{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C6HPAKS6RDCK2UIWF2SZTZNWOP","short_pith_number":"pith:C6HPAKS6","schema_version":"1.0","canonical_sha256":"178ef02a5e88c4ad51162ea599e5b673f93de694dffdca001b1c5ec71fb29c47","source":{"kind":"arxiv","id":"2502.02305","version":2},"attestation_state":"computed","paper":{"title":"Information-Theoretic Proofs for Diffusion Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Galen Reeves, Henry D. Pfister","submitted_at":"2025-02-04T13:19:21Z","abstract_excerpt":"This paper provides an elementary, self-contained analysis of diffusion-based sampling methods for generative modeling. In contrast to existing approaches that rely on continuous-time processes and then discretize, our treatment works directly with discrete-time stochastic processes and yields precise non-asymptotic convergence guarantees under broad assumptions. The key insight is to couple the sampling process of interest with an idealized comparison process that has an explicit Gaussian-convolution structure. We then leverage simple identities from information theory, including the I-MMSE r"},"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":"2502.02305","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-04T13:19:21Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"a3db6fcef8331c6bfd66f7a9ba85edd6855b4d414c27c8331faf186c94ca0460","abstract_canon_sha256":"41921ee15a5ed61811c12e2f5ea6a958343b9c1a2d2c98bdc268f192ba1d25c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:02.829405Z","signature_b64":"VwMbfczcuM5cTHbkK+/TN9GR6oFdK2Ui3ALtAChnI04f8rY8m7v70o5VA0OvwCh7tA7jW8z0eTsihZkrxcuZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"178ef02a5e88c4ad51162ea599e5b673f93de694dffdca001b1c5ec71fb29c47","last_reissued_at":"2026-07-05T11:26:02.828916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:02.828916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information-Theoretic Proofs for Diffusion Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Galen Reeves, Henry D. Pfister","submitted_at":"2025-02-04T13:19:21Z","abstract_excerpt":"This paper provides an elementary, self-contained analysis of diffusion-based sampling methods for generative modeling. In contrast to existing approaches that rely on continuous-time processes and then discretize, our treatment works directly with discrete-time stochastic processes and yields precise non-asymptotic convergence guarantees under broad assumptions. The key insight is to couple the sampling process of interest with an idealized comparison process that has an explicit Gaussian-convolution structure. We then leverage simple identities from information theory, including the I-MMSE r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02305","kind":"arxiv","version":2},"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/2502.02305/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":"2502.02305","created_at":"2026-07-05T11:26:02.828974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02305v2","created_at":"2026-07-05T11:26:02.828974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02305","created_at":"2026-07-05T11:26:02.828974+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6HPAKS6RDCK","created_at":"2026-07-05T11:26:02.828974+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6HPAKS6RDCK2UIW","created_at":"2026-07-05T11:26:02.828974+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6HPAKS6","created_at":"2026-07-05T11:26:02.828974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6HPAKS6RDCK2UIWF2SZTZNWOP","json":"https://pith.science/pith/C6HPAKS6RDCK2UIWF2SZTZNWOP.json","graph_json":"https://pith.science/api/pith-number/C6HPAKS6RDCK2UIWF2SZTZNWOP/graph.json","events_json":"https://pith.science/api/pith-number/C6HPAKS6RDCK2UIWF2SZTZNWOP/events.json","paper":"https://pith.science/paper/C6HPAKS6"},"agent_actions":{"view_html":"https://pith.science/pith/C6HPAKS6RDCK2UIWF2SZTZNWOP","download_json":"https://pith.science/pith/C6HPAKS6RDCK2UIWF2SZTZNWOP.json","view_paper":"https://pith.science/paper/C6HPAKS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02305&json=true","fetch_graph":"https://pith.science/api/pith-number/C6HPAKS6RDCK2UIWF2SZTZNWOP/graph.json","fetch_events":"https://pith.science/api/pith-number/C6HPAKS6RDCK2UIWF2SZTZNWOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6HPAKS6RDCK2UIWF2SZTZNWOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6HPAKS6RDCK2UIWF2SZTZNWOP/action/storage_attestation","attest_author":"https://pith.science/pith/C6HPAKS6RDCK2UIWF2SZTZNWOP/action/author_attestation","sign_citation":"https://pith.science/pith/C6HPAKS6RDCK2UIWF2SZTZNWOP/action/citation_signature","submit_replication":"https://pith.science/pith/C6HPAKS6RDCK2UIWF2SZTZNWOP/action/replication_record"}},"created_at":"2026-07-05T11:26:02.828974+00:00","updated_at":"2026-07-05T11:26:02.828974+00:00"}