{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RR5ODKUTPQSVA42OD5VPJO2NGP","short_pith_number":"pith:RR5ODKUT","schema_version":"1.0","canonical_sha256":"8c7ae1aa937c2550734e1f6af4bb4d33e066201114256db2ec9a85a85f66297f","source":{"kind":"arxiv","id":"2606.10537","version":1},"attestation_state":"computed","paper":{"title":"Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaofan Tao, Chengyue Wu, Chenyang Zhao, Jing Xiong, Ngai Wong, Qi Han, Shansan Gong, Yunta Hsieh","submitted_at":"2026-06-09T08:06:22Z","abstract_excerpt":"Diffusion large language models (dLLMs) re-encode the entire prefix at every denoising step, causing recomputation that scales\n  quadratically with context length and becomes prohibitive for long-context scenarios. We propose Prefilling-dLLM, a training-free\n  prefill-decode disaggregation framework for dLLMs that partitions the prefix into N chunks, caches their KV representations once,\n  and selects the top-K most relevant chunks with intra-chunk token sparsity for decoding, showing that sparse prefilling can\n  outperform dense attention while reducing per-step complexity from quadratic in t"},"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":"2606.10537","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T08:06:22Z","cross_cats_sorted":[],"title_canon_sha256":"bd884fd51073c8d0b038392e13397b98ab46071fcebfafc0c298a035ce18fc3b","abstract_canon_sha256":"c3b7585f0b001e9ae44346e6ce32c535a32e14ed88489910b3d49497942816b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:25.016442Z","signature_b64":"8Lj9KRRqG01+cXagr4tRZFyv/YebgklRCjX9xQfiaTuE8aD0F7FH7ueRmARnfhq2Z2A/dml5QXC/opX4L9moCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c7ae1aa937c2550734e1f6af4bb4d33e066201114256db2ec9a85a85f66297f","last_reissued_at":"2026-06-10T01:10:25.015577Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:25.015577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaofan Tao, Chengyue Wu, Chenyang Zhao, Jing Xiong, Ngai Wong, Qi Han, Shansan Gong, Yunta Hsieh","submitted_at":"2026-06-09T08:06:22Z","abstract_excerpt":"Diffusion large language models (dLLMs) re-encode the entire prefix at every denoising step, causing recomputation that scales\n  quadratically with context length and becomes prohibitive for long-context scenarios. We propose Prefilling-dLLM, a training-free\n  prefill-decode disaggregation framework for dLLMs that partitions the prefix into N chunks, caches their KV representations once,\n  and selects the top-K most relevant chunks with intra-chunk token sparsity for decoding, showing that sparse prefilling can\n  outperform dense attention while reducing per-step complexity from quadratic in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10537","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/2606.10537/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":"2606.10537","created_at":"2026-06-10T01:10:25.015717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10537v1","created_at":"2026-06-10T01:10:25.015717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10537","created_at":"2026-06-10T01:10:25.015717+00:00"},{"alias_kind":"pith_short_12","alias_value":"RR5ODKUTPQSV","created_at":"2026-06-10T01:10:25.015717+00:00"},{"alias_kind":"pith_short_16","alias_value":"RR5ODKUTPQSVA42O","created_at":"2026-06-10T01:10:25.015717+00:00"},{"alias_kind":"pith_short_8","alias_value":"RR5ODKUT","created_at":"2026-06-10T01:10:25.015717+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/RR5ODKUTPQSVA42OD5VPJO2NGP","json":"https://pith.science/pith/RR5ODKUTPQSVA42OD5VPJO2NGP.json","graph_json":"https://pith.science/api/pith-number/RR5ODKUTPQSVA42OD5VPJO2NGP/graph.json","events_json":"https://pith.science/api/pith-number/RR5ODKUTPQSVA42OD5VPJO2NGP/events.json","paper":"https://pith.science/paper/RR5ODKUT"},"agent_actions":{"view_html":"https://pith.science/pith/RR5ODKUTPQSVA42OD5VPJO2NGP","download_json":"https://pith.science/pith/RR5ODKUTPQSVA42OD5VPJO2NGP.json","view_paper":"https://pith.science/paper/RR5ODKUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10537&json=true","fetch_graph":"https://pith.science/api/pith-number/RR5ODKUTPQSVA42OD5VPJO2NGP/graph.json","fetch_events":"https://pith.science/api/pith-number/RR5ODKUTPQSVA42OD5VPJO2NGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RR5ODKUTPQSVA42OD5VPJO2NGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RR5ODKUTPQSVA42OD5VPJO2NGP/action/storage_attestation","attest_author":"https://pith.science/pith/RR5ODKUTPQSVA42OD5VPJO2NGP/action/author_attestation","sign_citation":"https://pith.science/pith/RR5ODKUTPQSVA42OD5VPJO2NGP/action/citation_signature","submit_replication":"https://pith.science/pith/RR5ODKUTPQSVA42OD5VPJO2NGP/action/replication_record"}},"created_at":"2026-06-10T01:10:25.015717+00:00","updated_at":"2026-06-10T01:10:25.015717+00:00"}