh-Hsin Lai, Dongjun Kim, Stefano Ermon, Yang Song, Yuki Mitsufuji","submitted_at":"2025-10-24T02:29:02Z","abstract_excerpt":"This monograph presents the core principles that have guided the development of diffusion models, tracing their origins and showing how diverse formulations arise from shared mathematical ideas. Diffusion modeling starts by defining a forward process that gradually corrupts data into noise, linking the data distribution to a simple prior through a continuum of intermediate distributions. The goal is to learn a reverse process that transforms noise back into data while recovering the same intermediates. We describe three complementary views. The variational view, inspired by variational autoenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.21890","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":""},"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":"2510.21890","created_at":"2026-05-17T23:51:27.729290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.21890v1","created_at":"2026-05-17T23:51:27.729290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.21890","created_at":"2026-05-17T23:51:27.729290+00:00"},{"alias_kind":"pith_short_12","alias_value":"BF6N6YRRSTRR","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"BF6N6YRRSTRRZQKU","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"BF6N6YRR","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":17,"sample":[{"citing_arxiv_id":"2511.08416","citing_title":"Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communications","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2512.02826","citing_title":"From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2512.16768","citing_title":"On The Hidden Biases of Flow Matching Samplers","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08318","citing_title":"Is Flow Matching Just Trajectory Replay for Sequential Data?","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2603.20189","citing_title":"Learning Sampled-data Control for Swarms via MeanFlow","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02415","citing_title":"Generative models on phase space","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11485","citing_title":"Coordinated Diffusion: Generating Multi-Agent Behavior Without Multi-Agent Demonstrations","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10076","citing_title":"A Stability Benchmark of Generative Regularizers for Inverse Problems","ref_index":94,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10821","citing_title":"Unified Noise Steering for Efficient Human-Guided VLA Adaptation","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24290","citing_title":"Lattice field theories with a sign problem","ref_index":116,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24290","citing_title":"Lattice field theories with a sign problem","ref_index":116,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23380","citing_title":"V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06583","citing_title":"Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21180","citing_title":"Uncertainty-Aware Spatiotemporal Super-Resolution Data Assimilation with Diffusion Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07661","citing_title":"Stochastic Transition-Map Distillation for Fast Probabilistic Inference","ref_index":180,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14914","citing_title":"Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18839","citing_title":"One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BF6N6YRRSTRRZQKU6BARCV3DMA","json":"https://pith.science/pith/BF6N6YRRSTRRZQKU6BARCV3DMA.json","graph_json":"https://pith.science/api/pith-number/BF6N6YRRSTRRZQKU6BARCV3DMA/graph.json","events_json":"https://pith.science/api/pith-number/BF6N6YRRSTRRZQKU6BARCV3DMA/events.json","paper":"https://pith.science/paper/BF6N6YRR"},"agent_actions":{"view_html":"https://pith.science/pith/BF6N6YRRSTRRZQKU6BARCV3DMA","download_json":"https://pith.science/pith/BF6N6YRRSTRRZQKU6BARCV3DMA.json","view_paper":"https://pith.science/paper/BF6N6YRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.21890&json=true","fetch_graph":"https://pith.science/api/pith-number/BF6N6YRRSTRRZQKU6BARCV3DMA/graph.json","fetch_events":"https://pith.science/api/pith-number/BF6N6YRRSTRRZQKU6BARCV3DMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BF6N6YRRSTRRZQKU6BARCV3DMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BF6N6YRRSTRRZQKU6BARCV3DMA/action/storage_attestation","attest_author":"https://pith.science/pith/BF6N6YRRSTRRZQKU6BARCV3DMA/action/author_attestation","sign_citation":"https://pith.science/pith/BF6N6YRRSTRRZQKU6BARCV3DMA/action/citation_signature","submit_replication":"https://pith.science/pith/BF6N6YRRSTRRZQKU6BARCV3DMA/action/replication_record"}},"created_at":"2026-05-17T23:51:27.729290+00:00","updated_at":"2026-05-17T23:51:27.729290+00:00"}