{"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/ndcg","entry":"ndcg","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":16,"n_papers_ran":9,"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":15,"n_samples_ran":9,"n_samples_fingerprinted":3,"n_places":16,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":3,"ran":6,"unverified":6},"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":"2608.22920","paper":"/paper/arxiv-2608-22920","title":"Beyond Observed Auxiliary Relations: Environment-Conditioned Modeling for Multi-Behavior Recommendation","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"LSH0411/BOAR","path":"src/model/trainer.py","file_url":"https://github.com/LSH0411/BOAR/blob/HEAD/src/model/trainer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dbb00da12cf9c374","mcp_get_code":{"code_sha256":"dbb00da12cf9c374"}},{"arxiv_id":"2606.15903","paper":"/paper/arxiv-2606-15903","title":"Control-Plane Placement Shapes Forgetting: An Architectural Study of Agent Memory Across Thirteen System Configurations","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"deeplethe/lethe","path":"bench/mempalace_bench.py","file_url":"https://github.com/deeplethe/lethe/blob/HEAD/bench/mempalace_bench.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9257acfb3b218b9c","mcp_get_code":{"code_sha256":"9257acfb3b218b9c"}},{"arxiv_id":"2601.06966","paper":"/paper/arxiv-2601-06966","title":"RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"AvatarMemory/RealMemBench","path":"eval/compute_auto_metrics_for_realmem.py","file_url":"https://github.com/AvatarMemory/RealMemBench/blob/HEAD/eval/compute_auto_metrics_for_realmem.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":"71b9778fa0d631c8","mcp_get_code":{"code_sha256":"71b9778fa0d631c8"}},{"arxiv_id":"2601.01280","paper":"/paper/arxiv-2601-01280","title":"Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"AvatarMemory/UnifiedMem","path":"evals/lme_eval_utils.py","file_url":"https://github.com/AvatarMemory/UnifiedMem/blob/HEAD/evals/lme_eval_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"878c3d776ad1928f","mcp_get_code":{"code_sha256":"878c3d776ad1928f"}},{"arxiv_id":"2410.20745","paper":"/paper/shopping-mmlu-a-massive-multi-task-online","title":"Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"KL4805/ShoppingMMLU","path":"task_wise_eval/hf_ranking.py","file_url":"https://github.com/KL4805/ShoppingMMLU/blob/HEAD/task_wise_eval/hf_ranking.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":"8d9104b9e41ddb8b","mcp_get_code":{"code_sha256":"8d9104b9e41ddb8b"}},{"arxiv_id":"2410.10813","paper":"/paper/longmemeval-benchmarking-chat-assistants-on","title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiaowu0162/longmemeval","path":"src/retrieval/eval_utils.py","file_url":"https://github.com/xiaowu0162/longmemeval/blob/HEAD/src/retrieval/eval_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"878c3d776ad1928f","mcp_get_code":{"code_sha256":"878c3d776ad1928f"}},{"arxiv_id":"2410.06581","paper":"/paper/enhancing-legal-case-retrieval-via-scaling","title":"Enhancing Legal Case Retrieval via Scaling High-quality Synthetic Query-Candidate Pairs","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/LEAD","path":"LeCaRD/metrics.py","file_url":"https://github.com/thunlp/LEAD/blob/HEAD/LeCaRD/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a6887cb2464e843e","mcp_get_code":{"code_sha256":"a6887cb2464e843e"}},{"arxiv_id":"2408.14393","paper":"/paper/cure4rec-a-benchmark-for-recommendation","title":"CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence","date":"2024-08-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiye7lai/CURE4Rec","path":"utils.py","file_url":"https://github.com/xiye7lai/CURE4Rec/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7f429335b5cc6bd3","mcp_get_code":{"code_sha256":"7f429335b5cc6bd3"}},{"arxiv_id":"2408.08931","paper":"/paper/personalized-federated-collaborative","title":"Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach","date":"2024-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mtics/feddae","path":"utils/evaluation.py","file_url":"https://github.com/mtics/feddae/blob/HEAD/utils/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9bdf014fdeae23f","mcp_get_code":{"code_sha256":"f9bdf014fdeae23f"}},{"arxiv_id":"2403.13574","paper":"/paper/a-large-language-model-enhanced-sequential","title":"A Large Language Model Enhanced Sequential Recommender for Joint Video and Comment Recommendation","date":"2024-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/lsvcr","path":"metrics.py","file_url":"https://github.com/rucaibox/lsvcr/blob/HEAD/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b2215adec6371d49","mcp_get_code":{"code_sha256":"b2215adec6371d49"}},{"arxiv_id":"2309.01103","paper":"/paper/multi-relational-contrastive-learning-for","title":"Multi-Relational Contrastive Learning for Recommendation","date":"2023-09-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HKUDS/RCL","path":"evaluate.py","file_url":"https://github.com/HKUDS/RCL/blob/HEAD/evaluate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"334fbf3e8871bb11","mcp_get_code":{"code_sha256":"334fbf3e8871bb11"}},{"arxiv_id":"2308.14029","paper":"/paper/text-matching-improves-sequential","title":"Text Matching Improves Sequential Recommendation by Reducing Popularity Biases","date":"2023-08-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmatch/taste","path":"utils/rec_metrics.py","file_url":"https://github.com/openmatch/taste/blob/HEAD/utils/rec_metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e352eaf812952701","mcp_get_code":{"code_sha256":"e352eaf812952701"}},{"arxiv_id":"2206.04789","paper":"/paper/comprehensive-fair-meta-learned-recommender","title":"Comprehensive Fair Meta-learned Recommender System","date":"2022-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weitianxin/CLOVER","path":"ML1M/maml.py","file_url":"https://github.com/weitianxin/CLOVER/blob/HEAD/ML1M/maml.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fd2a56eaa1ac6a6b","mcp_get_code":{"code_sha256":"fd2a56eaa1ac6a6b"}},{"arxiv_id":"1909.02050","paper":"/paper/tiger-text-to-image-grounding-for-image","title":"TIGEr: Text-to-Image Grounding for Image Caption Evaluation","date":"2019-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SeleenaJM/CapEval","path":"tiger.py","file_url":"https://github.com/SeleenaJM/CapEval/blob/HEAD/tiger.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f8a275b3e4999aca","mcp_get_code":{"code_sha256":"f8a275b3e4999aca"}},{"arxiv_id":"1802.05814","paper":"/paper/variational-autoencoders-for-collaborative","title":"Variational Autoencoders for Collaborative Filtering","date":"2018-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mkfilipiuk/VAE-CF","path":"vae/metrics/ndcg.py","file_url":"https://github.com/mkfilipiuk/VAE-CF/blob/HEAD/vae/metrics/ndcg.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":"4026df4b925b1a11","mcp_get_code":{"code_sha256":"4026df4b925b1a11"}},{"arxiv_id":"0705.2011","paper":"/paper/multi-dimensional-recurrent-neural-networks","title":"Multi-Dimensional Recurrent Neural Networks","date":"2007-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jzbjyb/rri_match","path":"metric.py","file_url":"https://github.com/jzbjyb/rri_match/blob/HEAD/metric.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":"e41abfe79a1abfca","mcp_get_code":{"code_sha256":"e41abfe79a1abfca"}}]}