{"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/eval-loop","entry":"eval_loop","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":7,"n_papers_ran":3,"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":6,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":3},"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":"2504.08129","paper":"/paper/between-linear-and-sinusoidal-rethinking-the","title":"Between Linear and Sinusoidal: Rethinking the Time Encoder in Dynamic Graph Learning","date":"2025-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hsinghuan/dg-linear-time","path":"auxiliary/synthetic.py","file_url":"https://github.com/hsinghuan/dg-linear-time/blob/HEAD/auxiliary/synthetic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0aa425a40e03ff85","mcp_get_code":{"code_sha256":"0aa425a40e03ff85"}},{"arxiv_id":"2410.21035","paper":"/paper/beyond-autoregression-fast-llms-via-self","title":"Beyond Autoregression: Fast LLMs via Self-Distillation Through Time","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jdeschena/sdtt","path":"src/sdtt/harness_gpt2.py","file_url":"https://github.com/jdeschena/sdtt/blob/HEAD/src/sdtt/harness_gpt2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b0a49b09dfb49452","mcp_get_code":{"code_sha256":"b0a49b09dfb49452"}},{"arxiv_id":"2410.08709","paper":"/paper/distillation-of-discrete-diffusion-through","title":"Distillation of Discrete Diffusion through Dimensional Correlations","date":"2024-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sony/di4c","path":"sdtt/src/sdtt/harness_gpt2.py","file_url":"https://github.com/sony/di4c/blob/HEAD/sdtt/src/sdtt/harness_gpt2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b0a49b09dfb49452","mcp_get_code":{"code_sha256":"b0a49b09dfb49452"}},{"arxiv_id":"2408.01417","paper":"/paper/2408-01417","title":"Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs","date":"2024-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lil-lab/icca","path":"src/run_icca.py","file_url":"https://github.com/lil-lab/icca/blob/HEAD/src/run_icca.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"788a4499c4864827","mcp_get_code":{"code_sha256":"788a4499c4864827"}},{"arxiv_id":"2402.12366","paper":"/paper/a-critical-evaluation-of-ai-feedback-for","title":"A Critical Evaluation of AI Feedback for Aligning Large Language Models","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"architsharma97/dpo-rlaif","path":"reward_trainer.py","file_url":"https://github.com/architsharma97/dpo-rlaif/blob/HEAD/reward_trainer.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":"b1c3a18860528ce9","mcp_get_code":{"code_sha256":"b1c3a18860528ce9"}},{"arxiv_id":"2401.06643","paper":"/paper/effects-of-diversity-incentives-on-sample","title":"Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kinit-sk/llm-div-incts","path":"datasets/20news/train_bert_news.py","file_url":"https://github.com/kinit-sk/llm-div-incts/blob/HEAD/datasets/20news/train_bert_news.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"59ba28960d2ca93b","mcp_get_code":{"code_sha256":"59ba28960d2ca93b"}},{"arxiv_id":"2309.08591","paper":"/paper/are-multilingual-llms-culturally-diverse","title":"Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings","date":"2023-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UKPLab/maps","path":"experiments/ft_standard.py","file_url":"https://github.com/UKPLab/maps/blob/HEAD/experiments/ft_standard.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"2dbf41f4c8c1c696","mcp_get_code":{"code_sha256":"2dbf41f4c8c1c696"}}]}