{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F5FAH4SFGYJPLEUMWBEE72GONQ","short_pith_number":"pith:F5FAH4SF","schema_version":"1.0","canonical_sha256":"2f4a03f2453612f5928cb0484fe8ce6c3e98104e5fdf0d4d1b6e3b389ff2ab88","source":{"kind":"arxiv","id":"2605.30753","version":1},"attestation_state":"computed","paper":{"title":"Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Li, Emad Barsoum, Ji Liu, Yiqing Huang, Zekai Li, Ziqiong Liu","submitted_at":"2026-05-29T02:29:28Z","abstract_excerpt":"Diffusion-based large language models (dLLMs) support parallel text generation via iterative denoising, yet inference remains latency-heavy because many steps are spent on redundant refinement and repeated remasking of tokens whose final values are already determined. Prior acceleration methods mainly depend on step-local confidence heuristics or fixed schedules, which are sensitive to prompt and task variation and ignore strong positional effects within a sequence. We cast diffusion decoding as a dynamic control problem and show that token-wise denoising trajectories provide the key signal fo"},"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":"2605.30753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T02:29:28Z","cross_cats_sorted":[],"title_canon_sha256":"c3180df1fcacf8c6565bd58c8a6a13dba4cb3b9958cfd43aa7ba5d8598432c26","abstract_canon_sha256":"ff29098756be7e2c547ccf33f93648ec6177db2bccdab82215e12abad90568e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:14.512287Z","signature_b64":"5wpvxenUy0hyKEGi/H8RqLok0I77S42fadWSHWRC51Q7cRbhVAwW2n05vD9ReG3mPstSMGiyQk840iVhd4s0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f4a03f2453612f5928cb0484fe8ce6c3e98104e5fdf0d4d1b6e3b389ff2ab88","last_reissued_at":"2026-06-01T01:03:14.511418Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:14.511418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dong Li, Emad Barsoum, Ji Liu, Yiqing Huang, Zekai Li, Ziqiong Liu","submitted_at":"2026-05-29T02:29:28Z","abstract_excerpt":"Diffusion-based large language models (dLLMs) support parallel text generation via iterative denoising, yet inference remains latency-heavy because many steps are spent on redundant refinement and repeated remasking of tokens whose final values are already determined. Prior acceleration methods mainly depend on step-local confidence heuristics or fixed schedules, which are sensitive to prompt and task variation and ignore strong positional effects within a sequence. We cast diffusion decoding as a dynamic control problem and show that token-wise denoising trajectories provide the key signal fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30753","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/2605.30753/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":"2605.30753","created_at":"2026-06-01T01:03:14.511564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30753v1","created_at":"2026-06-01T01:03:14.511564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30753","created_at":"2026-06-01T01:03:14.511564+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5FAH4SFGYJP","created_at":"2026-06-01T01:03:14.511564+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5FAH4SFGYJPLEUM","created_at":"2026-06-01T01:03:14.511564+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5FAH4SF","created_at":"2026-06-01T01:03:14.511564+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/F5FAH4SFGYJPLEUMWBEE72GONQ","json":"https://pith.science/pith/F5FAH4SFGYJPLEUMWBEE72GONQ.json","graph_json":"https://pith.science/api/pith-number/F5FAH4SFGYJPLEUMWBEE72GONQ/graph.json","events_json":"https://pith.science/api/pith-number/F5FAH4SFGYJPLEUMWBEE72GONQ/events.json","paper":"https://pith.science/paper/F5FAH4SF"},"agent_actions":{"view_html":"https://pith.science/pith/F5FAH4SFGYJPLEUMWBEE72GONQ","download_json":"https://pith.science/pith/F5FAH4SFGYJPLEUMWBEE72GONQ.json","view_paper":"https://pith.science/paper/F5FAH4SF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30753&json=true","fetch_graph":"https://pith.science/api/pith-number/F5FAH4SFGYJPLEUMWBEE72GONQ/graph.json","fetch_events":"https://pith.science/api/pith-number/F5FAH4SFGYJPLEUMWBEE72GONQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5FAH4SFGYJPLEUMWBEE72GONQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5FAH4SFGYJPLEUMWBEE72GONQ/action/storage_attestation","attest_author":"https://pith.science/pith/F5FAH4SFGYJPLEUMWBEE72GONQ/action/author_attestation","sign_citation":"https://pith.science/pith/F5FAH4SFGYJPLEUMWBEE72GONQ/action/citation_signature","submit_replication":"https://pith.science/pith/F5FAH4SFGYJPLEUMWBEE72GONQ/action/replication_record"}},"created_at":"2026-06-01T01:03:14.511564+00:00","updated_at":"2026-06-01T01:03:14.511564+00:00"}