{"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/batch-generate","entry":"batch_generate","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":2,"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":2,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":4,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":0,"unverified":4},"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":"2606.14122","paper":"/paper/arxiv-2606-14122","title":"Beyond Perplexity: UTF-8 Validity in Byte-aware Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"cynthia/bytecanary","path":"src/bytecanary/evaluate.py","file_url":"https://github.com/cynthia/bytecanary/blob/HEAD/src/bytecanary/evaluate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1e04eaf2590fab35","mcp_get_code":{"code_sha256":"1e04eaf2590fab35"}},{"arxiv_id":"2506.20100","paper":"/paper/mirage-a-benchmark-for-multimodal-information","title":"MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations","date":"2025-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mirage-benchmark/mirage-benchmark","path":"MMMT/src/llm_agents.py","file_url":"https://github.com/mirage-benchmark/mirage-benchmark/blob/HEAD/MMMT/src/llm_agents.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bf40ff2b135468ac","mcp_get_code":{"code_sha256":"bf40ff2b135468ac"}},{"arxiv_id":"2502.04510","paper":"/paper/heterogeneous-swarms-jointly-optimizing-model","title":"Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems","date":"2025-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BunsenFeng/heterogeneous_swarm","path":"search.py","file_url":"https://github.com/BunsenFeng/heterogeneous_swarm/blob/HEAD/search.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2a9ac558452970b5","mcp_get_code":{"code_sha256":"2a9ac558452970b5"}},{"arxiv_id":"2402.17497","paper":"/paper/rear-a-relevance-aware-retrieval-augmented","title":"REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RUCAIBox/REAR","path":"rear/src/inf.py","file_url":"https://github.com/RUCAIBox/REAR/blob/HEAD/rear/src/inf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1fa4c96d77ce5f71","mcp_get_code":{"code_sha256":"1fa4c96d77ce5f71"}},{"arxiv_id":"2109.14739","paper":"/paper/multi-task-pre-training-for-plug-and-play","title":"Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System","date":"2021-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"awslabs/pptod","path":"DST/inference_utlis.py","file_url":"https://github.com/awslabs/pptod/blob/HEAD/DST/inference_utlis.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":"157e7d21e425e71b","mcp_get_code":{"code_sha256":"157e7d21e425e71b"}},{"arxiv_id":"2023.emnlp-main.771","paper":null,"title":"arXiv:2023.emnlp-main.771","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Patrick-Ni/KnowEE","path":"src/interactive.py","file_url":"https://github.com/Patrick-Ni/KnowEE/blob/HEAD/src/interactive.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"04c570ef95f1a23e","mcp_get_code":{"code_sha256":"04c570ef95f1a23e"}}]}