{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TGEUAZG5IJ57PRWXFLR3VOAVQU","short_pith_number":"pith:TGEUAZG5","schema_version":"1.0","canonical_sha256":"99894064dd427bf7c6d72ae3bab8158509c56fa698cf1afa58f5d667b851932e","source":{"kind":"arxiv","id":"2605.29707","version":1},"attestation_state":"computed","paper":{"title":"Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanlin Xu, Hao Lin, Jianuo Huang, Linfeng Zhang, Qituan Zhang, Yaojie Zhang","submitted_at":"2026-05-28T10:07:44Z","abstract_excerpt":"Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in parallel with the target model. However, its practical speedup is constrained by the trade-off between draft quality and drafting cost: autoregressive drafters model causal dependencies among draft tokens but incur sequential overhead, while parallel drafters reduce drafting cost but weaken intra-block dependency modeling. In this paper, we propose Domino, a speculative decoding framework that decouples causal dependency modeling from expensive autoregressive draft execution. Domino first uses a pa"},"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":"2605.29707","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T10:07:44Z","cross_cats_sorted":[],"title_canon_sha256":"3dd079d1e4c97f2e547afb9f9b37251861e445ef25c4d50ab0bd67a13eae3a0c","abstract_canon_sha256":"baa875cf5ce2a86ae53197f2856a596d43399d407cc9e9a26d6dde2d1534ee27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:56.506408Z","signature_b64":"00C2UB6nlJtRRGuuBcWBCiUEPSRSBsH3GbXLmrb9NztQBsPRroI4yH5BDNP66uxKQBot8OgwyE0CX7fB3isQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99894064dd427bf7c6d72ae3bab8158509c56fa698cf1afa58f5d667b851932e","last_reissued_at":"2026-05-29T01:05:56.505931Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:56.505931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanlin Xu, Hao Lin, Jianuo Huang, Linfeng Zhang, Qituan Zhang, Yaojie Zhang","submitted_at":"2026-05-28T10:07:44Z","abstract_excerpt":"Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in parallel with the target model. However, its practical speedup is constrained by the trade-off between draft quality and drafting cost: autoregressive drafters model causal dependencies among draft tokens but incur sequential overhead, while parallel drafters reduce drafting cost but weaken intra-block dependency modeling. In this paper, we propose Domino, a speculative decoding framework that decouples causal dependency modeling from expensive autoregressive draft execution. Domino first uses a pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29707","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/2605.29707/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":"2605.29707","created_at":"2026-05-29T01:05:56.506004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29707v1","created_at":"2026-05-29T01:05:56.506004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29707","created_at":"2026-05-29T01:05:56.506004+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGEUAZG5IJ57","created_at":"2026-05-29T01:05:56.506004+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGEUAZG5IJ57PRWX","created_at":"2026-05-29T01:05:56.506004+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGEUAZG5","created_at":"2026-05-29T01:05:56.506004+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/TGEUAZG5IJ57PRWXFLR3VOAVQU","json":"https://pith.science/pith/TGEUAZG5IJ57PRWXFLR3VOAVQU.json","graph_json":"https://pith.science/api/pith-number/TGEUAZG5IJ57PRWXFLR3VOAVQU/graph.json","events_json":"https://pith.science/api/pith-number/TGEUAZG5IJ57PRWXFLR3VOAVQU/events.json","paper":"https://pith.science/paper/TGEUAZG5"},"agent_actions":{"view_html":"https://pith.science/pith/TGEUAZG5IJ57PRWXFLR3VOAVQU","download_json":"https://pith.science/pith/TGEUAZG5IJ57PRWXFLR3VOAVQU.json","view_paper":"https://pith.science/paper/TGEUAZG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29707&json=true","fetch_graph":"https://pith.science/api/pith-number/TGEUAZG5IJ57PRWXFLR3VOAVQU/graph.json","fetch_events":"https://pith.science/api/pith-number/TGEUAZG5IJ57PRWXFLR3VOAVQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGEUAZG5IJ57PRWXFLR3VOAVQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGEUAZG5IJ57PRWXFLR3VOAVQU/action/storage_attestation","attest_author":"https://pith.science/pith/TGEUAZG5IJ57PRWXFLR3VOAVQU/action/author_attestation","sign_citation":"https://pith.science/pith/TGEUAZG5IJ57PRWXFLR3VOAVQU/action/citation_signature","submit_replication":"https://pith.science/pith/TGEUAZG5IJ57PRWXFLR3VOAVQU/action/replication_record"}},"created_at":"2026-05-29T01:05:56.506004+00:00","updated_at":"2026-05-29T01:05:56.506004+00:00"}