{"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/tokenize-text","entry":"tokenize_text","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":8,"n_papers_ran":2,"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":2,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"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":"2603.04969","paper":"/paper/arxiv-2603-04969","title":"MPCEval: A Benchmark for Multi-Party Conversation Generation","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"Owen-Yang-18/MPCEval","path":"src/local_content_unsupervised/lexical.py","file_url":"https://github.com/Owen-Yang-18/MPCEval/blob/HEAD/src/local_content_unsupervised/lexical.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"188187f5ace4e3f1","mcp_get_code":{"code_sha256":"188187f5ace4e3f1"}},{"arxiv_id":"2510.10618","paper":"/paper/arxiv-2510-10618","title":"Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"BokwaiHo/COLA","path":"cola/dataset_processing.py","file_url":"https://github.com/BokwaiHo/COLA/blob/HEAD/cola/dataset_processing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9079bb08f9ff7bae","mcp_get_code":{"code_sha256":"9079bb08f9ff7bae"}},{"arxiv_id":"2410.11758","paper":"/paper/latent-action-pretraining-from-videos","title":"Latent Action Pretraining from Videos","date":"2024-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/language-table","path":"language_table/common/clip_tokenizer.py","file_url":"https://github.com/google-research/language-table/blob/HEAD/language_table/common/clip_tokenizer.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":"f38cfe2cf5433ba8","mcp_get_code":{"code_sha256":"f38cfe2cf5433ba8"}},{"arxiv_id":"2403.15744","paper":"/paper/on-the-fragility-of-active-learners","title":"On the Fragility of Active Learners for Text Classification","date":"2024-03-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ThuongTNguyen/ALchemist","path":"core/hf_model_selection.py","file_url":"https://github.com/ThuongTNguyen/ALchemist/blob/HEAD/core/hf_model_selection.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9f8877b9d156b548","mcp_get_code":{"code_sha256":"9f8877b9d156b548"}},{"arxiv_id":"2401.05792","paper":"/paper/discovering-low-rank-subspaces-for-language","title":"Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations","date":"2024-01-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fffffarmer/lsar","path":"src/utils_extract.py","file_url":"https://github.com/fffffarmer/lsar/blob/HEAD/src/utils_extract.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3fd6bbcf0a212b7","mcp_get_code":{"code_sha256":"e3fd6bbcf0a212b7"}},{"arxiv_id":"2007.00145","paper":"/paper/modality-agnostic-attention-fusion-for-visual","title":"Modality-Agnostic Attention Fusion for visual search with text feedback","date":"2020-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nashory/rtic-gcn-pytorch","path":"model/base.py","file_url":"https://github.com/nashory/rtic-gcn-pytorch/blob/HEAD/model/base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6aeac26973c32ea7","mcp_get_code":{"code_sha256":"6aeac26973c32ea7"}},{"arxiv_id":"2006.16205","paper":"/paper/simplifying-models-with-unlabeled-output-data","title":"Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization","date":"2020-06-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"p-lambda/unlabeled_outputs","path":"code/format_pairs.py","file_url":"https://github.com/p-lambda/unlabeled_outputs/blob/HEAD/code/format_pairs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6708dda8d2ddd583","mcp_get_code":{"code_sha256":"6708dda8d2ddd583"}},{"arxiv_id":"aaai_29863","paper":null,"title":"arXiv:aaai_29863","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"facebookresearch/EditEval","path":"src/preprocessing.py","file_url":"https://github.com/facebookresearch/EditEval/blob/HEAD/src/preprocessing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"7502f9319edda834","mcp_get_code":{"code_sha256":"7502f9319edda834"}}]}