{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H7FKSFSAJNMA3NAYNAOLJCNOX2","short_pith_number":"pith:H7FKSFSA","schema_version":"1.0","canonical_sha256":"3fcaa916404b580db418681cb489aebea870287af20a3815c2852b9cfeb2e9af","source":{"kind":"arxiv","id":"2503.02819","version":2},"attestation_state":"computed","paper":{"title":"Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Al\\'an Aspuru-Guzik, Alexander Tong, Arnaud Doucet, Kirill Neklyudov, Marta Skreta, Rob Brekelmans, Roberto Bondesan, Tara Akhound-Sadegh, Viktor Ohanesian","submitted_at":"2025-03-04T17:46:51Z","abstract_excerpt":"While score-based generative models are the model of choice across diverse domains, there are limited tools available for controlling inference-time behavior in a principled manner, e.g. for composing multiple pretrained models. Existing classifier-free guidance methods use a simple heuristic to mix conditional and unconditional scores to approximately sample from conditional distributions. However, such methods do not approximate the intermediate distributions, necessitating additional `corrector' steps. In this work, we provide an efficient and principled method for sampling from a sequence "},"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":"2503.02819","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-04T17:46:51Z","cross_cats_sorted":[],"title_canon_sha256":"dde20b1c3c201aeb218b3f8e27bea46132f5fd64d427de378678cb872f5b0f17","abstract_canon_sha256":"cf1def8736112d06a37d6cdaa606d6134f5be99d5f917de057dd33873b7bd84b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:42.690070Z","signature_b64":"ZXItNz6xdRq9JEACr3oN4KjljLapshsuPIg5hRxIr0gu5N3QWGwSOc4G7lZOI+q2wdkFynb/Z9/jjktHLuj2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fcaa916404b580db418681cb489aebea870287af20a3815c2852b9cfeb2e9af","last_reissued_at":"2026-07-05T11:17:42.689581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:42.689581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Al\\'an Aspuru-Guzik, Alexander Tong, Arnaud Doucet, Kirill Neklyudov, Marta Skreta, Rob Brekelmans, Roberto Bondesan, Tara Akhound-Sadegh, Viktor Ohanesian","submitted_at":"2025-03-04T17:46:51Z","abstract_excerpt":"While score-based generative models are the model of choice across diverse domains, there are limited tools available for controlling inference-time behavior in a principled manner, e.g. for composing multiple pretrained models. Existing classifier-free guidance methods use a simple heuristic to mix conditional and unconditional scores to approximately sample from conditional distributions. However, such methods do not approximate the intermediate distributions, necessitating additional `corrector' steps. In this work, we provide an efficient and principled method for sampling from a sequence "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02819","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/2503.02819/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":"2503.02819","created_at":"2026-07-05T11:17:42.689636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02819v2","created_at":"2026-07-05T11:17:42.689636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02819","created_at":"2026-07-05T11:17:42.689636+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7FKSFSAJNMA","created_at":"2026-07-05T11:17:42.689636+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7FKSFSAJNMA3NAY","created_at":"2026-07-05T11:17:42.689636+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7FKSFSA","created_at":"2026-07-05T11:17:42.689636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01144","citing_title":"Sequentially-Controlled Interactive Multi-Particle Flow-Maps for Online Feedback-Driven Search","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18745","citing_title":"SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00295","citing_title":"Adaptive Order Policies for Masked Diffusion","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30991","citing_title":"Parallel Tempering Initial Sampling in Inference-Time Reward Alignment","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23346","citing_title":"Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10933","citing_title":"CMAD: Cooperative Multi-Agent Diffusion via Stochastic Optimal Control","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18745","citing_title":"SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate","ref_index":22,"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":18,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25980","citing_title":"A Priori Sampling of Transition States with Guided Diffusion","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07762","citing_title":"Generative optimal transport via forward-backward HJB matching","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21066","citing_title":"Optimizing Diffusion Priors in Image Reconstruction from a Single Observation","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7FKSFSAJNMA3NAYNAOLJCNOX2","json":"https://pith.science/pith/H7FKSFSAJNMA3NAYNAOLJCNOX2.json","graph_json":"https://pith.science/api/pith-number/H7FKSFSAJNMA3NAYNAOLJCNOX2/graph.json","events_json":"https://pith.science/api/pith-number/H7FKSFSAJNMA3NAYNAOLJCNOX2/events.json","paper":"https://pith.science/paper/H7FKSFSA"},"agent_actions":{"view_html":"https://pith.science/pith/H7FKSFSAJNMA3NAYNAOLJCNOX2","download_json":"https://pith.science/pith/H7FKSFSAJNMA3NAYNAOLJCNOX2.json","view_paper":"https://pith.science/paper/H7FKSFSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02819&json=true","fetch_graph":"https://pith.science/api/pith-number/H7FKSFSAJNMA3NAYNAOLJCNOX2/graph.json","fetch_events":"https://pith.science/api/pith-number/H7FKSFSAJNMA3NAYNAOLJCNOX2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7FKSFSAJNMA3NAYNAOLJCNOX2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7FKSFSAJNMA3NAYNAOLJCNOX2/action/storage_attestation","attest_author":"https://pith.science/pith/H7FKSFSAJNMA3NAYNAOLJCNOX2/action/author_attestation","sign_citation":"https://pith.science/pith/H7FKSFSAJNMA3NAYNAOLJCNOX2/action/citation_signature","submit_replication":"https://pith.science/pith/H7FKSFSAJNMA3NAYNAOLJCNOX2/action/replication_record"}},"created_at":"2026-07-05T11:17:42.689636+00:00","updated_at":"2026-07-05T11:17:42.689636+00:00"}