{"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/split-sentences","entry":"split_sentences","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":14,"n_papers_ran":3,"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":14,"n_samples_ran":3,"n_samples_fingerprinted":3,"n_places":14,"n_places_pointer_only":8,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":2,"unverified":11},"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":"2609.13238","paper":"/paper/arxiv-2609-13238","title":"Clinical Reasoning Under a Partially Observed Objective in Cone Beam CT Report Generation","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"GIND123/CBCT-Clinical-Reasoner","path":"src/cbct_reasoner/text.py","file_url":"https://github.com/GIND123/CBCT-Clinical-Reasoner/blob/HEAD/src/cbct_reasoner/text.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d6c212bac3ad5dfc","mcp_get_code":{"code_sha256":"d6c212bac3ad5dfc"}},{"arxiv_id":"2608.07439","paper":"/paper/arxiv-2608-07439","title":"An Exploratory Evaluation of LLM-Assisted Rewriting of Moderate-Complexity Financial Sentences for DisCoCat-Based Sentiment Analysis","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"bllin001/qnlp-discocat-llms-finance-rewriting","path":"code/analyze_prompt_circuit_complexity.py","file_url":"https://github.com/bllin001/qnlp-discocat-llms-finance-rewriting/blob/HEAD/code/analyze_prompt_circuit_complexity.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"50fba3702f101dd5","mcp_get_code":{"code_sha256":"50fba3702f101dd5"}},{"arxiv_id":"2605.08888","paper":"/paper/arxiv-2605-08888","title":"DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"MiliLab/DocScope","path":"code/infer/reasoning_prompts.py","file_url":"https://github.com/MiliLab/DocScope/blob/HEAD/code/infer/reasoning_prompts.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c33b421f2b37e992","mcp_get_code":{"code_sha256":"c33b421f2b37e992"}},{"arxiv_id":"2604.12016","paper":"/paper/arxiv-2604-12016","title":"Identity as Attractor: Geometric Evidence for Persistent Agent Architecture in LLM Activation Space","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"b102e/yar-attractor-experiment","path":"bootstrap_experiment/d_random_bootstrap.py","file_url":"https://github.com/b102e/yar-attractor-experiment/blob/HEAD/bootstrap_experiment/d_random_bootstrap.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"93a9c0fe23024da6","mcp_get_code":{"code_sha256":"93a9c0fe23024da6"}},{"arxiv_id":"2603.07612","paper":"/paper/arxiv-2603-07612","title":"KohakuRAG: A simple RAG framework with hierarchical document indexing","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"KohakuBlueleaf/KohakuRAG","path":"src/kohakurag/indexer.py","file_url":"https://github.com/KohakuBlueleaf/KohakuRAG/blob/HEAD/src/kohakurag/indexer.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7d740ec94a7e44e8","mcp_get_code":{"code_sha256":"7d740ec94a7e44e8"}},{"arxiv_id":"2510.10681","paper":"/paper/arxiv-2510-10681","title":"RePro: Training Language Models to Faithfully Recycle the Web for Pretraining","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"cxcscmu/RePro","path":"pretrain/baselines/mappers/core_utils.py","file_url":"https://github.com/cxcscmu/RePro/blob/HEAD/pretrain/baselines/mappers/core_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c547a9e449d2b01b","mcp_get_code":{"code_sha256":"c547a9e449d2b01b"}},{"arxiv_id":"2509.17289","paper":"/paper/arxiv-2509-17289","title":"Automated Knowledge Graph Construction using Large Language Models and Sentence Complexity Modelling","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"KaushikMahmud/CoDe-KG_EMNLP_2025","path":"CoDe-KG/sentence_split_stage.py","file_url":"https://github.com/KaushikMahmud/CoDe-KG_EMNLP_2025/blob/HEAD/CoDe-KG/sentence_split_stage.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d9ea78a8be7f2476","mcp_get_code":{"code_sha256":"d9ea78a8be7f2476"}},{"arxiv_id":"2410.18050","paper":"/paper/longrag-a-dual-perspective-retrieval","title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"QingFei1/LongRAG","path":"src/gen_index.py","file_url":"https://github.com/QingFei1/LongRAG/blob/HEAD/src/gen_index.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"00adbf7ca43ffd6f","mcp_get_code":{"code_sha256":"00adbf7ca43ffd6f"}},{"arxiv_id":"2408.06941","paper":"/paper/openresearcher-unleashing-ai-for-accelerated","title":"OpenResearcher: Unleashing AI for Accelerated Scientific Research","date":"2024-08-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gair-nlp/openresearcher","path":"ui_app.py","file_url":"https://github.com/gair-nlp/openresearcher/blob/HEAD/ui_app.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":"693303dc8182ce92","mcp_get_code":{"code_sha256":"693303dc8182ce92"}},{"arxiv_id":"2405.03446","paper":"/paper/sevenllm-benchmarking-eliciting-and-enhancing","title":"SEvenLLM: Benchmarking, Eliciting, and Enhancing Abilities of Large Language Models in Cyber Threat Intelligence","date":null,"month_inferred_from_arxiv_id":"2024-05","title_source":"archive","repo":"csjianyang/seevenllm","path":"code/score/f1_rougel/gen_score_rougeL-en-path.py","file_url":"https://github.com/csjianyang/seevenllm/blob/HEAD/code/score/f1_rougel/gen_score_rougeL-en-path.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7b211652efdbbcd2","mcp_get_code":{"code_sha256":"7b211652efdbbcd2"}},{"arxiv_id":"2312.04889","paper":"/paper/kwaiagents-generalized-information-seeking","title":"KwaiAgents: Generalized Information-seeking Agent System with Large Language Models","date":"2023-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kwaikeg/kwaiagents","path":"kwaiagents/utils/nlp_utils.py","file_url":"https://github.com/kwaikeg/kwaiagents/blob/HEAD/kwaiagents/utils/nlp_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"b967246723156649","mcp_get_code":{"code_sha256":"b967246723156649"}},{"arxiv_id":"2305.15852","paper":"/paper/self-contradictory-hallucinations-of-large","title":"Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation","date":"2023-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eth-sri/chatprotect","path":"chatprotect/util.py","file_url":"https://github.com/eth-sri/chatprotect/blob/HEAD/chatprotect/util.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":"00998fc8648726d1","mcp_get_code":{"code_sha256":"00998fc8648726d1"}},{"arxiv_id":"1602.03606","paper":"/paper/variations-of-the-similarity-function-of","title":"Variations of the Similarity Function of TextRank for Automated Summarization","date":"2016-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chalothon/textRank","path":"summa/preprocessing/textcleaner.py","file_url":"https://github.com/chalothon/textRank/blob/HEAD/summa/preprocessing/textcleaner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bd5903bb5b570bc","mcp_get_code":{"code_sha256":"3bd5903bb5b570bc"}},{"arxiv_id":"openreview_JjILY9i6Wi","paper":null,"title":"arXiv:openreview_JjILY9i6Wi","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"nwlt/IPMark","path":"utils.py","file_url":"https://github.com/nwlt/IPMark/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"384d5b0b22097109","mcp_get_code":{"code_sha256":"384d5b0b22097109"}}]}