{"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/generate-text","entry":"generate_text","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":20,"n_papers_ran":7,"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":21,"n_samples_ran":7,"n_samples_fingerprinted":0,"n_places":21,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":5,"unverified":14},"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":"2606.11712","paper":"/paper/arxiv-2606-11712","title":"Substrate Asymmetry in User-Side Memory: A Diagnostic Framework","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"EpistemicaLab/substrate-asymmetry-memory","path":"bench/experiments/31_runner.py","file_url":"https://github.com/EpistemicaLab/substrate-asymmetry-memory/blob/HEAD/bench/experiments/31_runner.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":"df6e69ae71000442","mcp_get_code":{"code_sha256":"df6e69ae71000442"}},{"arxiv_id":"2605.11317","paper":"/paper/arxiv-2605-11317","title":"SOMA: Efficient Multi-turn LLM Serving via Small Language Model","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"LabRAI/SOMA","path":"soma/pipeline.py","file_url":"https://github.com/LabRAI/SOMA/blob/HEAD/soma/pipeline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"375a736e73709078","mcp_get_code":{"code_sha256":"375a736e73709078"}},{"arxiv_id":"2509.07730","paper":"/paper/arxiv-2509-07730","title":"M-BRe: Discovering Training Samples for Relation Extraction from Unlabeled Texts with Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"Lzx-ZBC/M-BRe","path":"NER/bbn_afet/binary-fgner.py","file_url":"https://github.com/Lzx-ZBC/M-BRe/blob/HEAD/NER/bbn_afet/binary-fgner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bf15ee34211787ff","mcp_get_code":{"code_sha256":"bf15ee34211787ff"}},{"arxiv_id":"2509.07730","paper":"/paper/arxiv-2509-07730","title":"M-BRe: Discovering Training Samples for Relation Extraction from Unlabeled Texts with Large Language Models","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"Lzx-ZBC/M-BRe","path":"NER/bbn_afet/multi-fgner.py","file_url":"https://github.com/Lzx-ZBC/M-BRe/blob/HEAD/NER/bbn_afet/multi-fgner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0a20307e453bc955","mcp_get_code":{"code_sha256":"0a20307e453bc955"}},{"arxiv_id":"2502.20122","paper":"/paper/self-training-elicits-concise-reasoning-in","title":"Self-Training Elicits Concise Reasoning in Large Language Models","date":"2025-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tergelmunkhbat/concise-reasoning","path":"src/training_utils.py","file_url":"https://github.com/tergelmunkhbat/concise-reasoning/blob/HEAD/src/training_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"84abbf776f80eaf8","mcp_get_code":{"code_sha256":"84abbf776f80eaf8"}},{"arxiv_id":"2412.06660","paper":"/paper/mumu-llama-multi-modal-music-understanding","title":"MuMu-LLaMA: Multi-modal Music Understanding and Generation via Large Language Models","date":null,"month_inferred_from_arxiv_id":"2024-12","title_source":"archive","repo":"shansongliu/M2UGen","path":"DataSet/MUEdit/mistral.py","file_url":"https://github.com/shansongliu/M2UGen/blob/HEAD/DataSet/MUEdit/mistral.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f016081a436c0aff","mcp_get_code":{"code_sha256":"f016081a436c0aff"}},{"arxiv_id":"2411.05037","paper":"/paper/towards-interpreting-language-models-a-case","title":"Towards Interpreting Language Models: A Case Study in Multi-Hop Reasoning","date":"2024-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"msakarvadia/attentionlens","path":"demos/measure_toxicity.py","file_url":"https://github.com/msakarvadia/attentionlens/blob/HEAD/demos/measure_toxicity.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c64dd03c9f019df6","mcp_get_code":{"code_sha256":"c64dd03c9f019df6"}},{"arxiv_id":"2410.17196","paper":"/paper/voicebench-benchmarking-llm-based-voice","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","date":"2024-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"matthewcym/voicebench","path":"src/models/diva.py","file_url":"https://github.com/matthewcym/voicebench/blob/HEAD/src/models/diva.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":"124d5d71fae7e5a3","mcp_get_code":{"code_sha256":"124d5d71fae7e5a3"}},{"arxiv_id":"2408.13467","paper":"/paper/llamaduo-llmops-pipeline-for-seamless","title":"LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs","date":"2024-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deep-diver/llamaduo","path":"src/gen/async_generate_data_gemini.py","file_url":"https://github.com/deep-diver/llamaduo/blob/HEAD/src/gen/async_generate_data_gemini.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":"a1849d123c6ba549","mcp_get_code":{"code_sha256":"a1849d123c6ba549"}},{"arxiv_id":"2406.04306","paper":"/paper/semantically-diverse-language-generation-for","title":"Semantically Diverse Language Generation for Uncertainty Estimation in Language Models","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ml-jku/SDLG","path":"sdlg.py","file_url":"https://github.com/ml-jku/SDLG/blob/HEAD/sdlg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"code_sha256_prefix":"a701b90b916f5466","mcp_get_code":{"code_sha256":"a701b90b916f5466"}},{"arxiv_id":"2406.00215","paper":"/paper/benchmarking-the-communication-competence-of","title":"HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent","date":null,"month_inferred_from_arxiv_id":"2024-06","title_source":"archive","repo":"jie-jw-wu/human-eval-comm","path":"generate_response.py","file_url":"https://github.com/jie-jw-wu/human-eval-comm/blob/HEAD/generate_response.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7f8144a905f5b101","mcp_get_code":{"code_sha256":"7f8144a905f5b101"}},{"arxiv_id":"2404.11262","paper":"/paper/sampling-based-pseudo-likelihood-for","title":"Sampling-based Pseudo-Likelihood for Membership Inference Attacks","date":"2024-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlp-titech/samia","path":"src/sampling.py","file_url":"https://github.com/nlp-titech/samia/blob/HEAD/src/sampling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0ff086b8ebd54874","mcp_get_code":{"code_sha256":"0ff086b8ebd54874"}},{"arxiv_id":"2404.00152","paper":"/paper/on-the-fly-definition-augmentation-of-llms","title":"On-the-fly Definition Augmentation of LLMs for Biomedical NER","date":"2024-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/beacon","path":"calls/openai_call.py","file_url":"https://github.com/allenai/beacon/blob/HEAD/calls/openai_call.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":"85b409d4935c8b83","mcp_get_code":{"code_sha256":"85b409d4935c8b83"}},{"arxiv_id":"2403.04706","paper":"/paper/common-7b-language-models-already-possess","title":"Common 7B Language Models Already Possess Strong Math Capabilities","date":"2024-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jerrywu-code/susgen","path":"src/template.py","file_url":"https://github.com/jerrywu-code/susgen/blob/HEAD/src/template.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aa963276f597a210","mcp_get_code":{"code_sha256":"aa963276f597a210"}},{"arxiv_id":"2402.12483","paper":"/paper/artifacts-or-abduction-how-do-llms-answer","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nbalepur/mcqa-artifacts","path":"model/run_hf.py","file_url":"https://github.com/nbalepur/mcqa-artifacts/blob/HEAD/model/run_hf.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"20ecd73683b53d64","mcp_get_code":{"code_sha256":"20ecd73683b53d64"}},{"arxiv_id":"2402.05785","paper":"/paper/limits-of-transformer-language-models-on","title":"Limits of Transformer Language Models on Learning to Compose Algorithms","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ibm/limitations-lm-algorithmic-compositional-learning","path":"prompting_experiment_utils/prompt_llm.py","file_url":"https://github.com/ibm/limitations-lm-algorithmic-compositional-learning/blob/HEAD/prompting_experiment_utils/prompt_llm.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":"95228c89a9638a61","mcp_get_code":{"code_sha256":"95228c89a9638a61"}},{"arxiv_id":"2310.16040","paper":"/paper/instruct-and-extract-instruction-tuning-for","title":"Instruct and Extract: Instruction Tuning for On-Demand Information Extraction","date":"2023-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yzjiao/on-demand-ie","path":"data_generation/generate_text.py","file_url":"https://github.com/yzjiao/on-demand-ie/blob/HEAD/data_generation/generate_text.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a6f428fed9e294b0","mcp_get_code":{"code_sha256":"a6f428fed9e294b0"}},{"arxiv_id":"2310.14053","paper":"/paper/beyond-accuracy-evaluating-self-consistency","title":"Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"marcusm117/identitychain","path":"examples/run_identity_chain_huggingface.py","file_url":"https://github.com/marcusm117/identitychain/blob/HEAD/examples/run_identity_chain_huggingface.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7eab47e294a8f31c","mcp_get_code":{"code_sha256":"7eab47e294a8f31c"}},{"arxiv_id":"2309.16211","paper":"/paper/vdc-versatile-data-cleanser-for-detecting","title":"VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zihao-ai/vdc","path":"vdc/cleanser.py","file_url":"https://github.com/zihao-ai/vdc/blob/HEAD/vdc/cleanser.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b3a3983654d23cc7","mcp_get_code":{"code_sha256":"b3a3983654d23cc7"}},{"arxiv_id":"2206.05941","paper":"/paper/towards-universal-sequence-representation","title":"Towards Universal Sequence Representation Learning for Recommender Systems","date":"2022-06-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/unisrec","path":"dataset/preprocessing/process_or.py","file_url":"https://github.com/rucaibox/unisrec/blob/HEAD/dataset/preprocessing/process_or.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3b6af7fa6012d8c4","mcp_get_code":{"code_sha256":"3b6af7fa6012d8c4"}},{"arxiv_id":"2025.naacl-long.65","paper":null,"title":"arXiv:2025.naacl-long.65","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Zehong-Wang/TANS","path":"TANS/preprocess/airport_graphs.py","file_url":"https://github.com/Zehong-Wang/TANS/blob/HEAD/TANS/preprocess/airport_graphs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2e37bdf0888f6f82","mcp_get_code":{"code_sha256":"2e37bdf0888f6f82"}}]}