{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FJRF2FEF322BQB7I67T2BCMTV6","short_pith_number":"pith:FJRF2FEF","schema_version":"1.0","canonical_sha256":"2a625d1485deb41807e8f7e7a08993af904783ca47cf7572cc823bf715c9844e","source":{"kind":"arxiv","id":"2602.16169","version":2},"attestation_state":"computed","paper":{"title":"Discrete Stochastic Localization for Non-autoregressive Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Evangelos E. Papalexakis, Greg Ver Steeg, Jiayi Cheng, Longxuan Yu, Partha Thakuria, Rob Brekelmans, Yunshu Wu","submitted_at":"2026-02-18T04:05:40Z","abstract_excerpt":"Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generation. We argue that the bottleneck is not continuity itself, but a representation in which denoising depends on timestep-indexed noise regimes. We introduce \\emph{Discrete Stochastic Localization} (DSL), a continuous-state framework with unit-sphere token embeddings whose Bayes-optimal denoiser is invariant to the nominal signal-to-noise ratio (SNR) under the localization channel. One trained network then supports an en"},"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":"2602.16169","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-18T04:05:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f32051e8cb979e2a912a731bc27d5c130f166ee1aef51e7e3f4c1da64bd9ff63","abstract_canon_sha256":"bb86625d4a1f1edefcadd008797997e3e5f67d4090b0b66b76d2a0ee79e53276"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:18.230723Z","signature_b64":"GwTJxAZOR81or3i0ADwv3PXQv55Eei00oX3AbQ3wLQtJ1/iiJdgZHygiN8KaL1d2buUsNr4BC80qogrJhxQzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a625d1485deb41807e8f7e7a08993af904783ca47cf7572cc823bf715c9844e","last_reissued_at":"2026-05-22T01:03:18.229794Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:18.229794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discrete Stochastic Localization for Non-autoregressive Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Evangelos E. Papalexakis, Greg Ver Steeg, Jiayi Cheng, Longxuan Yu, Partha Thakuria, Rob Brekelmans, Yunshu Wu","submitted_at":"2026-02-18T04:05:40Z","abstract_excerpt":"Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generation. We argue that the bottleneck is not continuity itself, but a representation in which denoising depends on timestep-indexed noise regimes. We introduce \\emph{Discrete Stochastic Localization} (DSL), a continuous-state framework with unit-sphere token embeddings whose Bayes-optimal denoiser is invariant to the nominal signal-to-noise ratio (SNR) under the localization channel. One trained network then supports an en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.16169","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/2602.16169/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":"2602.16169","created_at":"2026-05-22T01:03:18.229905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.16169v2","created_at":"2026-05-22T01:03:18.229905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.16169","created_at":"2026-05-22T01:03:18.229905+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJRF2FEF322B","created_at":"2026-05-22T01:03:18.229905+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJRF2FEF322BQB7I","created_at":"2026-05-22T01:03:18.229905+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJRF2FEF","created_at":"2026-05-22T01:03:18.229905+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/FJRF2FEF322BQB7I67T2BCMTV6","json":"https://pith.science/pith/FJRF2FEF322BQB7I67T2BCMTV6.json","graph_json":"https://pith.science/api/pith-number/FJRF2FEF322BQB7I67T2BCMTV6/graph.json","events_json":"https://pith.science/api/pith-number/FJRF2FEF322BQB7I67T2BCMTV6/events.json","paper":"https://pith.science/paper/FJRF2FEF"},"agent_actions":{"view_html":"https://pith.science/pith/FJRF2FEF322BQB7I67T2BCMTV6","download_json":"https://pith.science/pith/FJRF2FEF322BQB7I67T2BCMTV6.json","view_paper":"https://pith.science/paper/FJRF2FEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.16169&json=true","fetch_graph":"https://pith.science/api/pith-number/FJRF2FEF322BQB7I67T2BCMTV6/graph.json","fetch_events":"https://pith.science/api/pith-number/FJRF2FEF322BQB7I67T2BCMTV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJRF2FEF322BQB7I67T2BCMTV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJRF2FEF322BQB7I67T2BCMTV6/action/storage_attestation","attest_author":"https://pith.science/pith/FJRF2FEF322BQB7I67T2BCMTV6/action/author_attestation","sign_citation":"https://pith.science/pith/FJRF2FEF322BQB7I67T2BCMTV6/action/citation_signature","submit_replication":"https://pith.science/pith/FJRF2FEF322BQB7I67T2BCMTV6/action/replication_record"}},"created_at":"2026-05-22T01:03:18.229905+00:00","updated_at":"2026-05-22T01:03:18.229905+00:00"}