{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:I3EQA4UODDVIZADJOEGIQF42PJ","short_pith_number":"pith:I3EQA4UO","schema_version":"1.0","canonical_sha256":"46c900728e18ea8c8069710c88179a7a69539f4d98b9099a085316fcbd2ac320","source":{"kind":"arxiv","id":"2208.14699","version":1},"attestation_state":"computed","paper":{"title":"Let us Build Bridges: Understanding and Extending Diffusion Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Lemeng Wu, Mao Ye, Qiang Liu, Xingchao Liu","submitted_at":"2022-08-31T08:58:10Z","abstract_excerpt":"Diffusion-based generative models have achieved promising results recently, but raise an array of open questions in terms of conceptual understanding, theoretical analysis, algorithm improvement and extensions to discrete, structured, non-Euclidean domains. This work tries to re-exam the overall framework, in order to gain better theoretical understandings and develop algorithmic extensions for data from arbitrary domains. By viewing diffusion models as latent variable models with unobserved diffusion trajectories and applying maximum likelihood estimation (MLE) with latent trajectories impute"},"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":"2208.14699","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-31T08:58:10Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5b67a75b2e388f17e48c01404ba1f8b83eb26174cbfbb459ece8b328d9b4753a","abstract_canon_sha256":"8186d8d2e86d76f7f05d9c3c77ebee98ee84652b8894c3f69f7def0ace3613b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:33.557076Z","signature_b64":"Ni0Mi2or8stkBLBp1xktTZqGEvAheCqX+UkpXKQtXhvOXXtoXVGUaVijO2+gV3MRwwoo9YIyWT05n4+JWteBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46c900728e18ea8c8069710c88179a7a69539f4d98b9099a085316fcbd2ac320","last_reissued_at":"2026-07-05T04:53:33.556616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:33.556616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Let us Build Bridges: Understanding and Extending Diffusion Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Lemeng Wu, Mao Ye, Qiang Liu, Xingchao Liu","submitted_at":"2022-08-31T08:58:10Z","abstract_excerpt":"Diffusion-based generative models have achieved promising results recently, but raise an array of open questions in terms of conceptual understanding, theoretical analysis, algorithm improvement and extensions to discrete, structured, non-Euclidean domains. This work tries to re-exam the overall framework, in order to gain better theoretical understandings and develop algorithmic extensions for data from arbitrary domains. By viewing diffusion models as latent variable models with unobserved diffusion trajectories and applying maximum likelihood estimation (MLE) with latent trajectories impute"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.14699","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/2208.14699/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":"2208.14699","created_at":"2026-07-05T04:53:33.556674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.14699v1","created_at":"2026-07-05T04:53:33.556674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.14699","created_at":"2026-07-05T04:53:33.556674+00:00"},{"alias_kind":"pith_short_12","alias_value":"I3EQA4UODDVI","created_at":"2026-07-05T04:53:33.556674+00:00"},{"alias_kind":"pith_short_16","alias_value":"I3EQA4UODDVIZADJ","created_at":"2026-07-05T04:53:33.556674+00:00"},{"alias_kind":"pith_short_8","alias_value":"I3EQA4UO","created_at":"2026-07-05T04:53:33.556674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22630","citing_title":"Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30053","citing_title":"Notes on generative modeling: flow matching, diffusion, optimal transport and Schr{\\\"o}dinger bridge","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21911","citing_title":"Noise Schedule Design for Diffusion Models: An Optimal Control Perspective","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2209.14577","citing_title":"Rectified Flow: A Marginal Preserving Approach to Optimal Transport","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27443","citing_title":"ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2303.08797","citing_title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05673","citing_title":"Rectified Schr\\\"odinger Bridge Matching for Few-Step Visual Navigation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2209.03003","citing_title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I3EQA4UODDVIZADJOEGIQF42PJ","json":"https://pith.science/pith/I3EQA4UODDVIZADJOEGIQF42PJ.json","graph_json":"https://pith.science/api/pith-number/I3EQA4UODDVIZADJOEGIQF42PJ/graph.json","events_json":"https://pith.science/api/pith-number/I3EQA4UODDVIZADJOEGIQF42PJ/events.json","paper":"https://pith.science/paper/I3EQA4UO"},"agent_actions":{"view_html":"https://pith.science/pith/I3EQA4UODDVIZADJOEGIQF42PJ","download_json":"https://pith.science/pith/I3EQA4UODDVIZADJOEGIQF42PJ.json","view_paper":"https://pith.science/paper/I3EQA4UO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.14699&json=true","fetch_graph":"https://pith.science/api/pith-number/I3EQA4UODDVIZADJOEGIQF42PJ/graph.json","fetch_events":"https://pith.science/api/pith-number/I3EQA4UODDVIZADJOEGIQF42PJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I3EQA4UODDVIZADJOEGIQF42PJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I3EQA4UODDVIZADJOEGIQF42PJ/action/storage_attestation","attest_author":"https://pith.science/pith/I3EQA4UODDVIZADJOEGIQF42PJ/action/author_attestation","sign_citation":"https://pith.science/pith/I3EQA4UODDVIZADJOEGIQF42PJ/action/citation_signature","submit_replication":"https://pith.science/pith/I3EQA4UODDVIZADJOEGIQF42PJ/action/replication_record"}},"created_at":"2026-07-05T04:53:33.556674+00:00","updated_at":"2026-07-05T04:53:33.556674+00:00"}