{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BTT26H53S5CHOTCCLFFKY2PSXC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ee4131df89e827e58acc2c2dd5262bbc9d93f6c405a3ea3d7dd13344728ed9ab","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T17:43:40Z","title_canon_sha256":"9b40e1aacce6ca5e6225bfb376e1eeb9416502edb782bc9350072db557806efa"},"schema_version":"1.0","source":{"id":"2503.09573","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09573","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09573v3","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09573","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"BTT26H53S5CH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"BTT26H53S5CHOTCC","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"BTT26H53","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:4de56a638b09283cab2fc8ded76e8adc54322535517ab950b1434a73cb9a1444","target":"graph","created_at":"2026-05-17T23:38:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Block diffusion sets a new state-of-the-art performance among diffusion models on language modeling benchmarks and enables generation of arbitrary-length sequences."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the proposed training algorithm, estimators of gradient variance, and data-driven noise schedules will produce stable and effective models that generalize beyond the training data without hidden instabilities or overfitting."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Block diffusion language models interpolate between autoregressive and diffusion models to support flexible-length generation and achieve state-of-the-art performance among diffusion models."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Block diffusion language models interpolate between autoregressive and diffusion approaches to support arbitrary-length generation."}],"snapshot_sha256":"d8d2c38f29f42a19534692b11e3fbc296219ddb7aa85975d74a2d57a4b7032c9"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"83b5fdca3750b24655294c819078d4126181615e16a6e578dcf11a9646ec8cb7"},"paper":{"abstract_excerpt":"Diffusion language models offer unique benefits over autoregressive models due to their potential for parallelized generation and controllability, yet they lag in likelihood modeling and are limited to fixed-length generation. In this work, we introduce a class of block diffusion language models that interpolate between discrete denoising diffusion and autoregressive models. Block diffusion overcomes key limitations of both approaches by supporting flexible-length generation and improving inference efficiency with KV caching and parallel token sampling. We propose a recipe for building effecti","authors_text":"Aaron Gokaslan, Jiaqi Han, Justin T. Chiu, Marianne Arriola, Subham Sekhar Sahoo, Volodymyr Kuleshov, Zhihan Yang, Zhixuan Qi","cross_cats":["cs.AI"],"headline":"Block diffusion language models interpolate between autoregressive and diffusion approaches to support arbitrary-length generation.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T17:43:40Z","title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09573","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T10:53:58.246957Z","id":"de29bb41-2ce2-426c-89e5-052e5d87aada","model_set":{"reader":"grok-4.3"},"one_line_summary":"Block diffusion language models interpolate between autoregressive and diffusion models to support flexible-length generation and achieve state-of-the-art performance among diffusion models.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Block diffusion language models interpolate between autoregressive and diffusion approaches to support arbitrary-length generation.","strongest_claim":"Block diffusion sets a new state-of-the-art performance among diffusion models on language modeling benchmarks and enables generation of arbitrary-length sequences.","weakest_assumption":"The assumption that the proposed training algorithm, estimators of gradient variance, and data-driven noise schedules will produce stable and effective models that generalize beyond the training data without hidden instabilities or overfitting."}},"verdict_id":"de29bb41-2ce2-426c-89e5-052e5d87aada"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:994820e3968fc359a361943deeb2786f5c4a313cd33189611a169bbd88c94e48","target":"record","created_at":"2026-05-17T23:38:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ee4131df89e827e58acc2c2dd5262bbc9d93f6c405a3ea3d7dd13344728ed9ab","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T17:43:40Z","title_canon_sha256":"9b40e1aacce6ca5e6225bfb376e1eeb9416502edb782bc9350072db557806efa"},"schema_version":"1.0","source":{"id":"2503.09573","kind":"arxiv","version":3}},"canonical_sha256":"0ce7af1fbb9744774c42594aac69f2b8aaceb5070c5b144a53b2c43179d12287","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ce7af1fbb9744774c42594aac69f2b8aaceb5070c5b144a53b2c43179d12287","first_computed_at":"2026-05-17T23:38:52.722376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:52.722376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uNgYRic0Ih/Nx0GXZM9xvo+5L8WsJ5X4IiSwxxhOVywFbaX5g/VTvUzR/Y919Zj/7mdAx3Q62qiwyABzEMUYAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:52.723027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.09573","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:994820e3968fc359a361943deeb2786f5c4a313cd33189611a169bbd88c94e48","sha256:4de56a638b09283cab2fc8ded76e8adc54322535517ab950b1434a73cb9a1444"],"state_sha256":"577d4c5aaca7db606711ae70a7afdf965fed1ef4b65e84976cec33cfa4cd3055"}