{"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-into-sentences","entry":"split_into_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":18,"n_papers_ran":12,"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":13,"n_samples_ran":7,"n_samples_fingerprinted":7,"n_places":21,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":4,"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":"2605.17104","paper":"/paper/arxiv-2605-17104","title":"Scientific Logicality Enriched Methodology for LLM Reasoning: A Practice in Physics","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"ScienceOne-AI/PhysLogic","path":"src/logicality_metrics.py","file_url":"https://github.com/ScienceOne-AI/PhysLogic/blob/HEAD/src/logicality_metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"82ec6023fe3765ba","mcp_get_code":{"code_sha256":"82ec6023fe3765ba"}},{"arxiv_id":"2604.27453","paper":"/paper/arxiv-2604-27453","title":"From Coarse to Fine: Benchmarking and Reward Modeling for Writing-Centric Generation Tasks","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Rainier-rq1/From_Coarse_to_Fine","path":"WRL/verl/modules/instructions_util.py","file_url":"https://github.com/Rainier-rq1/From_Coarse_to_Fine/blob/HEAD/WRL/verl/modules/instructions_util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"34d346853108011e","mcp_get_code":{"code_sha256":"34d346853108011e"}},{"arxiv_id":"2604.02795","paper":"/paper/arxiv-2604-02795","title":"Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"TURLEing/Rubrics-To-Tokens","path":"Benchmark/IFBench/instructions_util.py","file_url":"https://github.com/TURLEing/Rubrics-To-Tokens/blob/HEAD/Benchmark/IFBench/instructions_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":"a87fa9a878e94aa6","mcp_get_code":{"code_sha256":"a87fa9a878e94aa6"}},{"arxiv_id":"2602.12639","paper":"/paper/arxiv-2602-12639","title":"CLASE: A Hybrid Method for Chinese Legalese Stylistic Evaluation","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"rexera/CLASE","path":"linguistic_features/feature_extractor.py","file_url":"https://github.com/rexera/CLASE/blob/HEAD/linguistic_features/feature_extractor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"410516a5a8ae2900","mcp_get_code":{"code_sha256":"410516a5a8ae2900"}},{"arxiv_id":"2411.14405","paper":"/paper/marco-o1-towards-open-reasoning-models-for","title":"Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions","date":"2024-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aidc-ai/marco-o1","path":"src/v2/src/tree_search/evaluator/ifeval.py","file_url":"https://github.com/aidc-ai/marco-o1/blob/HEAD/src/v2/src/tree_search/evaluator/ifeval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a87fa9a878e94aa6","mcp_get_code":{"code_sha256":"a87fa9a878e94aa6"}},{"arxiv_id":"2410.09584","paper":"/paper/toward-general-instruction-following","title":"Toward General Instruction-Following Alignment for Retrieval-Augmented Generation","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dongguanting/FollowRAG","path":"FollowRAG/utils/instruction_following_eval/instructions_util.py","file_url":"https://github.com/dongguanting/FollowRAG/blob/HEAD/FollowRAG/utils/instruction_following_eval/instructions_util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"34d346853108011e","mcp_get_code":{"code_sha256":"34d346853108011e"}},{"arxiv_id":"2409.19177","paper":"/paper/evidence-is-all-you-need-ordering-imaging","title":"Evidence Is All You Need: Ordering Imaging Studies via Language Model Alignment with the ACR Appropriateness Criteria","date":"2024-09-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"michael-s-yao/radGPT","path":"radgpt/utils.py","file_url":"https://github.com/michael-s-yao/radGPT/blob/HEAD/radgpt/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fd34dbdf7f23af0f","mcp_get_code":{"code_sha256":"fd34dbdf7f23af0f"}},{"arxiv_id":"2406.12809","paper":"/paper/can-large-language-models-always-solve-easy","title":"Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones?","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"QwenLM/ConsisEval","path":"instruction_following_check/instructions_util.py","file_url":"https://github.com/QwenLM/ConsisEval/blob/HEAD/instruction_following_check/instructions_util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"34d346853108011e","mcp_get_code":{"code_sha256":"34d346853108011e"}},{"arxiv_id":"2404.15846","paper":"/paper/from-complex-to-simple-enhancing-multi","title":"From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models","date":"2024-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"meowpass/followcomplexinstruction","path":"get_data/instructions_util.py","file_url":"https://github.com/meowpass/followcomplexinstruction/blob/HEAD/get_data/instructions_util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"34d346853108011e","mcp_get_code":{"code_sha256":"34d346853108011e"}},{"arxiv_id":"2402.11728","paper":"/paper/numerical-claim-detection-in-finance-a-new","title":"Numerical Claim Detection in Finance: A New Financial Dataset, Weak-Supervision Model, and Market Analysis","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gtfintechlab/fin-num-claim","path":"code/WS_model.py","file_url":"https://github.com/gtfintechlab/fin-num-claim/blob/HEAD/code/WS_model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"9a2f7841367ae5ee","mcp_get_code":{"code_sha256":"9a2f7841367ae5ee"}},{"arxiv_id":"2402.08113","paper":"/paper/addressing-cognitive-bias-in-medical-language","title":"Addressing cognitive bias in medical language models","date":"2024-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"carlwharris/cog-bias-med-llms","path":"med_llm_bias.py","file_url":"https://github.com/carlwharris/cog-bias-med-llms/blob/HEAD/med_llm_bias.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f2f32e85cad01c72","mcp_get_code":{"code_sha256":"f2f32e85cad01c72"}},{"arxiv_id":"2311.07911","paper":"/paper/instruction-following-evaluation-for-large","title":"Instruction-Following Evaluation for Large Language Models","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"josejg/instruction_following_eval","path":"instruction_following_eval/instructions_util.py","file_url":"https://github.com/josejg/instruction_following_eval/blob/HEAD/instruction_following_eval/instructions_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":"a87fa9a878e94aa6","mcp_get_code":{"code_sha256":"a87fa9a878e94aa6"}},{"arxiv_id":"2310.16111","paper":"/paper/locally-differentially-private-document","title":"Locally Differentially Private Document Generation Using Zero Shot Prompting","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saitejautpala/dp_prompt","path":"attacks/embedding_attacker_architecture.py","file_url":"https://github.com/saitejautpala/dp_prompt/blob/HEAD/attacks/embedding_attacker_architecture.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"56d503b9d0430bed","mcp_get_code":{"code_sha256":"56d503b9d0430bed"}},{"arxiv_id":"2310.16111","paper":"/paper/locally-differentially-private-document","title":"Locally Differentially Private Document Generation Using Zero Shot Prompting","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saitejautpala/dp_prompt","path":"mechanisms/sentencelevel/deep_candidate.py","file_url":"https://github.com/saitejautpala/dp_prompt/blob/HEAD/mechanisms/sentencelevel/deep_candidate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cf8124a7098de674","mcp_get_code":{"code_sha256":"cf8124a7098de674"}},{"arxiv_id":"2310.16111","paper":"/paper/locally-differentially-private-document","title":"Locally Differentially Private Document Generation Using Zero Shot Prompting","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"saitejautpala/dp_prompt","path":"mechanisms/sentencelevel/truncated_laplace.py","file_url":"https://github.com/saitejautpala/dp_prompt/blob/HEAD/mechanisms/sentencelevel/truncated_laplace.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"245e7444d9ed2ce3","mcp_get_code":{"code_sha256":"245e7444d9ed2ce3"}},{"arxiv_id":"2309.00071","paper":"/paper/yarn-efficient-context-window-extension-of","title":"YaRN: Efficient Context Window Extension of Large Language Models","date":"2023-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qwenlm/qwq","path":"eval/eval/ifeval_utils/instructions_util.py","file_url":"https://github.com/qwenlm/qwq/blob/HEAD/eval/eval/ifeval_utils/instructions_util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"34d346853108011e","mcp_get_code":{"code_sha256":"34d346853108011e"}},{"arxiv_id":"2210.06442","paper":"/paper/can-pretrained-language-models-yet-reason","title":"Can Pretrained Language Models (Yet) Reason Deductively?","date":"2022-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cambridgeltl/deductive_reasoning_probing","path":"src/download_wikipedia.py","file_url":"https://github.com/cambridgeltl/deductive_reasoning_probing/blob/HEAD/src/download_wikipedia.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"553e04d1ebfd0daa","mcp_get_code":{"code_sha256":"553e04d1ebfd0daa"}},{"arxiv_id":"2025.emnlp-main.1010","paper":null,"title":"arXiv:2025.emnlp-main.1010","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"joaopfonseca/SafeNudge","path":"ctg/instructions_util.py","file_url":"https://github.com/joaopfonseca/SafeNudge/blob/HEAD/ctg/instructions_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a87fa9a878e94aa6","mcp_get_code":{"code_sha256":"a87fa9a878e94aa6"}},{"arxiv_id":"2025.acl-long.445","paper":null,"title":"arXiv:2025.acl-long.445","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"elainew728/labe-agency","path":"inference_bert.py","file_url":"https://github.com/elainew728/labe-agency/blob/HEAD/inference_bert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6e3a3e341d134c4e","mcp_get_code":{"code_sha256":"6e3a3e341d134c4e"}},{"arxiv_id":"2025.acl-long.445","paper":null,"title":"arXiv:2025.acl-long.445","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"elainew728/labe-agency","path":"lac_dataset_construction/generate_dataset.py","file_url":"https://github.com/elainew728/labe-agency/blob/HEAD/lac_dataset_construction/generate_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cbf95352820c01dd","mcp_get_code":{"code_sha256":"cbf95352820c01dd"}},{"arxiv_id":"2023.findings-emnlp.566","paper":null,"title":"arXiv:2023.findings-emnlp.566","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"SaitejaUtpala/dp_prompt","path":"attacks/embedding_attacker_architecture.py","file_url":"https://github.com/SaitejaUtpala/dp_prompt/blob/HEAD/attacks/embedding_attacker_architecture.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"56d503b9d0430bed","mcp_get_code":{"code_sha256":"56d503b9d0430bed"}}]}