{"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/compute-recall","entry":"compute_recall","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":12,"n_samples_ran":6,"n_samples_fingerprinted":1,"n_places":13,"n_places_pointer_only":5,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":1,"ran":3,"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":"2605.12370","paper":"/paper/arxiv-2605-12370","title":"Context Convergence Improves Answering Inferential Questions","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"DataScienceUIBK/Context-Convergence-Inferential-QA","path":"experiments/convergence_vs_cosine.py","file_url":"https://github.com/DataScienceUIBK/Context-Convergence-Inferential-QA/blob/HEAD/experiments/convergence_vs_cosine.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3c261861a268a2a0","mcp_get_code":{"code_sha256":"3c261861a268a2a0"}},{"arxiv_id":"2604.09982","paper":"/paper/arxiv-2604-09982","title":"Reproduction Beyond Benchmarks: ConstBERT and ColBERT-v2 Across Backends and Query Distributions","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"utshabkg/multi-vector-reproducibility","path":"evaluation/metrics.py","file_url":"https://github.com/utshabkg/multi-vector-reproducibility/blob/HEAD/evaluation/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"08233ae383487ece","mcp_get_code":{"code_sha256":"08233ae383487ece"}},{"arxiv_id":"2506.09944","paper":"/paper/query-focused-retrieval-heads-improve-long","title":"Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-ranking","date":"2025-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-pli/QRHead","path":"exp_scripts/retrieval/eval_retrieval.py","file_url":"https://github.com/princeton-pli/QRHead/blob/HEAD/exp_scripts/retrieval/eval_retrieval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6485b6194332b150","mcp_get_code":{"code_sha256":"6485b6194332b150"}},{"arxiv_id":"2410.18926","paper":"/paper/lorann-low-rank-matrix-factorization-for","title":"LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ejaasaari/lorann","path":"python/lorann/lorann.py","file_url":"https://github.com/ejaasaari/lorann/blob/HEAD/python/lorann/lorann.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"67137b50ff87ea9b","mcp_get_code":{"code_sha256":"67137b50ff87ea9b"}},{"arxiv_id":"2405.19856","paper":"/paper/deveval-a-manually-annotated-code-generation","title":"DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seketeam/deveval","path":"parser/recall_k.py","file_url":"https://github.com/seketeam/deveval/blob/HEAD/parser/recall_k.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b57d66d6dc47f45b","mcp_get_code":{"code_sha256":"b57d66d6dc47f45b"}},{"arxiv_id":"2404.17288","paper":"/paper/excluir-exclusionary-neural-information","title":"ExcluIR: Exclusionary Neural Information Retrieval","date":"2024-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zwh-sdu/excluir","path":"src/utils.py","file_url":"https://github.com/zwh-sdu/excluir/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6a64d72d6a74b5e2","mcp_get_code":{"code_sha256":"6a64d72d6a74b5e2"}},{"arxiv_id":"2404.00599","paper":"/paper/evocodebench-an-evolving-code-generation","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seketeam/evocodebench","path":"parser/recall_k.py","file_url":"https://github.com/seketeam/evocodebench/blob/HEAD/parser/recall_k.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":"b57d66d6dc47f45b","mcp_get_code":{"code_sha256":"b57d66d6dc47f45b"}},{"arxiv_id":"2401.14493","paper":"/paper/k-qa-a-real-world-medical-q-a-benchmark","title":"K-QA: A Real-World Medical Q&A Benchmark","date":"2024-01-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"itaymanes/k-qa","path":"evaluation/metrics.py","file_url":"https://github.com/itaymanes/k-qa/blob/HEAD/evaluation/metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"faf5dd03e0b09ce3","mcp_get_code":{"code_sha256":"faf5dd03e0b09ce3"}},{"arxiv_id":"2311.16254","paper":"/paper/removing-nsfw-concepts-from-vision-and","title":"Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models","date":"2023-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aimagelab/safe-clip","path":"training/recall_computation.py","file_url":"https://github.com/aimagelab/safe-clip/blob/HEAD/training/recall_computation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1111a1c694170bfe","mcp_get_code":{"code_sha256":"1111a1c694170bfe"}},{"arxiv_id":"2212.10015","paper":"/paper/benchmarking-spatial-relationships-in-text-to","title":"Benchmarking Spatial Relationships in Text-to-Image Generation","date":"2022-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/VISOR","path":"visor.py","file_url":"https://github.com/microsoft/VISOR/blob/HEAD/visor.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"67c9b1c81c05cb3a","mcp_get_code":{"code_sha256":"67c9b1c81c05cb3a"}},{"arxiv_id":"2211.00768","paper":"/paper/why-is-winoground-hard-investigating-failures","title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality","date":"2022-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ajd12342/why-winoground-hard","path":"winoground_recall.py","file_url":"https://github.com/ajd12342/why-winoground-hard/blob/HEAD/winoground_recall.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e0ec484f940c1bd5","mcp_get_code":{"code_sha256":"e0ec484f940c1bd5"}},{"arxiv_id":"2004.05665","paper":"/paper/minimizing-flops-to-learn-efficient-sparse-1","title":"Minimizing FLOPs to Learn Efficient Sparse Representations","date":"2020-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"biswajitsc/sparse-embed","path":"evaluate_mfacenet_reranking.py","file_url":"https://github.com/biswajitsc/sparse-embed/blob/HEAD/evaluate_mfacenet_reranking.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4b4213b3b4b974ad","mcp_get_code":{"code_sha256":"4b4213b3b4b974ad"}},{"arxiv_id":"1906.01859","paper":"/paper/fair-near-neighbor-search-independent-range","title":"Fair Near Neighbor Search: Independent Range Sampling in High Dimensions","date":"2019-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alfahaf/fair-near-neighbor-search","path":"src/helpers.py","file_url":"https://github.com/alfahaf/fair-near-neighbor-search/blob/HEAD/src/helpers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e47a2eb123973f49","mcp_get_code":{"code_sha256":"e47a2eb123973f49"}}]}