{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NJTHOYK6P2PTQJALQLE2QCHII4","short_pith_number":"pith:NJTHOYK6","schema_version":"1.0","canonical_sha256":"6a6677615e7e9f38240b82c9a808e8473baea7ee507d2a8748376ceea3cdbdf2","source":{"kind":"arxiv","id":"2312.12728","version":3},"attestation_state":"computed","paper":{"title":"Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Chen Liang, Chenyi Zhuang, Jinjie Gu, Yao Zhao, Zhitian Xie","submitted_at":"2023-12-20T02:55:15Z","abstract_excerpt":"As Large Language Models (LLMs) have made significant advancements across various tasks, such as question answering, translation, text summarization, and dialogue systems, the need for accuracy in information becomes crucial, especially for serious financial products serving billions of users like Alipay. However, for a real-world product serving millions of users, the inference speed of LLMs becomes a critical factor compared to a mere experimental model.\n  Hence, this paper presents a generic framework for accelerating the inference process, resulting in a substantial increase in speed and c"},"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":"2312.12728","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2023-12-20T02:55:15Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2dc59d7625a2a96d4132d93b563805e00ec471e4ae79a6b74944d33536d11b0e","abstract_canon_sha256":"42e3d891d7c86492e35972f44f694caceb11c6f5a9b31ec7d66ba6ddc0ab3c2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:59.067086Z","signature_b64":"SrZRilnCxLOtGBO3dRvoReVAJtTIPak9Cd+jfPX25Ykn7YPfx7RrKnQbbG9knf0ahqgY6xWc9Pm//RezCIE+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a6677615e7e9f38240b82c9a808e8473baea7ee507d2a8748376ceea3cdbdf2","last_reissued_at":"2026-07-05T08:24:59.066562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:59.066562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Chen Liang, Chenyi Zhuang, Jinjie Gu, Yao Zhao, Zhitian Xie","submitted_at":"2023-12-20T02:55:15Z","abstract_excerpt":"As Large Language Models (LLMs) have made significant advancements across various tasks, such as question answering, translation, text summarization, and dialogue systems, the need for accuracy in information becomes crucial, especially for serious financial products serving billions of users like Alipay. However, for a real-world product serving millions of users, the inference speed of LLMs becomes a critical factor compared to a mere experimental model.\n  Hence, this paper presents a generic framework for accelerating the inference process, resulting in a substantial increase in speed and c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12728","kind":"arxiv","version":3},"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/2312.12728/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":"2312.12728","created_at":"2026-07-05T08:24:59.066626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.12728v3","created_at":"2026-07-05T08:24:59.066626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12728","created_at":"2026-07-05T08:24:59.066626+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJTHOYK6P2PT","created_at":"2026-07-05T08:24:59.066626+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJTHOYK6P2PTQJAL","created_at":"2026-07-05T08:24:59.066626+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJTHOYK6","created_at":"2026-07-05T08:24:59.066626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13319","citing_title":"PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NJTHOYK6P2PTQJALQLE2QCHII4","json":"https://pith.science/pith/NJTHOYK6P2PTQJALQLE2QCHII4.json","graph_json":"https://pith.science/api/pith-number/NJTHOYK6P2PTQJALQLE2QCHII4/graph.json","events_json":"https://pith.science/api/pith-number/NJTHOYK6P2PTQJALQLE2QCHII4/events.json","paper":"https://pith.science/paper/NJTHOYK6"},"agent_actions":{"view_html":"https://pith.science/pith/NJTHOYK6P2PTQJALQLE2QCHII4","download_json":"https://pith.science/pith/NJTHOYK6P2PTQJALQLE2QCHII4.json","view_paper":"https://pith.science/paper/NJTHOYK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.12728&json=true","fetch_graph":"https://pith.science/api/pith-number/NJTHOYK6P2PTQJALQLE2QCHII4/graph.json","fetch_events":"https://pith.science/api/pith-number/NJTHOYK6P2PTQJALQLE2QCHII4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJTHOYK6P2PTQJALQLE2QCHII4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJTHOYK6P2PTQJALQLE2QCHII4/action/storage_attestation","attest_author":"https://pith.science/pith/NJTHOYK6P2PTQJALQLE2QCHII4/action/author_attestation","sign_citation":"https://pith.science/pith/NJTHOYK6P2PTQJALQLE2QCHII4/action/citation_signature","submit_replication":"https://pith.science/pith/NJTHOYK6P2PTQJALQLE2QCHII4/action/replication_record"}},"created_at":"2026-07-05T08:24:59.066626+00:00","updated_at":"2026-07-05T08:24:59.066626+00:00"}