{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QOE5ACTBNZSG7SSV66ZM45KQST","short_pith_number":"pith:QOE5ACTB","schema_version":"1.0","canonical_sha256":"8389d00a616e646fca55f7b2ce755094c6c020ea369d0a972a10134948cc9798","source":{"kind":"arxiv","id":"2312.14589","version":1},"attestation_state":"computed","paper":{"title":"Non-Denoising Forward-Time Diffusions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Stefano Peluchetti","submitted_at":"2023-12-22T10:26:31Z","abstract_excerpt":"The scope of this paper is generative modeling through diffusion processes. An approach falling within this paradigm is the work of Song et al. (2021), which relies on a time-reversal argument to construct a diffusion process targeting the desired data distribution. We show that the time-reversal argument, common to all denoising diffusion probabilistic modeling proposals, is not necessary. We obtain diffusion processes targeting the desired data distribution by taking appropriate mixtures of diffusion bridges. The resulting transport is exact by construction, allows for greater flexibility in"},"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":"2312.14589","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-22T10:26:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"47a11a154f4416deec6c11d3983fac64bd68bdf00f0ddbc0101a73fbe950c578","abstract_canon_sha256":"e78222a62dffea3391790e6677eacbfbc2d95e7e5dfbb2b62ce70b6cf91c9921"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:17.420615Z","signature_b64":"kViQghjnrmNSSXDVt+C6czsm5i9mxeM4hbv8UxlUh7c30RkNH1i3yJtUqlWIaLu/jSwK0L6BuGBho3VQ0MViCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8389d00a616e646fca55f7b2ce755094c6c020ea369d0a972a10134948cc9798","last_reissued_at":"2026-07-05T07:27:17.420204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:17.420204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Denoising Forward-Time Diffusions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Stefano Peluchetti","submitted_at":"2023-12-22T10:26:31Z","abstract_excerpt":"The scope of this paper is generative modeling through diffusion processes. An approach falling within this paradigm is the work of Song et al. (2021), which relies on a time-reversal argument to construct a diffusion process targeting the desired data distribution. We show that the time-reversal argument, common to all denoising diffusion probabilistic modeling proposals, is not necessary. We obtain diffusion processes targeting the desired data distribution by taking appropriate mixtures of diffusion bridges. The resulting transport is exact by construction, allows for greater flexibility in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14589","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/2312.14589/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":"2312.14589","created_at":"2026-07-05T07:27:17.420260+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.14589v1","created_at":"2026-07-05T07:27:17.420260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14589","created_at":"2026-07-05T07:27:17.420260+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOE5ACTBNZSG","created_at":"2026-07-05T07:27:17.420260+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOE5ACTBNZSG7SSV","created_at":"2026-07-05T07:27:17.420260+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOE5ACTB","created_at":"2026-07-05T07:27:17.420260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12710","citing_title":"A Stabilized Path-Space Approach to Diffusion-Based Posterior Sampling","ref_index":9,"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":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31576","citing_title":"Introduction to Stochastic Differential Equations for Generative Machine Learning: A Variational Perspective","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10989","citing_title":"Variational Optimality of F\\\"ollmer Processes in Generative Diffusions","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14190","citing_title":"Random-Bridges as Stochastic Transports for Generative Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12416","citing_title":"Aligning Flow Map Policies with Optimal Q-Guidance","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06264","citing_title":"Flow Matching Guide and Code","ref_index":61,"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":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08882","citing_title":"Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07661","citing_title":"Stochastic Transition-Map Distillation for Fast Probabilistic Inference","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOE5ACTBNZSG7SSV66ZM45KQST","json":"https://pith.science/pith/QOE5ACTBNZSG7SSV66ZM45KQST.json","graph_json":"https://pith.science/api/pith-number/QOE5ACTBNZSG7SSV66ZM45KQST/graph.json","events_json":"https://pith.science/api/pith-number/QOE5ACTBNZSG7SSV66ZM45KQST/events.json","paper":"https://pith.science/paper/QOE5ACTB"},"agent_actions":{"view_html":"https://pith.science/pith/QOE5ACTBNZSG7SSV66ZM45KQST","download_json":"https://pith.science/pith/QOE5ACTBNZSG7SSV66ZM45KQST.json","view_paper":"https://pith.science/paper/QOE5ACTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.14589&json=true","fetch_graph":"https://pith.science/api/pith-number/QOE5ACTBNZSG7SSV66ZM45KQST/graph.json","fetch_events":"https://pith.science/api/pith-number/QOE5ACTBNZSG7SSV66ZM45KQST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOE5ACTBNZSG7SSV66ZM45KQST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOE5ACTBNZSG7SSV66ZM45KQST/action/storage_attestation","attest_author":"https://pith.science/pith/QOE5ACTBNZSG7SSV66ZM45KQST/action/author_attestation","sign_citation":"https://pith.science/pith/QOE5ACTBNZSG7SSV66ZM45KQST/action/citation_signature","submit_replication":"https://pith.science/pith/QOE5ACTBNZSG7SSV66ZM45KQST/action/replication_record"}},"created_at":"2026-07-05T07:27:17.420260+00:00","updated_at":"2026-07-05T07:27:17.420260+00:00"}