{"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/make-prompt","entry":"make_prompt","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":19,"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":20,"n_samples_ran":13,"n_samples_fingerprinted":6,"n_places":21,"n_places_pointer_only":12,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":7,"ran_fixture":0,"ran":6,"unverified":7},"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":"2609.12653","paper":"/paper/arxiv-2609-12653","title":"SWARM: A Multilingual Human-Annotated Dataset for Russian Propaganda Detection in Search Engine Results","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"manueltonneau/swarm","path":"swarm/common.py","file_url":"https://github.com/manueltonneau/swarm/blob/HEAD/swarm/common.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0e6a0cd98d63ca44","mcp_get_code":{"code_sha256":"0e6a0cd98d63ca44"}},{"arxiv_id":"2606.00619","paper":"/paper/arxiv-2606-00619","title":"MemPro: Agentic Memory Systems as Evolvable Programs","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"wanghai673/MemPro","path":"MemPro/hotpotqa/versions/v_best/working_prompts.py","file_url":"https://github.com/wanghai673/MemPro/blob/HEAD/MemPro/hotpotqa/versions/v_best/working_prompts.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bd08cb277bcf62c1","mcp_get_code":{"code_sha256":"bd08cb277bcf62c1"}},{"arxiv_id":"2605.01148","paper":"/paper/arxiv-2605-01148","title":"Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"goodfire-ai/arithmetic-wild","path":"src/fourier_probes/fourier_probes_sweep.py","file_url":"https://github.com/goodfire-ai/arithmetic-wild/blob/HEAD/src/fourier_probes/fourier_probes_sweep.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b086cc55c7031e8d","mcp_get_code":{"code_sha256":"b086cc55c7031e8d"}},{"arxiv_id":"2604.16132","paper":"/paper/arxiv-2604-16132","title":"Can LLMs Understand the Impact of Trauma? Costs and Benefits of LLMs Coding the Interviews of Firearm Violence Survivors","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"jhzsquared/AIvsHumanCoding","path":"travail_code/llm_topic.py","file_url":"https://github.com/jhzsquared/AIvsHumanCoding/blob/HEAD/travail_code/llm_topic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a1d37b95239f4557","mcp_get_code":{"code_sha256":"a1d37b95239f4557"}},{"arxiv_id":"2604.05818","paper":"/paper/arxiv-2604-05818","title":"WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"zhuyjan/WikiSeeker","path":"gen_refined_queries.py","file_url":"https://github.com/zhuyjan/WikiSeeker/blob/HEAD/gen_refined_queries.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":"93de3112886f0ae2","mcp_get_code":{"code_sha256":"93de3112886f0ae2"}},{"arxiv_id":"2601.17823","paper":"/paper/arxiv-2601-17823","title":"DIETA: A Decoder-only transformer-based model for Italian-English machine TrAnslation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"pkasela/DIETA-Machine-Translation","path":"src/translate.py","file_url":"https://github.com/pkasela/DIETA-Machine-Translation/blob/HEAD/src/translate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e132f3b8af6f483b","mcp_get_code":{"code_sha256":"e132f3b8af6f483b"}},{"arxiv_id":"2509.07730","paper":"/paper/arxiv-2509-07730","title":"M-BRe: Discovering Training Samples for Relation Extraction from Unlabeled Texts with Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"Lzx-ZBC/M-BRe","path":"NER/bbn_afet/binary-fgner.py","file_url":"https://github.com/Lzx-ZBC/M-BRe/blob/HEAD/NER/bbn_afet/binary-fgner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cfbc649efbcdf87a","mcp_get_code":{"code_sha256":"cfbc649efbcdf87a"}},{"arxiv_id":"2509.07730","paper":"/paper/arxiv-2509-07730","title":"M-BRe: Discovering Training Samples for Relation Extraction from Unlabeled Texts with Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"Lzx-ZBC/M-BRe","path":"NER/bbn_afet/multi-fgner.py","file_url":"https://github.com/Lzx-ZBC/M-BRe/blob/HEAD/NER/bbn_afet/multi-fgner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e9f46da936abe1ae","mcp_get_code":{"code_sha256":"e9f46da936abe1ae"}},{"arxiv_id":"2509.07730","paper":"/paper/arxiv-2509-07730","title":"M-BRe: Discovering Training Samples for Relation Extraction from Unlabeled Texts with Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"Lzx-ZBC/M-BRe","path":"NER/ontonotes_uf/multi-fgner.py","file_url":"https://github.com/Lzx-ZBC/M-BRe/blob/HEAD/NER/ontonotes_uf/multi-fgner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d568a7b50137cda","mcp_get_code":{"code_sha256":"0d568a7b50137cda"}},{"arxiv_id":"2505.05505","paper":"/paper/apply-hierarchical-chain-of-generation-to","title":"Apply Hierarchical-Chain-of-Generation to Complex Attributes Text-to-3D Generation","date":"2025-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Wakals/GASCOL","path":"threestudio/gpt/PE.py","file_url":"https://github.com/Wakals/GASCOL/blob/HEAD/threestudio/gpt/PE.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":"a738297eb782fb24","mcp_get_code":{"code_sha256":"a738297eb782fb24"}},{"arxiv_id":"2503.16212","paper":"/paper/mathfusion-enhancing-mathematic-problem","title":"MathFusion: Enhancing Mathematic Problem-solving of LLM through Instruction Fusion","date":"2025-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qizhipei/mathfusion","path":"evaluation/dart_math/olympiadbench.py","file_url":"https://github.com/qizhipei/mathfusion/blob/HEAD/evaluation/dart_math/olympiadbench.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":"e6eeb93f5a059925","mcp_get_code":{"code_sha256":"e6eeb93f5a059925"}},{"arxiv_id":"2501.18623","paper":"/paper/vlmaterial-procedural-material-generation","title":"VLMaterial: Procedural Material Generation with Large Vision-Language Models","date":"2025-01-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mit-gfx/VLMaterial","path":"data_scripts/gen_programs_llm_async.py","file_url":"https://github.com/mit-gfx/VLMaterial/blob/HEAD/data_scripts/gen_programs_llm_async.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":"3884ccd0ec99644e","mcp_get_code":{"code_sha256":"3884ccd0ec99644e"}},{"arxiv_id":"2407.13690","paper":"/paper/dart-math-difficulty-aware-rejection-tuning-1","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hkust-nlp/dart-math","path":"dart_math/olympiadbench.py","file_url":"https://github.com/hkust-nlp/dart-math/blob/HEAD/dart_math/olympiadbench.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e6eeb93f5a059925","mcp_get_code":{"code_sha256":"e6eeb93f5a059925"}},{"arxiv_id":"2406.15885","paper":"/paper/the-music-maestro-or-the-musically-challenged","title":"The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models","date":"2024-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zcli-charlie/ziqi-eval","path":"src/five-shot.py","file_url":"https://github.com/zcli-charlie/ziqi-eval/blob/HEAD/src/five-shot.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e5b9d3d8fb4bd79d","mcp_get_code":{"code_sha256":"e5b9d3d8fb4bd79d"}},{"arxiv_id":"2406.09948","paper":"/paper/blend-a-benchmark-for-llms-on-everyday","title":"BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlee0212/BLEnD","path":"model_inference.py","file_url":"https://github.com/nlee0212/BLEnD/blob/HEAD/model_inference.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"debb9aac44c9ee82","mcp_get_code":{"code_sha256":"debb9aac44c9ee82"}},{"arxiv_id":"2405.10548","paper":"/paper/language-models-can-exploit-cross-task-in","title":"Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks","date":"2024-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"C-anwoy/Cross-Task-ICL","path":"LLAMA-psudo.py","file_url":"https://github.com/C-anwoy/Cross-Task-ICL/blob/HEAD/LLAMA-psudo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"64e4f9b4c5d53a6b","mcp_get_code":{"code_sha256":"64e4f9b4c5d53a6b"}},{"arxiv_id":"2404.02418","paper":"/paper/auxiliary-task-demands-mask-the-capabilities","title":"Auxiliary task demands mask the capabilities of smaller language models","date":"2024-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jennhu/lm-task-demands","path":"src/metrics/crt.py","file_url":"https://github.com/jennhu/lm-task-demands/blob/HEAD/src/metrics/crt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"29db9cb7090f2405","mcp_get_code":{"code_sha256":"29db9cb7090f2405"}},{"arxiv_id":"2403.20009","paper":"/paper/on-large-language-models-hallucination-with","title":"On Large Language Models' Hallucination with Regard to Known Facts","date":"2024-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dcdsf321/known_fact_hallucination","path":"get_model_output_example_opt.py","file_url":"https://github.com/dcdsf321/known_fact_hallucination/blob/HEAD/get_model_output_example_opt.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c7189a783afded05","mcp_get_code":{"code_sha256":"c7189a783afded05"}},{"arxiv_id":"2403.02966","paper":"/paper/evidence-focused-fact-summarization-for","title":"Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering","date":"2024-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kk13332488/EFSum","path":"hallucination_check/hallucination_checking.py","file_url":"https://github.com/kk13332488/EFSum/blob/HEAD/hallucination_check/hallucination_checking.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6cd4220d01988589","mcp_get_code":{"code_sha256":"6cd4220d01988589"}},{"arxiv_id":"2308.16705","paper":"/paper/crehate-cross-cultural-re-annotation-of","title":"Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis","date":"2023-08-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlee0212/crehate","path":"llm_inference.py","file_url":"https://github.com/nlee0212/crehate/blob/HEAD/llm_inference.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c083b5f35fb91864","mcp_get_code":{"code_sha256":"c083b5f35fb91864"}},{"arxiv_id":"2302.12239","paper":"/paper/what-makes-a-language-easy-to-deep-learn","title":"What makes a language easy to deep-learn? Deep neural networks and humans similarly benefit from compositional structure","date":"2023-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lgalke/easy2deeplearn","path":"lang2prompt.py","file_url":"https://github.com/lgalke/easy2deeplearn/blob/HEAD/lang2prompt.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"246b6d3de7325350","mcp_get_code":{"code_sha256":"246b6d3de7325350"}}]}