{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FHKOI2VTXPNIURCLGLXMF2VS7Q","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":"22422466774206bcc3a444e91f3fc1ad054fa065eec2059596cc1c9c43117bc6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T02:47:50Z","title_canon_sha256":"75db09de160feb970103f9dfb130764b9c22faca8e5f71322094f09d9379b6a8"},"schema_version":"1.0","source":{"id":"2606.26120","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26120","created_at":"2026-06-26T00:15:26Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26120v1","created_at":"2026-06-26T00:15:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26120","created_at":"2026-06-26T00:15:26Z"},{"alias_kind":"pith_short_12","alias_value":"FHKOI2VTXPNI","created_at":"2026-06-26T00:15:26Z"},{"alias_kind":"pith_short_16","alias_value":"FHKOI2VTXPNIURCL","created_at":"2026-06-26T00:15:26Z"},{"alias_kind":"pith_short_8","alias_value":"FHKOI2VT","created_at":"2026-06-26T00:15:26Z"}],"graph_snapshots":[{"event_id":"sha256:70ee1d7cf1856c6cf5e2cb611795ee6e5e2753dbdbc5ed2991451765b209bf4c","target":"graph","created_at":"2026-06-26T00:15:26Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.26120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion Large Language Models (dLLMs) offer a promising alternative to autoregressive models, excelling in text generation tasks due to their bidirectional attention mechanisms. However, their computational complexity scales on the order of L cubed with the sequence length L. This poses significant challenges for long-sequence and real-time applications, primarily due to the lack of compatibility with key-value caching and the non-autoregressive nature of denoising steps. Existing acceleration methods rely on static caching or parallel decoding strategies, which fail to account for the dynam","authors_text":"Tianyi Wu, Xiaoxi Sun, Yanhua Jiao, YiQi Hu, Yixin Chen, Yulin Li, Yunhao Cao, Zhuotao Tian","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T02:47:50Z","title":"Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26120","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:48d3148f03ad40cee04a390196935bfda74e5ddb0db8ee46a7a5b6de4199e026","target":"record","created_at":"2026-06-26T00:15:26Z","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":"22422466774206bcc3a444e91f3fc1ad054fa065eec2059596cc1c9c43117bc6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T02:47:50Z","title_canon_sha256":"75db09de160feb970103f9dfb130764b9c22faca8e5f71322094f09d9379b6a8"},"schema_version":"1.0","source":{"id":"2606.26120","kind":"arxiv","version":1}},"canonical_sha256":"29d4e46ab3bbda8a444b32eec2eab2fc20301ff80434919ff05eb03ef676e283","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29d4e46ab3bbda8a444b32eec2eab2fc20301ff80434919ff05eb03ef676e283","first_computed_at":"2026-06-26T00:15:26.731161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T00:15:26.731161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p6e/SgtDp5hAqnNe6rHf/RyQ+E+K2Wi3UFLkCD2VpUC1ypCPUXFyIV9nxaTOXM8BOS6vfdHnJ3pCAETyx1aRAg==","signature_status":"signed_v1","signed_at":"2026-06-26T00:15:26.731573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26120","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48d3148f03ad40cee04a390196935bfda74e5ddb0db8ee46a7a5b6de4199e026","sha256:70ee1d7cf1856c6cf5e2cb611795ee6e5e2753dbdbc5ed2991451765b209bf4c"],"state_sha256":"fefd30f6f48c3bba615c7e0133cabbb0e8dd2a5cac45c98029950e0ae041eb44"}