{"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/find-ngrams","entry":"find_ngrams","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":7,"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":5,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":4},"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":"2606.28044","paper":"/paper/arxiv-2606-28044","title":"A Tree-of-Thoughts Hybrid Approach for Legal Case Judgement Summarization using LLMs","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Yale-LILY/SummEval","path":"evaluation/summ_eval/data_stats_metric.py","file_url":"https://github.com/Yale-LILY/SummEval/blob/HEAD/evaluation/summ_eval/data_stats_metric.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"15011c2229e5cd8b","mcp_get_code":{"code_sha256":"15011c2229e5cd8b"}},{"arxiv_id":"2212.07919","paper":"/paper/roscoe-a-suite-of-metrics-for-scoring-step-by","title":"ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning","date":"2022-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/ParlAI","path":"parlai/core/dict.py","file_url":"https://github.com/facebookresearch/ParlAI/blob/HEAD/parlai/core/dict.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"761ab53c3cc0c21a","mcp_get_code":{"code_sha256":"761ab53c3cc0c21a"}},{"arxiv_id":"2005.00816","paper":"/paper/dqi-measuring-data-quality-in-nlp","title":"DQI: Measuring Data Quality in NLP","date":"2020-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"swarooprm/DQI","path":"p6.py","file_url":"https://github.com/swarooprm/DQI/blob/HEAD/p6.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":"3a96d5a58354daea","mcp_get_code":{"code_sha256":"3a96d5a58354daea"}},{"arxiv_id":"2003.11963","paper":"/paper/tldr-token-loss-dynamic-reweighting-for","title":"TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation","date":"2020-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ShaojieJiang/tldr","path":"parlai/core/dict.py","file_url":"https://github.com/ShaojieJiang/tldr/blob/HEAD/parlai/core/dict.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"761ab53c3cc0c21a","mcp_get_code":{"code_sha256":"761ab53c3cc0c21a"}},{"arxiv_id":"1909.05863","paper":"/paper/finding-generalizable-evidence-by-learning-to","title":"Finding Generalizable Evidence by Learning to Convince Q&A Models","date":"2019-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ethanjperez/convince","path":"ParlAI/parlai/core/dict.py","file_url":"https://github.com/ethanjperez/convince/blob/HEAD/ParlAI/parlai/core/dict.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":"63c2a8c36bd5cbff","mcp_get_code":{"code_sha256":"63c2a8c36bd5cbff"}},{"arxiv_id":"1906.01603","paper":"/paper/do-neural-dialog-systems-use-the-conversation","title":"Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study","date":"2019-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chinnadhurai/ParlAI","path":"parlai/core/dict.py","file_url":"https://github.com/chinnadhurai/ParlAI/blob/HEAD/parlai/core/dict.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"761ab53c3cc0c21a","mcp_get_code":{"code_sha256":"761ab53c3cc0c21a"}},{"arxiv_id":"2024.naacl-srw.28","paper":null,"title":"arXiv:2024.naacl-srw.28","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"life4/textdistance","path":"textdistance/utils.py","file_url":"https://github.com/life4/textdistance/blob/HEAD/textdistance/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"36179eef3e5cd993","mcp_get_code":{"code_sha256":"36179eef3e5cd993"}}]}