{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:J4OQHNX355MKIFS2MAN7W6EIJ7","short_pith_number":"pith:J4OQHNX3","schema_version":"1.0","canonical_sha256":"4f1d03b6fbef58a4165a601bfb78884fcedafe29359455bd8b1198de25635541","source":{"kind":"arxiv","id":"2407.15595","version":2},"attestation_state":"computed","paper":{"title":"Discrete Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Felix Kreuk, Gabriel Synnaeve, Itai Gat, Neta Shaul, Ricky T. Q. Chen, Tal Remez, Yaron Lipman, Yossi Adi","submitted_at":"2024-07-22T12:33:27Z","abstract_excerpt":"Despite Flow Matching and diffusion models having emerged as powerful generative paradigms for continuous variables such as images and videos, their application to high-dimensional discrete data, such as language, is still limited. In this work, we present Discrete Flow Matching, a novel discrete flow paradigm designed specifically for generating discrete data. Discrete Flow Matching offers several key contributions:(i) it works with a general family of probability paths interpolating between source and target distributions; (ii) it allows for a generic formula for sampling from these probabil"},"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":"2407.15595","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-22T12:33:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff80c8b8c13ad1ef5cccc87cf45132445e57b68cdcf11a9a34d23610cd35da6b","abstract_canon_sha256":"c73d1c7b7b0ead957f5a990f82db3620a53a20df07a2cf216bd0f1250b435daf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:06.026188Z","signature_b64":"oe8axtZZT0zTN/NO1kHu+88PE6fxnVdtWjPqqLD36SiF+VnUmy9ubj1njwUQCr2tPdnRtcOn3HWNeIYIMA9QAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f1d03b6fbef58a4165a601bfb78884fcedafe29359455bd8b1198de25635541","last_reissued_at":"2026-07-05T09:31:06.025664Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:06.025664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discrete Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Felix Kreuk, Gabriel Synnaeve, Itai Gat, Neta Shaul, Ricky T. Q. Chen, Tal Remez, Yaron Lipman, Yossi Adi","submitted_at":"2024-07-22T12:33:27Z","abstract_excerpt":"Despite Flow Matching and diffusion models having emerged as powerful generative paradigms for continuous variables such as images and videos, their application to high-dimensional discrete data, such as language, is still limited. In this work, we present Discrete Flow Matching, a novel discrete flow paradigm designed specifically for generating discrete data. Discrete Flow Matching offers several key contributions:(i) it works with a general family of probability paths interpolating between source and target distributions; (ii) it allows for a generic formula for sampling from these probabil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15595","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/2407.15595/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":"2407.15595","created_at":"2026-07-05T09:31:06.025727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15595v2","created_at":"2026-07-05T09:31:06.025727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15595","created_at":"2026-07-05T09:31:06.025727+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4OQHNX355MK","created_at":"2026-07-05T09:31:06.025727+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4OQHNX355MKIFS2","created_at":"2026-07-05T09:31:06.025727+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4OQHNX3","created_at":"2026-07-05T09:31:06.025727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27361","citing_title":"Autoregressive Boltzmann Generators","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08417","citing_title":"Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07239","citing_title":"Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27732","citing_title":"Bifocal Diffusion Language Models: Asymmetric Bidirectional Context for Parallel Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19594","citing_title":"Unsupervised Causal Abstractions Discovery","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2411.10618","citing_title":"D-Flow: Multi-modality Flow Matching for D-peptide Design","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19726","citing_title":"Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention","ref_index":14,"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":6,"is_internal_anchor":false},{"citing_arxiv_id":"2511.03015","citing_title":"Discrete Bayesian Sample Inference for Graph Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16933","citing_title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2505.22618","citing_title":"Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2412.06264","citing_title":"Flow Matching Guide and Code","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09992","citing_title":"Large Language Diffusion Models","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J4OQHNX355MKIFS2MAN7W6EIJ7","json":"https://pith.science/pith/J4OQHNX355MKIFS2MAN7W6EIJ7.json","graph_json":"https://pith.science/api/pith-number/J4OQHNX355MKIFS2MAN7W6EIJ7/graph.json","events_json":"https://pith.science/api/pith-number/J4OQHNX355MKIFS2MAN7W6EIJ7/events.json","paper":"https://pith.science/paper/J4OQHNX3"},"agent_actions":{"view_html":"https://pith.science/pith/J4OQHNX355MKIFS2MAN7W6EIJ7","download_json":"https://pith.science/pith/J4OQHNX355MKIFS2MAN7W6EIJ7.json","view_paper":"https://pith.science/paper/J4OQHNX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15595&json=true","fetch_graph":"https://pith.science/api/pith-number/J4OQHNX355MKIFS2MAN7W6EIJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/J4OQHNX355MKIFS2MAN7W6EIJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4OQHNX355MKIFS2MAN7W6EIJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4OQHNX355MKIFS2MAN7W6EIJ7/action/storage_attestation","attest_author":"https://pith.science/pith/J4OQHNX355MKIFS2MAN7W6EIJ7/action/author_attestation","sign_citation":"https://pith.science/pith/J4OQHNX355MKIFS2MAN7W6EIJ7/action/citation_signature","submit_replication":"https://pith.science/pith/J4OQHNX355MKIFS2MAN7W6EIJ7/action/replication_record"}},"created_at":"2026-07-05T09:31:06.025727+00:00","updated_at":"2026-07-05T09:31:06.025727+00:00"}