{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QJ27HOLPDZM4WIFXIFF5K54BBZ","short_pith_number":"pith:QJ27HOLP","schema_version":"1.0","canonical_sha256":"8275f3b96f1e59cb20b7414bd577810e59c50982909d6efa70deeec7a8b0e7d3","source":{"kind":"arxiv","id":"2406.01572","version":4},"attestation_state":"computed","paper":{"title":"Unlocking Guidance for Discrete State-Space Diffusion and Flow Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hunter Nisonoff, Jennifer Listgarten, Junhao Xiong, Stephan Allenspach","submitted_at":"2024-06-03T17:51:54Z","abstract_excerpt":"Generative models on discrete state-spaces have a wide range of potential applications, particularly in the domain of natural sciences. In continuous state-spaces, controllable and flexible generation of samples with desired properties has been realized using guidance on diffusion and flow models. However, these guidance approaches are not readily amenable to discrete state-space models. Consequently, we introduce a general and principled method for applying guidance on such models. Our method depends on leveraging continuous-time Markov processes on discrete state-spaces, which unlocks comput"},"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":"2406.01572","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-03T17:51:54Z","cross_cats_sorted":[],"title_canon_sha256":"29f555f6c2002f7437322eb95b98571744a9fb480b8f779539899483c841d14e","abstract_canon_sha256":"ff6c9e1ab59f6d24147df896979ecb5c95a193db696378b919b97b1a7d2a644f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:19.263158Z","signature_b64":"3GapFCWRurx9O5N1xII24ICX0+/gcI2dNv8ZYOrorq6lIjcOtMYBw7ZCEmL1eTsPrI8HnkaFuT8bC9PifmnWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8275f3b96f1e59cb20b7414bd577810e59c50982909d6efa70deeec7a8b0e7d3","last_reissued_at":"2026-07-05T10:39:19.262709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:19.262709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking Guidance for Discrete State-Space Diffusion and Flow Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hunter Nisonoff, Jennifer Listgarten, Junhao Xiong, Stephan Allenspach","submitted_at":"2024-06-03T17:51:54Z","abstract_excerpt":"Generative models on discrete state-spaces have a wide range of potential applications, particularly in the domain of natural sciences. In continuous state-spaces, controllable and flexible generation of samples with desired properties has been realized using guidance on diffusion and flow models. However, these guidance approaches are not readily amenable to discrete state-space models. Consequently, we introduce a general and principled method for applying guidance on such models. Our method depends on leveraging continuous-time Markov processes on discrete state-spaces, which unlocks comput"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01572","kind":"arxiv","version":4},"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/2406.01572/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":"2406.01572","created_at":"2026-07-05T10:39:19.262762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01572v4","created_at":"2026-07-05T10:39:19.262762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01572","created_at":"2026-07-05T10:39:19.262762+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJ27HOLPDZM4","created_at":"2026-07-05T10:39:19.262762+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJ27HOLPDZM4WIFX","created_at":"2026-07-05T10:39:19.262762+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJ27HOLP","created_at":"2026-07-05T10:39:19.262762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01693","citing_title":"A Mathematical Introduction to Diffusion Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10543","citing_title":"Flexible Flows for Biological Sequence Design","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02241","citing_title":"BlockGen: Flexible Blockwise Sequence Modeling with Hybrid Samplers","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11125","citing_title":"Language Modeling with Hyperspherical Flows","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00295","citing_title":"Adaptive Order Policies for Masked Diffusion","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23346","citing_title":"Contrastive Distribution Matching for Amortized Sequential Monte Carlo in Discrete Diffusion","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22963","citing_title":"Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11125","citing_title":"Language Modeling with Hyperspherical Flows","ref_index":62,"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":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11125","citing_title":"Language Modeling with Hyperspherical Flows","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00360","citing_title":"Binomial flows: Denoising and flow matching for discrete ordinal data","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17310","citing_title":"Interpolating Discrete Diffusion Models with Controllable Resampling","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QJ27HOLPDZM4WIFXIFF5K54BBZ","json":"https://pith.science/pith/QJ27HOLPDZM4WIFXIFF5K54BBZ.json","graph_json":"https://pith.science/api/pith-number/QJ27HOLPDZM4WIFXIFF5K54BBZ/graph.json","events_json":"https://pith.science/api/pith-number/QJ27HOLPDZM4WIFXIFF5K54BBZ/events.json","paper":"https://pith.science/paper/QJ27HOLP"},"agent_actions":{"view_html":"https://pith.science/pith/QJ27HOLPDZM4WIFXIFF5K54BBZ","download_json":"https://pith.science/pith/QJ27HOLPDZM4WIFXIFF5K54BBZ.json","view_paper":"https://pith.science/paper/QJ27HOLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01572&json=true","fetch_graph":"https://pith.science/api/pith-number/QJ27HOLPDZM4WIFXIFF5K54BBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/QJ27HOLPDZM4WIFXIFF5K54BBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJ27HOLPDZM4WIFXIFF5K54BBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJ27HOLPDZM4WIFXIFF5K54BBZ/action/storage_attestation","attest_author":"https://pith.science/pith/QJ27HOLPDZM4WIFXIFF5K54BBZ/action/author_attestation","sign_citation":"https://pith.science/pith/QJ27HOLPDZM4WIFXIFF5K54BBZ/action/citation_signature","submit_replication":"https://pith.science/pith/QJ27HOLPDZM4WIFXIFF5K54BBZ/action/replication_record"}},"created_at":"2026-07-05T10:39:19.262762+00:00","updated_at":"2026-07-05T10:39:19.262762+00:00"}