{"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/load-jsonl-file","entry":"load_jsonl_file","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":5,"n_papers_ran":3,"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":5,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"unverified":2},"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":"2606.29920","paper":"/paper/arxiv-2606-29920","title":"Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"THU-KEG/RuVerBench","path":"code/run_judges/agenticcoding/compare_score_results.py","file_url":"https://github.com/THU-KEG/RuVerBench/blob/HEAD/code/run_judges/agenticcoding/compare_score_results.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0b08cc270a553df7","mcp_get_code":{"code_sha256":"0b08cc270a553df7"}},{"arxiv_id":"2602.11570","paper":"/paper/arxiv-2602-11570","title":"PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"wonderful9462/PRIME","path":"evaluation/calculate_accuracy.py","file_url":"https://github.com/wonderful9462/PRIME/blob/HEAD/evaluation/calculate_accuracy.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"59a153f4788626a3","mcp_get_code":{"code_sha256":"59a153f4788626a3"}},{"arxiv_id":"2509.23499","paper":"/paper/arxiv-2509-23499","title":"Multi-modal Data Spectrum: Multi-modal Datasets are Multi-dimensional","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"divyam3897/multimodal-spectrum","path":"eval/compare_model_performance.py","file_url":"https://github.com/divyam3897/multimodal-spectrum/blob/HEAD/eval/compare_model_performance.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"68ca259a0a354c2c","mcp_get_code":{"code_sha256":"68ca259a0a354c2c"}},{"arxiv_id":"2505.24550","paper":"/paper/a-thought-efficient-reasoning-via","title":"A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings","date":"2025-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ai9stars/astar-thought","path":"long_cot_compress_v1.py","file_url":"https://github.com/ai9stars/astar-thought/blob/HEAD/long_cot_compress_v1.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"796e03f0a9c30ea5","mcp_get_code":{"code_sha256":"796e03f0a9c30ea5"}},{"arxiv_id":"2025.findings-emnlp.1015","paper":null,"title":"arXiv:2025.findings-emnlp.1015","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"fzp0424/MT-R1-Zero","path":"eval/vllm_inference.py","file_url":"https://github.com/fzp0424/MT-R1-Zero/blob/HEAD/eval/vllm_inference.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":"b668cca432858d9f","mcp_get_code":{"code_sha256":"b668cca432858d9f"}}]}