{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K3TRWS6CEYFECTFO4LJSYCD4BE","short_pith_number":"pith:K3TRWS6C","schema_version":"1.0","canonical_sha256":"56e71b4bc2260a414caee2d32c087c093069f06d56b250d493f868d106a73093","source":{"kind":"arxiv","id":"2306.17775","version":2},"attestation_state":"computed","paper":{"title":"Practical and Asymptotically Exact Conditional Sampling in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"stat.ML","authors_text":"Brian L. Trippe, Christian A. Naesseth, David M. Blei, John P. Cunningham, Luhuan Wu","submitted_at":"2023-06-30T16:29:44Z","abstract_excerpt":"Diffusion models have been successful on a range of conditional generation tasks including molecular design and text-to-image generation. However, these achievements have primarily depended on task-specific conditional training or error-prone heuristic approximations. Ideally, a conditional generation method should provide exact samples for a broad range of conditional distributions without requiring task-specific training. To this end, we introduce the Twisted Diffusion Sampler, or TDS. TDS is a sequential Monte Carlo (SMC) algorithm that targets the conditional distributions of diffusion mod"},"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":"2306.17775","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-06-30T16:29:44Z","cross_cats_sorted":["cs.LG","q-bio.BM"],"title_canon_sha256":"7b80ad8aae94ff28b30cae066ba856d6953692b8691b521e818e202cabc87f1e","abstract_canon_sha256":"4ce4eb81a126b559d1f25560e76257976a07b54d74f2067df78bebfaafcdd4b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:19.157681Z","signature_b64":"KlPSydJev7SiFi2L1ET1kTPL/LiNru1H489jESh7kKM9uBXp0mgdAH84/qbVsAf3zMXPZkxaHZ6ZqT7DhvZbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56e71b4bc2260a414caee2d32c087c093069f06d56b250d493f868d106a73093","last_reissued_at":"2026-07-05T09:39:19.157203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:19.157203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Practical and Asymptotically Exact Conditional Sampling in Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"stat.ML","authors_text":"Brian L. Trippe, Christian A. Naesseth, David M. Blei, John P. Cunningham, Luhuan Wu","submitted_at":"2023-06-30T16:29:44Z","abstract_excerpt":"Diffusion models have been successful on a range of conditional generation tasks including molecular design and text-to-image generation. However, these achievements have primarily depended on task-specific conditional training or error-prone heuristic approximations. Ideally, a conditional generation method should provide exact samples for a broad range of conditional distributions without requiring task-specific training. To this end, we introduce the Twisted Diffusion Sampler, or TDS. TDS is a sequential Monte Carlo (SMC) algorithm that targets the conditional distributions of diffusion mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17775","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/2306.17775/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":"2306.17775","created_at":"2026-07-05T09:39:19.157262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.17775v2","created_at":"2026-07-05T09:39:19.157262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17775","created_at":"2026-07-05T09:39:19.157262+00:00"},{"alias_kind":"pith_short_12","alias_value":"K3TRWS6CEYFE","created_at":"2026-07-05T09:39:19.157262+00:00"},{"alias_kind":"pith_short_16","alias_value":"K3TRWS6CEYFECTFO","created_at":"2026-07-05T09:39:19.157262+00:00"},{"alias_kind":"pith_short_8","alias_value":"K3TRWS6C","created_at":"2026-07-05T09:39:19.157262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27361","citing_title":"Autoregressive Boltzmann Generators","ref_index":297,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21395","citing_title":"Atomistic Language Models Understand and Generate Materials","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01693","citing_title":"A Mathematical Introduction to Diffusion Models","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10302","citing_title":"Follow the Mean: Reference-Guided Flow Matching","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17850","citing_title":"Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2511.09216","citing_title":"Controllable protein design with particle-based Feynman-Kac steering","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10302","citing_title":"Follow the Mean: Reference-Guided Flow Matching","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03712","citing_title":"Tempered Guided Diffusion","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10302","citing_title":"Follow the Mean: Reference-Guided Flow Matching","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K3TRWS6CEYFECTFO4LJSYCD4BE","json":"https://pith.science/pith/K3TRWS6CEYFECTFO4LJSYCD4BE.json","graph_json":"https://pith.science/api/pith-number/K3TRWS6CEYFECTFO4LJSYCD4BE/graph.json","events_json":"https://pith.science/api/pith-number/K3TRWS6CEYFECTFO4LJSYCD4BE/events.json","paper":"https://pith.science/paper/K3TRWS6C"},"agent_actions":{"view_html":"https://pith.science/pith/K3TRWS6CEYFECTFO4LJSYCD4BE","download_json":"https://pith.science/pith/K3TRWS6CEYFECTFO4LJSYCD4BE.json","view_paper":"https://pith.science/paper/K3TRWS6C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.17775&json=true","fetch_graph":"https://pith.science/api/pith-number/K3TRWS6CEYFECTFO4LJSYCD4BE/graph.json","fetch_events":"https://pith.science/api/pith-number/K3TRWS6CEYFECTFO4LJSYCD4BE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K3TRWS6CEYFECTFO4LJSYCD4BE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K3TRWS6CEYFECTFO4LJSYCD4BE/action/storage_attestation","attest_author":"https://pith.science/pith/K3TRWS6CEYFECTFO4LJSYCD4BE/action/author_attestation","sign_citation":"https://pith.science/pith/K3TRWS6CEYFECTFO4LJSYCD4BE/action/citation_signature","submit_replication":"https://pith.science/pith/K3TRWS6CEYFECTFO4LJSYCD4BE/action/replication_record"}},"created_at":"2026-07-05T09:39:19.157262+00:00","updated_at":"2026-07-05T09:39:19.157262+00:00"}