{"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/top-p-logits","entry":"top_p_logits","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":13,"n_papers_ran":7,"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":8,"n_samples_ran":3,"n_samples_fingerprinted":3,"n_places":13,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":2,"ran":0,"unverified":5},"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":"2608.10288","paper":"/paper/arxiv-2608-10288","title":"Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"burcgokden/lm-evaluation-harness-with-PLDR-LLM","path":"lm_eval/models/pldrllm.py","file_url":"https://github.com/burcgokden/lm-evaluation-harness-with-PLDR-LLM/blob/HEAD/lm_eval/models/pldrllm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8110b89018ed3fcc","mcp_get_code":{"code_sha256":"8110b89018ed3fcc"}},{"arxiv_id":"2606.18781","paper":"/paper/arxiv-2606-18781","title":"Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"PunchlineAAAA/DICE","path":"dream/generation_utils.py","file_url":"https://github.com/PunchlineAAAA/DICE/blob/HEAD/dream/generation_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8139ba2bcf3eb84b","mcp_get_code":{"code_sha256":"8139ba2bcf3eb84b"}},{"arxiv_id":"2604.18995","paper":"/paper/arxiv-2604-18995","title":"R 2 -dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"GATECH-EIC/R2-dLLM","path":"dream/model/generation_utils.py","file_url":"https://github.com/GATECH-EIC/R2-dLLM/blob/HEAD/dream/model/generation_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8139ba2bcf3eb84b","mcp_get_code":{"code_sha256":"8139ba2bcf3eb84b"}},{"arxiv_id":"2604.15750","paper":"/paper/arxiv-2604-15750","title":"DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"X-Xia0828/DepCap","path":"dream/model/generation_utils.py","file_url":"https://github.com/X-Xia0828/DepCap/blob/HEAD/dream/model/generation_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8139ba2bcf3eb84b","mcp_get_code":{"code_sha256":"8139ba2bcf3eb84b"}},{"arxiv_id":"2602.06953","paper":"/paper/arxiv-2602-06953","title":"DAWN: Dependency-Aware Fast Inference for Diffusion LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"lizhuo-luo/DAWN","path":"dream/model/generation_utils.py","file_url":"https://github.com/lizhuo-luo/DAWN/blob/HEAD/dream/model/generation_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8139ba2bcf3eb84b","mcp_get_code":{"code_sha256":"8139ba2bcf3eb84b"}},{"arxiv_id":"2602.02178","paper":"/paper/arxiv-2602-02178","title":"AR-MAP: Are Autoregressive Large Language Models Implicit Teachers for Diffusion Large Language Models?","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"AMAP-ML/AR-MAP","path":"dLLM-RL-main/generate.py","file_url":"https://github.com/AMAP-ML/AR-MAP/blob/HEAD/dLLM-RL-main/generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"66db01566412a3db","mcp_get_code":{"code_sha256":"66db01566412a3db"}},{"arxiv_id":"2601.17917","paper":"/paper/arxiv-2601-17917","title":"Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"xiaoshideta/Streaming-dLLM","path":"OpenPangu/inference/generation_utils_streaming.py","file_url":"https://github.com/xiaoshideta/Streaming-dLLM/blob/HEAD/OpenPangu/inference/generation_utils_streaming.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8139ba2bcf3eb84b","mcp_get_code":{"code_sha256":"8139ba2bcf3eb84b"}},{"arxiv_id":"2601.10926","paper":"/paper/arxiv-2601-10926","title":"Selecting Language Models for Social Science: Start Small, Start Open, and Validate Preprint XX(X):1-22 ©The Author(s) 2026","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"openai/gpt-2","path":"src/sample.py","file_url":"https://github.com/openai/gpt-2/blob/HEAD/src/sample.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8110b89018ed3fcc","mcp_get_code":{"code_sha256":"8110b89018ed3fcc"}},{"arxiv_id":"2502.14204","paper":"/paper/on-the-fly-preference-alignment-via-principle","title":"On-the-fly Preference Alignment via Principle-Guided Decoding","date":"2025-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stevie1023/opad","path":"model.py","file_url":"https://github.com/stevie1023/opad/blob/HEAD/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2ba2c099a65a9cd","mcp_get_code":{"code_sha256":"e2ba2c099a65a9cd"}},{"arxiv_id":"2410.17891","paper":"/paper/scaling-diffusion-language-models-via","title":"Scaling Diffusion Language Models via Adaptation from Autoregressive Models","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HKUNLP/DiffuLLaMA","path":"evaluation/eval-diffullama.py","file_url":"https://github.com/HKUNLP/DiffuLLaMA/blob/HEAD/evaluation/eval-diffullama.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fd2fe76b57111989","mcp_get_code":{"code_sha256":"fd2fe76b57111989"}},{"arxiv_id":"1908.09451","paper":"/paper/improving-neural-story-generation-by-targeted","title":"Improving Neural Story Generation by Targeted Common Sense Grounding","date":"2019-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"calclavia/story-generation","path":"analysis/generate.py","file_url":"https://github.com/calclavia/story-generation/blob/HEAD/analysis/generate.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f4bdad69d56eb2a0","mcp_get_code":{"code_sha256":"f4bdad69d56eb2a0"}},{"arxiv_id":"openreview_QrC8OgQyOI","paper":null,"title":"arXiv:openreview_QrC8OgQyOI","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"viiika/Prism","path":"Dream/Dream_Prism/src/diffllm/gen_utils.py","file_url":"https://github.com/viiika/Prism/blob/HEAD/Dream/Dream_Prism/src/diffllm/gen_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":"5b9d49f026840bbb","mcp_get_code":{"code_sha256":"5b9d49f026840bbb"}},{"arxiv_id":"2023.findings-acl.765","paper":null,"title":"arXiv:2023.findings-acl.765","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"qtli/EIB","path":"code/BottleSum/bottleSelf_summarize.py","file_url":"https://github.com/qtli/EIB/blob/HEAD/code/BottleSum/bottleSelf_summarize.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":"3b9dbc9cbc681120","mcp_get_code":{"code_sha256":"3b9dbc9cbc681120"}}]}