{"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/truncate","entry":"truncate","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":26,"n_papers_ran":14,"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":27,"n_samples_ran":14,"n_samples_fingerprinted":11,"n_places":27,"n_places_pointer_only":9,"by_status":{"ran_honours":4,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":9,"unverified":13},"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":"2608.04374","paper":"/paper/arxiv-2608-04374","title":"FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"MisterBrookT/finreportbench","path":"harness/prepare/reverse_query.py","file_url":"https://github.com/MisterBrookT/finreportbench/blob/HEAD/harness/prepare/reverse_query.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":"ef7fa1ce3390e81f","mcp_get_code":{"code_sha256":"ef7fa1ce3390e81f"}},{"arxiv_id":"2606.29493","paper":"/paper/arxiv-2606-29493","title":"Faults in Our Formal Benchmarking: Dataset Defects and Evaluation Failures in Lean Theorem Proving","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"leanprover/lean4","path":"script/junit_embed_output.py","file_url":"https://github.com/leanprover/lean4/blob/HEAD/script/junit_embed_output.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":"8664291b9fcd8fb8","mcp_get_code":{"code_sha256":"8664291b9fcd8fb8"}},{"arxiv_id":"2604.03616","paper":"/paper/arxiv-2604-03616","title":"The Format Tax","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"ivnle/the-format-tax","path":"dev/show_triple.py","file_url":"https://github.com/ivnle/the-format-tax/blob/HEAD/dev/show_triple.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"3c3f8b68575a2689","mcp_get_code":{"code_sha256":"3c3f8b68575a2689"}},{"arxiv_id":"2502.13668","paper":"/paper/peerqa-a-scientific-question-answering","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","date":"2025-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ukplab/peerqa","path":"peerqa/generate_utils.py","file_url":"https://github.com/ukplab/peerqa/blob/HEAD/peerqa/generate_utils.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":"2e014728127b6d13","mcp_get_code":{"code_sha256":"2e014728127b6d13"}},{"arxiv_id":"2409.19951","paper":"/paper/law-of-the-weakest-link-cross-capabilities-of","title":"Law of the Weakest Link: Cross Capabilities of Large Language Models","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/llm-cross-capabilities","path":"evaluation/utils.py","file_url":"https://github.com/facebookresearch/llm-cross-capabilities/blob/HEAD/evaluation/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"66e63322b5a434b5","mcp_get_code":{"code_sha256":"66e63322b5a434b5"}},{"arxiv_id":"2409.19951","paper":"/paper/law-of-the-weakest-link-cross-capabilities-of","title":"Law of the Weakest Link: Cross Capabilities of Large Language Models","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/llm-cross-capabilities","path":"generate_response/models/utils.py","file_url":"https://github.com/facebookresearch/llm-cross-capabilities/blob/HEAD/generate_response/models/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"aba025460db71689","mcp_get_code":{"code_sha256":"aba025460db71689"}},{"arxiv_id":"2405.14377","paper":"/paper/comera-computing-and-memory-efficient","title":"CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ziyangjoy/CoMERA","path":"data_process.py","file_url":"https://github.com/ziyangjoy/CoMERA/blob/HEAD/data_process.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2afb43ca8be6a440","mcp_get_code":{"code_sha256":"2afb43ca8be6a440"}},{"arxiv_id":"2404.14215","paper":"/paper/text-tuple-table-towards-information","title":"Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gersteinlab/Struc-Bench","path":"score/D2T/moverscore.py","file_url":"https://github.com/gersteinlab/Struc-Bench/blob/HEAD/score/D2T/moverscore.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e7166f45e5a6fb2a","mcp_get_code":{"code_sha256":"e7166f45e5a6fb2a"}},{"arxiv_id":"2402.15938","paper":"/paper/generalization-or-memorization-data","title":"Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models","date":"2024-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihongdong/cdd-ted4llms","path":"TED.py","file_url":"https://github.com/yihongdong/cdd-ted4llms/blob/HEAD/TED.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"25ceaacde290b651","mcp_get_code":{"code_sha256":"25ceaacde290b651"}},{"arxiv_id":"2402.14433","paper":"/paper/a-language-model-s-guide-through-latent-space","title":"A Language Model's Guide Through Latent Space","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvruette/concept-guidance","path":"concept_guidance/eval/open_assistant.py","file_url":"https://github.com/dvruette/concept-guidance/blob/HEAD/concept_guidance/eval/open_assistant.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2b8ac1277f79833e","mcp_get_code":{"code_sha256":"2b8ac1277f79833e"}},{"arxiv_id":"2402.12550","paper":"/paper/multilinear-mixture-of-experts-scalable","title":"Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"james-oldfield/mmoe","path":"utils.py","file_url":"https://github.com/james-oldfield/mmoe/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"32f08e6e8ce8238e","mcp_get_code":{"code_sha256":"32f08e6e8ce8238e"}},{"arxiv_id":"2402.09844","paper":"/paper/jack-of-all-trades-master-of-some-a-multi","title":"Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huggingface/jat","path":"jat/processing_jat.py","file_url":"https://github.com/huggingface/jat/blob/HEAD/jat/processing_jat.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":"92702d141fa25fd0","mcp_get_code":{"code_sha256":"92702d141fa25fd0"}},{"arxiv_id":"2402.05639","paper":"/paper/nonparametric-instrumental-variable-2","title":"Nonparametric Instrumental Variable Regression through Stochastic Approximate Gradients","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"caioflp/sagd-iv","path":"src/models/sagdiv.py","file_url":"https://github.com/caioflp/sagd-iv/blob/HEAD/src/models/sagdiv.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"06fc036884f4989c","mcp_get_code":{"code_sha256":"06fc036884f4989c"}},{"arxiv_id":"2401.06532","paper":"/paper/inters-unlocking-the-power-of-large-language","title":"INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DaoD/INTERS","path":"evaluation/qdu-tasks/eval_rerank.py","file_url":"https://github.com/DaoD/INTERS/blob/HEAD/evaluation/qdu-tasks/eval_rerank.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5cf8f57b0919504b","mcp_get_code":{"code_sha256":"5cf8f57b0919504b"}},{"arxiv_id":"2312.04601","paper":"/paper/estimating-frechet-bounds-for-validating","title":"Weak Supervision Performance Evaluation via Partial Identification","date":"2023-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"felipemaiapolo/wsbounds","path":"wsbounds/eval_pws.py","file_url":"https://github.com/felipemaiapolo/wsbounds/blob/HEAD/wsbounds/eval_pws.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"104935a2b237ae7a","mcp_get_code":{"code_sha256":"104935a2b237ae7a"}},{"arxiv_id":"2310.10543","paper":"/paper/vipe-visualise-pretty-much-everything","title":"ViPE: Visualise Pretty-much Everything","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hazel1994/vipe","path":"lyric_canvas/build_lyric_canvas.py","file_url":"https://github.com/hazel1994/vipe/blob/HEAD/lyric_canvas/build_lyric_canvas.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c84d84309dad43b1","mcp_get_code":{"code_sha256":"c84d84309dad43b1"}},{"arxiv_id":"2310.10501","paper":"/paper/nemo-guardrails-a-toolkit-for-controllable","title":"NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NVIDIA/NeMo-Guardrails","path":"nemoguardrails/guardrails/guardrails_types.py","file_url":"https://github.com/NVIDIA/NeMo-Guardrails/blob/HEAD/nemoguardrails/guardrails/guardrails_types.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"bf5f7e555db0492e","mcp_get_code":{"code_sha256":"bf5f7e555db0492e"}},{"arxiv_id":"2305.14327","paper":"/paper/dynosaur-a-dynamic-growth-paradigm-for","title":"Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"WadeYin9712/Dynosaur","path":"code/instruction_generation/generate_tasks_with_description.py","file_url":"https://github.com/WadeYin9712/Dynosaur/blob/HEAD/code/instruction_generation/generate_tasks_with_description.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":"341a6b8ffd520b77","mcp_get_code":{"code_sha256":"341a6b8ffd520b77"}},{"arxiv_id":"2109.03630","paper":"/paper/discrete-and-soft-prompting-for-multilingual","title":"Discrete and Soft Prompting for Multilingual Models","date":"2021-09-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mprompting/xlmrprompt","path":"finetuning/data_loader/bert_formatting.py","file_url":"https://github.com/mprompting/xlmrprompt/blob/HEAD/finetuning/data_loader/bert_formatting.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"de4d375e6fe86346","mcp_get_code":{"code_sha256":"de4d375e6fe86346"}},{"arxiv_id":"2008.12579","paper":"/paper/the-adapter-bot-all-in-one-controllable","title":"The Adapter-Bot: All-In-One Controllable Conversational Model","date":"2020-08-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HLTCHKUST/adapterbot","path":"utils/helper.py","file_url":"https://github.com/HLTCHKUST/adapterbot/blob/HEAD/utils/helper.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ad31d45e980abd6c","mcp_get_code":{"code_sha256":"ad31d45e980abd6c"}},{"arxiv_id":"2008.06471","paper":"/paper/self-sampling-for-neural-point-cloud","title":"Self-Sampling for Neural Point Cloud Consolidation","date":"2020-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"galmetzer/self-sample","path":"util.py","file_url":"https://github.com/galmetzer/self-sample/blob/HEAD/util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"423ca44dc6df8a92","mcp_get_code":{"code_sha256":"423ca44dc6df8a92"}},{"arxiv_id":"1907.01180","paper":"/paper/conservative-q-improvement-reinforcement","title":"Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy","date":"2019-07-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AMR-/Conservative-Q-Improvement","path":"cqi_cpp/src/wrapper/example.py","file_url":"https://github.com/AMR-/Conservative-Q-Improvement/blob/HEAD/cqi_cpp/src/wrapper/example.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d2abb2a6977651a5","mcp_get_code":{"code_sha256":"d2abb2a6977651a5"}},{"arxiv_id":"1906.06187","paper":"/paper/nlprolog-reasoning-with-weak-unification-for-1","title":"NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language","date":"2019-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leonweber/nlprolog","path":"preprocessing.py","file_url":"https://github.com/leonweber/nlprolog/blob/HEAD/preprocessing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d57be32fa41e563","mcp_get_code":{"code_sha256":"0d57be32fa41e563"}},{"arxiv_id":"1703.03864","paper":"/paper/evolution-strategies-as-a-scalable","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","date":"2017-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"czen88/qtrader","path":"params.py","file_url":"https://github.com/czen88/qtrader/blob/HEAD/params.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":"9ceef2b01661079b","mcp_get_code":{"code_sha256":"9ceef2b01661079b"}},{"arxiv_id":"1606.04797","paper":"/paper/v-net-fully-convolutional-neural-networks-for","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","date":"2016-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YellowLight021/Vnet","path":"luna.py","file_url":"https://github.com/YellowLight021/Vnet/blob/HEAD/luna.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":"60f0bebd8c9d6ac0","mcp_get_code":{"code_sha256":"60f0bebd8c9d6ac0"}},{"arxiv_id":"1603.06021","paper":"/paper/a-fast-unified-model-for-parsing-and-sentence","title":"A Fast Unified Model for Parsing and Sentence Understanding","date":"2016-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NYU-MLL/spinn","path":"python/spinn/models/base.py","file_url":"https://github.com/NYU-MLL/spinn/blob/HEAD/python/spinn/models/base.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ad8f82f72df0f106","mcp_get_code":{"code_sha256":"ad8f82f72df0f106"}},{"arxiv_id":"1406.6247","paper":"/paper/recurrent-models-of-visual-attention","title":"Recurrent Models of Visual Attention","date":"2014-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"theowu23451/DRAM","path":"model/utils.py","file_url":"https://github.com/theowu23451/DRAM/blob/HEAD/model/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eae54352422ca8a7","mcp_get_code":{"code_sha256":"eae54352422ca8a7"}}]}