{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LZKXYAL5O4DJEDENTCEMVLTJPA","short_pith_number":"pith:LZKXYAL5","schema_version":"1.0","canonical_sha256":"5e557c017d7706920c8d9888caae697803dc1e0b14f90abb38f3b2c8b3a3a9fc","source":{"kind":"arxiv","id":"2605.18204","version":1},"attestation_state":"computed","paper":{"title":"Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Grigory Bartosh, Javier Zazo, Sushrut Karmalkar, Teodora Pandeva","submitted_at":"2026-05-18T10:43:36Z","abstract_excerpt":"Discrete diffusion models are a powerful class of generative models with strong performance across many domains. For efficiency, however, discrete diffusion typically parameterizes the generative (reverse) process with factorized distributions, which makes it difficult for the model to learn the target process in a small number of steps and necessitates a long, computationally expensive sampling procedure. To reduce the gap between the target and model distributions and enable few-step generation, we propose Forward-Learned Discrete Diffusion (FLDD), which introduces discrete diffusion with a "},"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":"2605.18204","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-18T10:43:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2e62d78afc49e57b5bc2644e64e8c41863f3afab64614febbc8dfc5e774fc17e","abstract_canon_sha256":"e501a4f12e98f9edb2cbec260f5c9a5737b9df46f5fce7d2aca64aab277f9b08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:50.495208Z","signature_b64":"9tEf8GNk13OoQ+R4M8eqXXn5Z5gVuyRzUI8/rgowV+Doz0UiKHvTlqXkIaqOjUIl7tL89o0V0gyXrZ4uyj8mDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e557c017d7706920c8d9888caae697803dc1e0b14f90abb38f3b2c8b3a3a9fc","last_reissued_at":"2026-05-20T00:05:50.494575Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:50.494575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Grigory Bartosh, Javier Zazo, Sushrut Karmalkar, Teodora Pandeva","submitted_at":"2026-05-18T10:43:36Z","abstract_excerpt":"Discrete diffusion models are a powerful class of generative models with strong performance across many domains. For efficiency, however, discrete diffusion typically parameterizes the generative (reverse) process with factorized distributions, which makes it difficult for the model to learn the target process in a small number of steps and necessitates a long, computationally expensive sampling procedure. To reduce the gap between the target and model distributions and enable few-step generation, we propose Forward-Learned Discrete Diffusion (FLDD), which introduces discrete diffusion with a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18204","kind":"arxiv","version":1},"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/2605.18204/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T23:41:58.985898Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.317934Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"53fa3d6590b1426408c6a1d5e3820ca4dc1601b4c4fb2470e93f88762eaef941"},"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":"2605.18204","created_at":"2026-05-20T00:05:50.494672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18204v1","created_at":"2026-05-20T00:05:50.494672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18204","created_at":"2026-05-20T00:05:50.494672+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZKXYAL5O4DJ","created_at":"2026-05-20T00:05:50.494672+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZKXYAL5O4DJEDEN","created_at":"2026-05-20T00:05:50.494672+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZKXYAL5","created_at":"2026-05-20T00:05:50.494672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LZKXYAL5O4DJEDENTCEMVLTJPA","json":"https://pith.science/pith/LZKXYAL5O4DJEDENTCEMVLTJPA.json","graph_json":"https://pith.science/api/pith-number/LZKXYAL5O4DJEDENTCEMVLTJPA/graph.json","events_json":"https://pith.science/api/pith-number/LZKXYAL5O4DJEDENTCEMVLTJPA/events.json","paper":"https://pith.science/paper/LZKXYAL5"},"agent_actions":{"view_html":"https://pith.science/pith/LZKXYAL5O4DJEDENTCEMVLTJPA","download_json":"https://pith.science/pith/LZKXYAL5O4DJEDENTCEMVLTJPA.json","view_paper":"https://pith.science/paper/LZKXYAL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18204&json=true","fetch_graph":"https://pith.science/api/pith-number/LZKXYAL5O4DJEDENTCEMVLTJPA/graph.json","fetch_events":"https://pith.science/api/pith-number/LZKXYAL5O4DJEDENTCEMVLTJPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZKXYAL5O4DJEDENTCEMVLTJPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZKXYAL5O4DJEDENTCEMVLTJPA/action/storage_attestation","attest_author":"https://pith.science/pith/LZKXYAL5O4DJEDENTCEMVLTJPA/action/author_attestation","sign_citation":"https://pith.science/pith/LZKXYAL5O4DJEDENTCEMVLTJPA/action/citation_signature","submit_replication":"https://pith.science/pith/LZKXYAL5O4DJEDENTCEMVLTJPA/action/replication_record"}},"created_at":"2026-05-20T00:05:50.494672+00:00","updated_at":"2026-05-20T00:05:50.494672+00:00"}