{"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-annotations","entry":"get_annotations","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":13,"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":9,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":13,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":7},"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":"2606.10528","paper":"/paper/arxiv-2606-10528","title":"Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"tatsu-lab/alpaca_eval","path":"src/alpaca_eval/analyze.py","file_url":"https://github.com/tatsu-lab/alpaca_eval/blob/HEAD/src/alpaca_eval/analyze.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":"0eb53db38f0faafd","mcp_get_code":{"code_sha256":"0eb53db38f0faafd"}},{"arxiv_id":"2503.18476","paper":"/paper/global-local-tree-search-for-language-guided","title":"Global-Local Tree Search in VLMs for 3D Indoor Scene Generation","date":"2025-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dw-dengwei/TreeSearchGen","path":"retrieve.py","file_url":"https://github.com/dw-dengwei/TreeSearchGen/blob/HEAD/retrieve.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":"375fc4c0fe2a253d","mcp_get_code":{"code_sha256":"375fc4c0fe2a253d"}},{"arxiv_id":"2502.01534","paper":"/paper/preference-leakage-a-contamination-problem-in","title":"Preference Leakage: A Contamination Problem in LLM-as-a-judge","date":"2025-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"david-li0406/preference-leakage","path":"evaluation/Alpaca_Eval2/src/alpaca_eval/analyze.py","file_url":"https://github.com/david-li0406/preference-leakage/blob/HEAD/evaluation/Alpaca_Eval2/src/alpaca_eval/analyze.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0eb53db38f0faafd","mcp_get_code":{"code_sha256":"0eb53db38f0faafd"}},{"arxiv_id":"2410.08964","paper":"/paper/language-imbalance-driven-rewarding-for","title":"Language Imbalance Driven Rewarding for Multilingual Self-improving","date":"2024-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZNLP/Language-Imbalance-Driven-Rewarding","path":"alpaca_eval/src/alpaca_eval/analyze.py","file_url":"https://github.com/ZNLP/Language-Imbalance-Driven-Rewarding/blob/HEAD/alpaca_eval/src/alpaca_eval/analyze.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0eb53db38f0faafd","mcp_get_code":{"code_sha256":"0eb53db38f0faafd"}},{"arxiv_id":"2407.14044","paper":"/paper/ecco-can-we-improve-model-generated-code","title":"ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?","date":"2024-07-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/DeepSpeed","path":"deepspeed/compat.py","file_url":"https://github.com/microsoft/DeepSpeed/blob/HEAD/deepspeed/compat.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":"45604a14e400b2f3","mcp_get_code":{"code_sha256":"45604a14e400b2f3"}},{"arxiv_id":"2406.09948","paper":"/paper/blend-a-benchmark-for-llms-on-everyday","title":"BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nlee0212/blend","path":"evaluation/evaluation_utils.py","file_url":"https://github.com/nlee0212/blend/blob/HEAD/evaluation/evaluation_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2a74de03f6298de8","mcp_get_code":{"code_sha256":"2a74de03f6298de8"}},{"arxiv_id":"2406.04692","paper":"/paper/mixture-of-agents-enhances-large-language","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","date":"2024-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"0eb53db38f0faafd","mcp_get_code":{"code_sha256":"0eb53db38f0faafd"}},{"arxiv_id":"2402.18667","paper":"/paper/fofo-a-benchmark-to-evaluate-llms-format","title":"FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforceairesearch/fofo","path":"alpaca_eval/src/alpaca_eval/analyze.py","file_url":"https://github.com/salesforceairesearch/fofo/blob/HEAD/alpaca_eval/src/alpaca_eval/analyze.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":"104b5b1c589a3175","mcp_get_code":{"code_sha256":"104b5b1c589a3175"}},{"arxiv_id":"2310.05294","paper":"/paper/hi-guys-or-hi-folks-benchmarking-gender","title":"Hi Guys or Hi Folks? Benchmarking Gender-Neutral Machine Translation with the GeNTE Corpus","date":"2023-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hlt-mt/fbk-NEUTR-evAL","path":"src/fbk_neutreval/cli/neogate_evaluation.py","file_url":"https://github.com/hlt-mt/fbk-NEUTR-evAL/blob/HEAD/src/fbk_neutreval/cli/neogate_evaluation.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":"0a86d4b3dbe47b96","mcp_get_code":{"code_sha256":"0a86d4b3dbe47b96"}},{"arxiv_id":"2305.14032","paper":"/paper/patch-mix-contrastive-learning-with-audio","title":"Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"raymin0223/patch-mix_contrastive_learning","path":"util/icbhi_util.py","file_url":"https://github.com/raymin0223/patch-mix_contrastive_learning/blob/HEAD/util/icbhi_util.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"61e09e6d13e83b66","mcp_get_code":{"code_sha256":"61e09e6d13e83b66"}},{"arxiv_id":"1912.02315","paper":"/paper/12-in-1-multi-task-vision-and-language","title":"12-in-1: Multi-Task Vision and Language Representation Learning","date":"2019-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/vilbert-multi-task","path":"vilbert/datasets/flickr_grounding_dataset.py","file_url":"https://github.com/facebookresearch/vilbert-multi-task/blob/HEAD/vilbert/datasets/flickr_grounding_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"32d8e4939405d6e2","mcp_get_code":{"code_sha256":"32d8e4939405d6e2"}},{"arxiv_id":"1505.04870","paper":"/paper/flickr30k-entities-collecting-region-to","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","date":"2015-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bryanplummer/flickr30k_entities","path":"flickr30k_entities_utils.py","file_url":"https://github.com/bryanplummer/flickr30k_entities/blob/HEAD/flickr30k_entities_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"66a196e3cfa1ebe6","mcp_get_code":{"code_sha256":"66a196e3cfa1ebe6"}},{"arxiv_id":"aaai_28278","paper":null,"title":"arXiv:aaai_28278","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"om-ai-lab/GroundVLP","path":"Detic/flickr30k_entities_utils.py","file_url":"https://github.com/om-ai-lab/GroundVLP/blob/HEAD/Detic/flickr30k_entities_utils.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":"66a196e3cfa1ebe6","mcp_get_code":{"code_sha256":"66a196e3cfa1ebe6"}}]}