{"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/get-messages","entry":"get_messages","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":6,"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":6,"n_samples_ran":4,"n_samples_fingerprinted":1,"n_places":6,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":3,"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":"2505.10981","paper":"/paper/2505-10981","title":"Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory","date":"2025-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MraDonkey/rethinking_prompting","path":"model.py","file_url":"https://github.com/MraDonkey/rethinking_prompting/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"22f36d100d431b72","mcp_get_code":{"code_sha256":"22f36d100d431b72"}},{"arxiv_id":"2408.08067","paper":"/paper/ragchecker-a-fine-grained-framework-for","title":"RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation","date":"2024-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/ragchecker","path":"rag_baselines/generation.py","file_url":"https://github.com/amazon-science/ragchecker/blob/HEAD/rag_baselines/generation.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":"ff81b5723118624d","mcp_get_code":{"code_sha256":"ff81b5723118624d"}},{"arxiv_id":"2406.13375","paper":"/paper/aliice-evaluating-positional-fine-grained","title":"ALiiCE: Evaluating Positional Fine-grained Citation Generation","date":"2024-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ylXuu/ALiiCE","path":"generate.py","file_url":"https://github.com/ylXuu/ALiiCE/blob/HEAD/generate.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":"d3454cb82cfad8b3","mcp_get_code":{"code_sha256":"d3454cb82cfad8b3"}},{"arxiv_id":"2405.15383","paper":"/paper/generating-code-world-models-with-large","title":"Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicoladainese96/code-world-models","path":"src/code_helpers.py","file_url":"https://github.com/nicoladainese96/code-world-models/blob/HEAD/src/code_helpers.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":"b4b79bcfa9a97f09","mcp_get_code":{"code_sha256":"b4b79bcfa9a97f09"}},{"arxiv_id":"2404.19094","paper":"/paper/in-context-symbolic-regression-leveraging","title":"In-Context Symbolic Regression: Leveraging Large Language Models for Function Discovery","date":"2024-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"merlerm/in-context-symbolic-regression","path":"utils.py","file_url":"https://github.com/merlerm/in-context-symbolic-regression/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"996ffcf5697d3b6a","mcp_get_code":{"code_sha256":"996ffcf5697d3b6a"}},{"arxiv_id":"2025.findings-acl.491","paper":null,"title":"arXiv:2025.findings-acl.491","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"biodatlab/ec-raft","path":"evaluate.py","file_url":"https://github.com/biodatlab/ec-raft/blob/HEAD/evaluate.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":"3301e9b305e3c1b5","mcp_get_code":{"code_sha256":"3301e9b305e3c1b5"}}]}