{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O7PXCELZ6KIUD2SEQ3HEJD4FEV","short_pith_number":"pith:O7PXCELZ","schema_version":"1.0","canonical_sha256":"77df711179f29141ea4486ce448f85256f1c5ecfd12e9eedd5769e91df26b9f4","source":{"kind":"arxiv","id":"2410.20587","version":3},"attestation_state":"computed","paper":{"title":"Generator Matching: Generative modeling with arbitrary Markov processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brian Karrer, Itai Gat, Jason Yim, Marton Havasi, Neta Shaul, Peter Holderrieth, Ricky T. Q. Chen, Tommi Jaakkola, Yaron Lipman","submitted_at":"2024-10-27T20:47:29Z","abstract_excerpt":"We introduce Generator Matching, a modality-agnostic framework for generative modeling using arbitrary Markov processes. Generators characterize the infinitesimal evolution of a Markov process, which we leverage for generative modeling in a similar vein to flow matching: we construct conditional generators which generate single data points, then learn to approximate the marginal generator which generates the full data distribution. We show that Generator Matching unifies various generative modeling methods, including diffusion models, flow matching and discrete diffusion models. Furthermore, i"},"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":"2410.20587","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-27T20:47:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78167f7773125a045e62de79279dd4d1153ab90d3e0a5dd152d77e13149591d3","abstract_canon_sha256":"430a410a6b09e3cf0a1183bab564825a4a99fb77c0880b031459b9caa9fd4484"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:41.230057Z","signature_b64":"q5pqFSBvT8lWf3sJn1u3psJIMB2NIuH4+l0hYuuRbkX79sHCB8t4l+0fRwV6WZeRrF8a8NDmCqTlspO+AJ8nAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77df711179f29141ea4486ce448f85256f1c5ecfd12e9eedd5769e91df26b9f4","last_reissued_at":"2026-07-05T10:20:41.229544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:41.229544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generator Matching: Generative modeling with arbitrary Markov processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brian Karrer, Itai Gat, Jason Yim, Marton Havasi, Neta Shaul, Peter Holderrieth, Ricky T. Q. Chen, Tommi Jaakkola, Yaron Lipman","submitted_at":"2024-10-27T20:47:29Z","abstract_excerpt":"We introduce Generator Matching, a modality-agnostic framework for generative modeling using arbitrary Markov processes. Generators characterize the infinitesimal evolution of a Markov process, which we leverage for generative modeling in a similar vein to flow matching: we construct conditional generators which generate single data points, then learn to approximate the marginal generator which generates the full data distribution. We show that Generator Matching unifies various generative modeling methods, including diffusion models, flow matching and discrete diffusion models. Furthermore, i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20587","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/2410.20587/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":"2410.20587","created_at":"2026-07-05T10:20:41.229611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20587v3","created_at":"2026-07-05T10:20:41.229611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20587","created_at":"2026-07-05T10:20:41.229611+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7PXCELZ6KIU","created_at":"2026-07-05T10:20:41.229611+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7PXCELZ6KIUD2SE","created_at":"2026-07-05T10:20:41.229611+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7PXCELZ","created_at":"2026-07-05T10:20:41.229611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17465","citing_title":"Perron--Frobenius Operator Matching for Generative Modeling","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10543","citing_title":"Flexible Flows for Biological Sequence Design","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07239","citing_title":"Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31063","citing_title":"Free energy Estimation on Any State Space","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20210","citing_title":"Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06264","citing_title":"Flow Matching Guide and Code","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08882","citing_title":"Discrete Flow Matching: Convergence Guarantees Under Minimal Assumptions","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7PXCELZ6KIUD2SEQ3HEJD4FEV","json":"https://pith.science/pith/O7PXCELZ6KIUD2SEQ3HEJD4FEV.json","graph_json":"https://pith.science/api/pith-number/O7PXCELZ6KIUD2SEQ3HEJD4FEV/graph.json","events_json":"https://pith.science/api/pith-number/O7PXCELZ6KIUD2SEQ3HEJD4FEV/events.json","paper":"https://pith.science/paper/O7PXCELZ"},"agent_actions":{"view_html":"https://pith.science/pith/O7PXCELZ6KIUD2SEQ3HEJD4FEV","download_json":"https://pith.science/pith/O7PXCELZ6KIUD2SEQ3HEJD4FEV.json","view_paper":"https://pith.science/paper/O7PXCELZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20587&json=true","fetch_graph":"https://pith.science/api/pith-number/O7PXCELZ6KIUD2SEQ3HEJD4FEV/graph.json","fetch_events":"https://pith.science/api/pith-number/O7PXCELZ6KIUD2SEQ3HEJD4FEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7PXCELZ6KIUD2SEQ3HEJD4FEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7PXCELZ6KIUD2SEQ3HEJD4FEV/action/storage_attestation","attest_author":"https://pith.science/pith/O7PXCELZ6KIUD2SEQ3HEJD4FEV/action/author_attestation","sign_citation":"https://pith.science/pith/O7PXCELZ6KIUD2SEQ3HEJD4FEV/action/citation_signature","submit_replication":"https://pith.science/pith/O7PXCELZ6KIUD2SEQ3HEJD4FEV/action/replication_record"}},"created_at":"2026-07-05T10:20:41.229611+00:00","updated_at":"2026-07-05T10:20:41.229611+00:00"}