{"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/call-model","entry":"call_model","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":9,"n_papers_ran":4,"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":11,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"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":"2604.06834","paper":"/paper/arxiv-2604-06834","title":"On the Step Length Confounding in LLM Reasoning Data Selection","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"wangbing1416/ASLEC","path":"data_syn_gptoss.py","file_url":"https://github.com/wangbing1416/ASLEC/blob/HEAD/data_syn_gptoss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"038676f8a60ba539","mcp_get_code":{"code_sha256":"038676f8a60ba539"}},{"arxiv_id":"2604.06834","paper":"/paper/arxiv-2604-06834","title":"On the Step Length Confounding in LLM Reasoning Data Selection","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"wangbing1416/ASLEC","path":"data_syn_qwen3_32b.py","file_url":"https://github.com/wangbing1416/ASLEC/blob/HEAD/data_syn_qwen3_32b.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"73a355b5b67882f5","mcp_get_code":{"code_sha256":"73a355b5b67882f5"}},{"arxiv_id":"2604.06834","paper":"/paper/arxiv-2604-06834","title":"On the Step Length Confounding in LLM Reasoning Data Selection","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"wangbing1416/ASLEC","path":"data_syn_qwq_32b.py","file_url":"https://github.com/wangbing1416/ASLEC/blob/HEAD/data_syn_qwq_32b.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dd79b2a8e07e5a49","mcp_get_code":{"code_sha256":"dd79b2a8e07e5a49"}},{"arxiv_id":"2602.10715","paper":"/paper/arxiv-2602-10715","title":"Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"xjtuleeyf/Locomo-Plus","path":"evaluation_framework/task_eval/llm_as_judge.py","file_url":"https://github.com/xjtuleeyf/Locomo-Plus/blob/HEAD/evaluation_framework/task_eval/llm_as_judge.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7e92aca251456902","mcp_get_code":{"code_sha256":"7e92aca251456902"}},{"arxiv_id":"2601.02578","paper":"/paper/arxiv-2601-02578","title":"DataParasite Enables Scalable and Repurposable Online Data Curation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"mengysun/DataParasite","path":"src/data_parasite.py","file_url":"https://github.com/mengysun/DataParasite/blob/HEAD/src/data_parasite.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"85d3712a61fec456","mcp_get_code":{"code_sha256":"85d3712a61fec456"}},{"arxiv_id":"2506.11763","paper":"/paper/deepresearch-bench-a-comprehensive-benchmark","title":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","date":"2025-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ayanami0730/deep_research_bench","path":"utils/api.py","file_url":"https://github.com/ayanami0730/deep_research_bench/blob/HEAD/utils/api.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":"8c4b44ca751e88c7","mcp_get_code":{"code_sha256":"8c4b44ca751e88c7"}},{"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-abalations-random.py","file_url":"https://github.com/C-anwoy/Cross-Task-ICL/blob/HEAD/LLAMA-abalations-random.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"00eba4d4d2e34691","mcp_get_code":{"code_sha256":"00eba4d4d2e34691"}},{"arxiv_id":"2402.16058","paper":"/paper/say-more-with-less-understanding-prompt","title":"Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression","date":"2024-02-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openmatch/gist-coco","path":"src/inference/generalize/get_generalize_instruction_data.py","file_url":"https://github.com/openmatch/gist-coco/blob/HEAD/src/inference/generalize/get_generalize_instruction_data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"185759d79e24efed","mcp_get_code":{"code_sha256":"185759d79e24efed"}},{"arxiv_id":"2402.10811","paper":"/paper/quantifying-the-persona-effect-in-llm","title":"Quantifying the Persona Effect in LLM Simulations","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cambridgeltl/persona_effect","path":"Dependency.py","file_url":"https://github.com/cambridgeltl/persona_effect/blob/HEAD/Dependency.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"04c4d6d4cb132a44","mcp_get_code":{"code_sha256":"04c4d6d4cb132a44"}},{"arxiv_id":"2305.18395","paper":"/paper/knowledge-augmented-reasoning-distillation-1","title":"Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks","date":"2023-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nardien/kard","path":"generate_explanations.py","file_url":"https://github.com/nardien/kard/blob/HEAD/generate_explanations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"11adf9c948ae2a78","mcp_get_code":{"code_sha256":"11adf9c948ae2a78"}},{"arxiv_id":"2212.10511","paper":"/paper/when-not-to-trust-language-models","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","date":"2022-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alextmallen/adaptive-retrieval","path":"run_model.py","file_url":"https://github.com/alextmallen/adaptive-retrieval/blob/HEAD/run_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"098c21c81fd6e9e8","mcp_get_code":{"code_sha256":"098c21c81fd6e9e8"}}]}