{"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/merge-datasets","entry":"merge_datasets","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":5,"n_papers_ran":1,"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":4,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"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":"2606.18993","paper":"/paper/arxiv-2606-18993","title":"Sequential Kernel-based Conditional Independence Testing via Adaptive Betting","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"he-zh/SKCI","path":"trainer/trainer.py","file_url":"https://github.com/he-zh/SKCI/blob/HEAD/trainer/trainer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c4be48a1d0b8f76f","mcp_get_code":{"code_sha256":"c4be48a1d0b8f76f"}},{"arxiv_id":"2603.26746","paper":"/paper/arxiv-2603-26746","title":"TDEC: Deep Embedded Image Clustering with Transformer and Distribution Information","date":"2026-03-23","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"BGU-CS-VIL/DeepDPM","path":"src/datasets.py","file_url":"https://github.com/BGU-CS-VIL/DeepDPM/blob/HEAD/src/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"72b10f5c47341c58","mcp_get_code":{"code_sha256":"72b10f5c47341c58"}},{"arxiv_id":"2408.13492","paper":"/paper/online-continuous-generalized-category","title":"Online Continuous Generalized Category Discovery","date":"2024-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"khu-agi/ocgcd","path":"net/datasets.py","file_url":"https://github.com/khu-agi/ocgcd/blob/HEAD/net/datasets.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"72b10f5c47341c58","mcp_get_code":{"code_sha256":"72b10f5c47341c58"}},{"arxiv_id":"2406.17385","paper":"/paper/native-design-bias-studying-the-impact-of","title":"Native Design Bias: Studying the Impact of English Nativeness on Language Model Performance","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"manon-reusens/native_en_bias","path":"gather_scores.py","file_url":"https://github.com/manon-reusens/native_en_bias/blob/HEAD/gather_scores.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e8e2042e330e6514","mcp_get_code":{"code_sha256":"e8e2042e330e6514"}},{"arxiv_id":"2025.emnlp-main.67","paper":null,"title":"arXiv:2025.emnlp-main.67","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"isyuhaochen/RRC-DSCD","path":"code/data_processing/cot_data_distill/merge_data.py","file_url":"https://github.com/isyuhaochen/RRC-DSCD/blob/HEAD/code/data_processing/cot_data_distill/merge_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"381929da2fa6fae2","mcp_get_code":{"code_sha256":"381929da2fa6fae2"}}]}