{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/prepare-logits-processor","entry":"prepare_logits_processor","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":11,"n_papers_ran":11,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":5,"n_samples_ran":4,"n_samples_fingerprinted":1,"n_places":13,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":3,"unverified":1},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2606.00535","paper":"/paper/arxiv-2606-00535","title":"DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"SAI-Lab-NYU/DREAM-S","path":"dream_s/model/utils.py","file_url":"https://github.com/SAI-Lab-NYU/DREAM-S/blob/HEAD/dream_s/model/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"78ae913ae6243c38","mcp_get_code":{"code_sha256":"78ae913ae6243c38"}},{"arxiv_id":"2606.00535","paper":"/paper/arxiv-2606-00535","title":"DREAM-S: Speculative Decoding with Searchable Drafting and Target-Aware Refinement for Multimodal Generation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"SAI-Lab-NYU/DREAM-S","path":"dream_s/model/utils_alpha.py","file_url":"https://github.com/SAI-Lab-NYU/DREAM-S/blob/HEAD/dream_s/model/utils_alpha.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f02fecb5f780c3f8","mcp_get_code":{"code_sha256":"f02fecb5f780c3f8"}},{"arxiv_id":"2602.16052","paper":"/paper/arxiv-2602-16052","title":"MoE-Spec: Expert Budgeting for Efficient Speculative Decoding","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"SafeAILab/EAGLE","path":"eagle/model/utils.py","file_url":"https://github.com/SafeAILab/EAGLE/blob/HEAD/eagle/model/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"78ae913ae6243c38","mcp_get_code":{"code_sha256":"78ae913ae6243c38"}},{"arxiv_id":"2601.19278","paper":"/paper/arxiv-2601-19278","title":"DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"fvliang/DART","path":"dart/model/dart_utils.py","file_url":"https://github.com/fvliang/DART/blob/HEAD/dart/model/dart_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"78ae913ae6243c38","mcp_get_code":{"code_sha256":"78ae913ae6243c38"}},{"arxiv_id":"2601.15498","paper":"/paper/arxiv-2601-15498","title":"MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"5SSjw/MARS","path":"mars/model/utils.py","file_url":"https://github.com/5SSjw/MARS/blob/HEAD/mars/model/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"78ae913ae6243c38","mcp_get_code":{"code_sha256":"78ae913ae6243c38"}},{"arxiv_id":"2503.10135","paper":"/paper/gumiho-a-hybrid-architecture-to-prioritize","title":"Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding","date":"2025-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AMD-AIG-AIMA/Gumiho","path":"gumiho/model/utils.py","file_url":"https://github.com/AMD-AIG-AIMA/Gumiho/blob/HEAD/gumiho/model/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"78ae913ae6243c38","mcp_get_code":{"code_sha256":"78ae913ae6243c38"}},{"arxiv_id":"2408.00264","paper":"/paper/clover-2-accurate-inference-for-regressive","title":"Clover-2: Accurate Inference for Regressive Lightweight Speculative Decoding","date":"2024-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XiaoBin1992/clover","path":"clover/model/utils_alpha.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/utils_alpha.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f02fecb5f780c3f8","mcp_get_code":{"code_sha256":"f02fecb5f780c3f8"}},{"arxiv_id":"2408.00264","paper":"/paper/clover-2-accurate-inference-for-regressive","title":"Clover-2: Accurate Inference for Regressive Lightweight Speculative Decoding","date":"2024-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XiaoBin1992/clover","path":"clover/model/utils.py","file_url":"https://github.com/XiaoBin1992/clover/blob/HEAD/clover/model/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fdb811155913ebca","mcp_get_code":{"code_sha256":"fdb811155913ebca"}},{"arxiv_id":"2402.11651","paper":"/paper/learning-from-failure-integrating-negative","title":"Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"reason-wang/nat","path":"utils/interactive.py","file_url":"https://github.com/reason-wang/nat/blob/HEAD/utils/interactive.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"93c25411cf60d992","mcp_get_code":{"code_sha256":"93c25411cf60d992"}},{"arxiv_id":"2401.07324","paper":"/paper/small-llms-are-weak-tool-learners-a-multi-llm","title":"Small LLMs Are Weak Tool Learners: A Multi-LLM Agent","date":"2024-01-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"x-plug/multi-llm-agent","path":"ToolBench-multiLLM/toolbench/inference/LLM/collab_agent_model.py","file_url":"https://github.com/x-plug/multi-llm-agent/blob/HEAD/ToolBench-multiLLM/toolbench/inference/LLM/collab_agent_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"93c25411cf60d992","mcp_get_code":{"code_sha256":"93c25411cf60d992"}},{"arxiv_id":"2312.02614","paper":"/paper/prompt-optimization-via-adversarial-in","title":"Prompt Optimization via Adversarial In-Context Learning","date":"2023-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaoyiran924/adv-in-context-learning","path":"eval/adversarial/gan_vicuna.py","file_url":"https://github.com/zhaoyiran924/adv-in-context-learning/blob/HEAD/eval/adversarial/gan_vicuna.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f18271a9ca05a04a","mcp_get_code":{"code_sha256":"f18271a9ca05a04a"}},{"arxiv_id":"2310.16450","paper":"/paper/clex-continuous-length-extrapolation-for","title":"CLEX: Continuous Length Extrapolation for Large Language Models","date":"2023-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DAMO-NLP-SG/CLEX","path":"serve/inference.py","file_url":"https://github.com/DAMO-NLP-SG/CLEX/blob/HEAD/serve/inference.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"93c25411cf60d992","mcp_get_code":{"code_sha256":"93c25411cf60d992"}},{"arxiv_id":"2305.14233","paper":"/paper/enhancing-chat-language-models-by-scaling","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/UltraChat","path":"UltraLM/util/inference.py","file_url":"https://github.com/thunlp/UltraChat/blob/HEAD/UltraLM/util/inference.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"93c25411cf60d992","mcp_get_code":{"code_sha256":"93c25411cf60d992"}}]}