{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NPHUYEC7KC5CWDEDWYKOOF3LWO","short_pith_number":"pith:NPHUYEC7","schema_version":"1.0","canonical_sha256":"6bcf4c105f50ba2b0c83b614e7176bb381fc493d52429701f07c145d7a064a08","source":{"kind":"arxiv","id":"2502.06079","version":3},"attestation_state":"computed","paper":{"title":"Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlo","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheuk Kit Lee, Francisco Vargas, Jes Frellsen, Michael Samuel Albergo, Paul Jeha, Pietro Lio","submitted_at":"2025-02-10T00:27:54Z","abstract_excerpt":"Discrete diffusion models are a class of generative models that produce samples from an approximated data distribution within a discrete state space. Often, there is a need to target specific regions of the data distribution. Current guidance methods aim to sample from a distribution with mass proportional to $p_0(x_0) p(\\zeta|x_0)^\\alpha$ but fail to achieve this in practice. We introduce a Sequential Monte Carlo algorithm that generates unbiasedly from this target distribution, utilising the learnt unconditional and guided process. We validate our approach on low-dimensional distributions, c"},"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":"2502.06079","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T00:27:54Z","cross_cats_sorted":[],"title_canon_sha256":"86c9268b5a36b25f66df14f3c1088825393a7df88d5b63fff7e8cce40eed5d29","abstract_canon_sha256":"25606ba73a64f5a936f7b1ddf30c8325798fde8dfeca4908bd802e5e3bca298a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:40.477740Z","signature_b64":"kA5ydvTF1t+M84jSThDyBN+LVhceYCuk5mMbPViSmtjaVyV4hhGnsYxJIcWBDhGoOP3lRLkJ9eZjXQJ5XyJbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bcf4c105f50ba2b0c83b614e7176bb381fc493d52429701f07c145d7a064a08","last_reissued_at":"2026-07-05T12:02:40.477269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:40.477269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlo","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheuk Kit Lee, Francisco Vargas, Jes Frellsen, Michael Samuel Albergo, Paul Jeha, Pietro Lio","submitted_at":"2025-02-10T00:27:54Z","abstract_excerpt":"Discrete diffusion models are a class of generative models that produce samples from an approximated data distribution within a discrete state space. Often, there is a need to target specific regions of the data distribution. Current guidance methods aim to sample from a distribution with mass proportional to $p_0(x_0) p(\\zeta|x_0)^\\alpha$ but fail to achieve this in practice. We introduce a Sequential Monte Carlo algorithm that generates unbiasedly from this target distribution, utilising the learnt unconditional and guided process. We validate our approach on low-dimensional distributions, c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06079","kind":"arxiv","version":3},"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/2502.06079/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":"2502.06079","created_at":"2026-07-05T12:02:40.477321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06079v3","created_at":"2026-07-05T12:02:40.477321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06079","created_at":"2026-07-05T12:02:40.477321+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPHUYEC7KC5C","created_at":"2026-07-05T12:02:40.477321+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPHUYEC7KC5CWDED","created_at":"2026-07-05T12:02:40.477321+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPHUYEC7","created_at":"2026-07-05T12:02:40.477321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"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":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00295","citing_title":"Adaptive Order Policies for Masked Diffusion","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23346","citing_title":"Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion","ref_index":41,"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":78,"is_internal_anchor":false},{"citing_arxiv_id":"2510.12916","citing_title":"Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01373","citing_title":"Focus on the Core: Empowering Diffusion Large Language Models by Self-Contrast","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPHUYEC7KC5CWDEDWYKOOF3LWO","json":"https://pith.science/pith/NPHUYEC7KC5CWDEDWYKOOF3LWO.json","graph_json":"https://pith.science/api/pith-number/NPHUYEC7KC5CWDEDWYKOOF3LWO/graph.json","events_json":"https://pith.science/api/pith-number/NPHUYEC7KC5CWDEDWYKOOF3LWO/events.json","paper":"https://pith.science/paper/NPHUYEC7"},"agent_actions":{"view_html":"https://pith.science/pith/NPHUYEC7KC5CWDEDWYKOOF3LWO","download_json":"https://pith.science/pith/NPHUYEC7KC5CWDEDWYKOOF3LWO.json","view_paper":"https://pith.science/paper/NPHUYEC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06079&json=true","fetch_graph":"https://pith.science/api/pith-number/NPHUYEC7KC5CWDEDWYKOOF3LWO/graph.json","fetch_events":"https://pith.science/api/pith-number/NPHUYEC7KC5CWDEDWYKOOF3LWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPHUYEC7KC5CWDEDWYKOOF3LWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPHUYEC7KC5CWDEDWYKOOF3LWO/action/storage_attestation","attest_author":"https://pith.science/pith/NPHUYEC7KC5CWDEDWYKOOF3LWO/action/author_attestation","sign_citation":"https://pith.science/pith/NPHUYEC7KC5CWDEDWYKOOF3LWO/action/citation_signature","submit_replication":"https://pith.science/pith/NPHUYEC7KC5CWDEDWYKOOF3LWO/action/replication_record"}},"created_at":"2026-07-05T12:02:40.477321+00:00","updated_at":"2026-07-05T12:02:40.477321+00:00"}