{"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/extract-boxed","entry":"extract_boxed","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":12,"n_papers_ran":6,"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":6,"n_samples_fingerprinted":6,"n_places":12,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":5,"unverified":5},"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":"2608.08557","paper":"/paper/arxiv-2608-08557","title":"OpenVisTool: An Open Recipe for Synthesizing Instructive Visual Tool-Use Trajectories","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"Changhao-Xiang/OpenVisTool","path":"distill/filter/evaluate_answer_rule.py","file_url":"https://github.com/Changhao-Xiang/OpenVisTool/blob/HEAD/distill/filter/evaluate_answer_rule.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f1e5290562997ded","mcp_get_code":{"code_sha256":"f1e5290562997ded"}},{"arxiv_id":"2607.28166","paper":"/paper/arxiv-2607-28166","title":"Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"ming053l/C4-dLLM","path":"c4/extract.py","file_url":"https://github.com/ming053l/C4-dLLM/blob/HEAD/c4/extract.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"414a8b03b41334b1","mcp_get_code":{"code_sha256":"414a8b03b41334b1"}},{"arxiv_id":"2607.02510","paper":"/paper/arxiv-2607-02510","title":"Online Safety Monitoring for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"monasch/llm-monitor","path":"python_scripts/add_final_label.py","file_url":"https://github.com/monasch/llm-monitor/blob/HEAD/python_scripts/add_final_label.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5a8fb7969db533be","mcp_get_code":{"code_sha256":"5a8fb7969db533be"}},{"arxiv_id":"2606.31048","paper":"/paper/arxiv-2606-31048","title":"Knowledge Distillation from Large Reasoning Models to Compact Student Models: A Case Study on the John O'Bryan Mathematics Competition","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"TempGaurab/Distillation.John-O-Bryan","path":"rab.py","file_url":"https://github.com/TempGaurab/Distillation.John-O-Bryan/blob/HEAD/rab.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2d4f6ee4beb234ea","mcp_get_code":{"code_sha256":"2d4f6ee4beb234ea"}},{"arxiv_id":"2604.00698","paper":"/paper/arxiv-2604-00698","title":"Learning to Hint for Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Andree-9/HiLL","path":"eval/compute_score.py","file_url":"https://github.com/Andree-9/HiLL/blob/HEAD/eval/compute_score.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"82ab5df795d522c8","mcp_get_code":{"code_sha256":"82ab5df795d522c8"}},{"arxiv_id":"2603.22754","paper":"/paper/arxiv-2603-22754","title":"PRISM: A Dual View of LLM Reasoning through Semantic Flow and Latent Computation","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"chili-lab/PRISM","path":"prism_code/classifier.py","file_url":"https://github.com/chili-lab/PRISM/blob/HEAD/prism_code/classifier.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8d99269d19deb7b8","mcp_get_code":{"code_sha256":"8d99269d19deb7b8"}},{"arxiv_id":"2602.03143","paper":"/paper/arxiv-2602-03143","title":"Self-Hinting Language Models Enhance Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"BaohaoLiao/SAGE","path":"eval/compute_score.py","file_url":"https://github.com/BaohaoLiao/SAGE/blob/HEAD/eval/compute_score.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":"82ab5df795d522c8","mcp_get_code":{"code_sha256":"82ab5df795d522c8"}},{"arxiv_id":"2510.04019","paper":"/paper/arxiv-2510-04019","title":"Simple Policy Gradients for Reasoning with Diffusion Language Models","date":"2025-10-05","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"probablyabot/agrpo","path":"rewards.py","file_url":"https://github.com/probablyabot/agrpo/blob/HEAD/rewards.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4eb074484f3ce4a2","mcp_get_code":{"code_sha256":"4eb074484f3ce4a2"}},{"arxiv_id":"2503.21380","paper":"/paper/challenging-the-boundaries-of-reasoning-an","title":"Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models","date":"2025-03-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/olymmath","path":"local_tester.py","file_url":"https://github.com/rucaibox/olymmath/blob/HEAD/local_tester.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0687ec701d38b338","mcp_get_code":{"code_sha256":"0687ec701d38b338"}},{"arxiv_id":"2502.01618","paper":"/paper/a-probabilistic-inference-approach-to","title":"A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","date":"2025-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Red-Hat-AI-Innovation-Team/its_hub","path":"examples/self-consistency.py","file_url":"https://github.com/Red-Hat-AI-Innovation-Team/its_hub/blob/HEAD/examples/self-consistency.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f91f47e62962bec8","mcp_get_code":{"code_sha256":"f91f47e62962bec8"}},{"arxiv_id":"2410.06634","paper":"/paper/tree-of-problems-improving-structured-problem","title":"Tree of Problems: Improving structured problem solving with compositionality","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"masoudhashemi/AWMS","path":"awms/utils.py","file_url":"https://github.com/masoudhashemi/AWMS/blob/HEAD/awms/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":"432af6a5e4dafb42","mcp_get_code":{"code_sha256":"432af6a5e4dafb42"}},{"arxiv_id":"2404.13925","paper":"/paper/mario-eval-evaluate-your-math-llm-with-your","title":"MARIO Eval: Evaluate Your Math LLM with your Math LLM--A mathematical dataset evaluation toolkit","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mario-math-reasoning/math_evaluation","path":"example_tora_eval.py","file_url":"https://github.com/mario-math-reasoning/math_evaluation/blob/HEAD/example_tora_eval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9815785426c107dd","mcp_get_code":{"code_sha256":"9815785426c107dd"}}]}