{"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/model-slug","entry":"model_slug","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":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":5,"n_samples_ran":4,"n_samples_fingerprinted":3,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":1},"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":"2609.00384","paper":"/paper/arxiv-2609-00384","title":"RestoreBench: Can AI Agents Restore Power Flow Convergence?","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"Mansutti081/RestoreBench","path":"restorebench/llm/models.py","file_url":"https://github.com/Mansutti081/RestoreBench/blob/HEAD/restorebench/llm/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0981bb0a4e9ed4a7","mcp_get_code":{"code_sha256":"0981bb0a4e9ed4a7"}},{"arxiv_id":"2608.26119","paper":"/paper/arxiv-2608-26119","title":"DeflectBench: A Benchmark for Evaluating Rhetorical Fallacy Generation in LLMs","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"ArtKanke/DeflectBench","path":"generation/core.py","file_url":"https://github.com/ArtKanke/DeflectBench/blob/HEAD/generation/core.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f08c31f49e36fb1e","mcp_get_code":{"code_sha256":"f08c31f49e36fb1e"}},{"arxiv_id":"2608.12324","paper":"/paper/arxiv-2608-12324","title":"When AI Is Your Pastor: A Benchmark for Theological Triage and Pastoral Guidance in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"FideAI/fmg-bench","path":"benchmark/system_benchmark/models.py","file_url":"https://github.com/FideAI/fmg-bench/blob/HEAD/benchmark/system_benchmark/models.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"424f79ce463b54a7","mcp_get_code":{"code_sha256":"424f79ce463b54a7"}},{"arxiv_id":"2607.03929","paper":"/paper/arxiv-2607-03929","title":"Probe, Don't Prompt: A Hidden-State Probe for Metadata Filtering in Multi-Meta-RAG","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"mxpoliakov/Multi-Meta-RAG","path":"probe_artifacts.py","file_url":"https://github.com/mxpoliakov/Multi-Meta-RAG/blob/HEAD/probe_artifacts.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"962ab679ff841786","mcp_get_code":{"code_sha256":"962ab679ff841786"}},{"arxiv_id":"2606.11854","paper":"/paper/arxiv-2606-11854","title":"Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"jinymusim/ART","path":"src/reasoning_with_art/config.py","file_url":"https://github.com/jinymusim/ART/blob/HEAD/src/reasoning_with_art/config.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"e2ea59d8ffd7feee","mcp_get_code":{"code_sha256":"e2ea59d8ffd7feee"}}]}