{"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/collate-tokens","entry":"collate_tokens","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":4,"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":5,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":5,"unverified":1},"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":"2410.13179","paper":"/paper/eh-mam-easy-to-hard-masked-acoustic-modeling","title":"EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning","date":"2024-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cs20s030/ehmam","path":"data_utils.py","file_url":"https://github.com/cs20s030/ehmam/blob/HEAD/data_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d0c01822a7592080","mcp_get_code":{"code_sha256":"d0c01822a7592080"}},{"arxiv_id":"2406.03872","paper":"/paper/blsp-emo-towards-empathetic-large-speech","title":"BLSP-Emo: Towards Empathetic Large Speech-Language Models","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cwang621/blsp-emo","path":"generate.py","file_url":"https://github.com/cwang621/blsp-emo/blob/HEAD/generate.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":"746ac520906d93d1","mcp_get_code":{"code_sha256":"746ac520906d93d1"}},{"arxiv_id":"2309.00916","paper":"/paper/blsp-bootstrapping-language-speech-pre-1","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","date":"2023-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cwang621/blsp","path":"blsp/src/speech_text_paired_dataset.py","file_url":"https://github.com/cwang621/blsp/blob/HEAD/blsp/src/speech_text_paired_dataset.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":"11be103f3c940844","mcp_get_code":{"code_sha256":"11be103f3c940844"}},{"arxiv_id":"2309.00916","paper":"/paper/blsp-bootstrapping-language-speech-pre-1","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","date":"2023-09-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cwang621/blsp","path":"data_process/asr_text_generation.py","file_url":"https://github.com/cwang621/blsp/blob/HEAD/data_process/asr_text_generation.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":"25e0884d6d058e54","mcp_get_code":{"code_sha256":"25e0884d6d058e54"}},{"arxiv_id":"2308.11730","paper":"/paper/knowledge-graph-prompting-for-multi-document","title":"Knowledge Graph Prompting for Multi-Document Question Answering","date":"2023-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuwvandy/kg-llm-mdqa","path":"DPR/loader.py","file_url":"https://github.com/yuwvandy/kg-llm-mdqa/blob/HEAD/DPR/loader.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1935b354c2dfc484","mcp_get_code":{"code_sha256":"1935b354c2dfc484"}},{"arxiv_id":"2108.06645","paper":"/paper/on-multi-modal-learning-of-editing-source","title":"On Multi-Modal Learning of Editing Source Code","date":"2021-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"modit-team/MODIT","path":"src/denoising_dataset.py","file_url":"https://github.com/modit-team/MODIT/blob/HEAD/src/denoising_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1bc93e6eb54b046e","mcp_get_code":{"code_sha256":"1bc93e6eb54b046e"}}]}