{"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/check-answer","entry":"check_answer","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":28,"n_papers_ran":9,"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":18,"n_samples_ran":10,"n_samples_fingerprinted":3,"n_places":29,"n_places_pointer_only":17,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":0,"ran_fixture":0,"ran":9,"unverified":8},"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":"2604.11628","paper":"/paper/arxiv-2604-11628","title":"Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"facebookresearch/contriever","path":"src/evaluation.py","file_url":"https://github.com/facebookresearch/contriever/blob/HEAD/src/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"637b51b8df78832a","mcp_get_code":{"code_sha256":"637b51b8df78832a"}},{"arxiv_id":"2602.22296","paper":"/paper/arxiv-2602-22296","title":"UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"dshah02/upskill","path":"experiments/gsm8k/benchmark.py","file_url":"https://github.com/dshah02/upskill/blob/HEAD/experiments/gsm8k/benchmark.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2b7225f74d0266a6","mcp_get_code":{"code_sha256":"2b7225f74d0266a6"}},{"arxiv_id":"2506.21215","paper":"/paper/unveiling-causal-reasoning-in-large-language","title":"Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?","date":"2025-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Haoang97/CausalProbe-2024","path":"src/evaluation.py","file_url":"https://github.com/Haoang97/CausalProbe-2024/blob/HEAD/src/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"637b51b8df78832a","mcp_get_code":{"code_sha256":"637b51b8df78832a"}},{"arxiv_id":"2412.12151","paper":"/paper/smartcal-an-approach-to-self-aware-tool-use","title":"SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration","date":"2024-12-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Henrysyh2000/SMARTCAL","path":"ART_SM_CAL/metric.py","file_url":"https://github.com/Henrysyh2000/SMARTCAL/blob/HEAD/ART_SM_CAL/metric.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"219b8d0fcf748400","mcp_get_code":{"code_sha256":"219b8d0fcf748400"}},{"arxiv_id":"2410.16130","paper":"/paper/can-large-audio-language-models-truly-hear","title":"Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kuan2jiu99/audio-hallucination","path":"icassp2025/evaluation.py","file_url":"https://github.com/kuan2jiu99/audio-hallucination/blob/HEAD/icassp2025/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b1c856ce62873154","mcp_get_code":{"code_sha256":"b1c856ce62873154"}},{"arxiv_id":"2410.04139","paper":"/paper/from-reading-to-compressing-exploring-the","title":"From Reading to Compressing: Exploring the Multi-document Reader for Prompt Compression","date":"2024-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eunseongc/r2c","path":"src_fid/evaluation.py","file_url":"https://github.com/eunseongc/r2c/blob/HEAD/src_fid/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6bad17909398049e","mcp_get_code":{"code_sha256":"6bad17909398049e"}},{"arxiv_id":"2408.02544","paper":"/paper/2408-02544","title":"Caution for the Environment: Multimodal Agents are Susceptible to Environmental Distractions","date":"2024-08-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xbmxb/EnvDistraction","path":"evaluation.py","file_url":"https://github.com/xbmxb/EnvDistraction/blob/HEAD/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"073de53b1531f4b6","mcp_get_code":{"code_sha256":"073de53b1531f4b6"}},{"arxiv_id":"2407.10670","paper":"/paper/enhancing-retrieval-and-managing-retrieval-a","title":"Enhancing Retrieval and Managing Retrieval: A Four-Module Synergy for Improved Quality and Efficiency in RAG Systems","date":"2024-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ancientshi/erm4","path":"evaluation.py","file_url":"https://github.com/ancientshi/erm4/blob/HEAD/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"c97060e48c93da97","mcp_get_code":{"code_sha256":"c97060e48c93da97"}},{"arxiv_id":"2407.09014","paper":"/paper/compact-compressing-retrieved-documents","title":"CompAct: Compressing Retrieved Documents Actively for Question Answering","date":"2024-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dmis-lab/CompAct","path":"evaluate.py","file_url":"https://github.com/dmis-lab/CompAct/blob/HEAD/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"637b51b8df78832a","mcp_get_code":{"code_sha256":"637b51b8df78832a"}},{"arxiv_id":"2405.17402","paper":"/paper/thread-thinking-deeper-with-recursive","title":"THREAD: Thinking Deeper with Recursive Spawning","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"philipmit/thread","path":"datacommons_qa/run_datacommons_qa.py","file_url":"https://github.com/philipmit/thread/blob/HEAD/datacommons_qa/run_datacommons_qa.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"069b0f9b21a6a04c","mcp_get_code":{"code_sha256":"069b0f9b21a6a04c"}},{"arxiv_id":"2405.17402","paper":"/paper/thread-thinking-deeper-with-recursive","title":"THREAD: Thinking Deeper with Recursive Spawning","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"philipmit/thread","path":"mimiciii_icu_qa/run_mimiciii_icuqa.py","file_url":"https://github.com/philipmit/thread/blob/HEAD/mimiciii_icu_qa/run_mimiciii_icuqa.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1ef20761472016e0","mcp_get_code":{"code_sha256":"1ef20761472016e0"}},{"arxiv_id":"2404.19705","paper":"/paper/when-to-retrieve-teaching-llms-to-utilize","title":"When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectively","date":"2024-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tLabruna/Adapt-LLM","path":"contriever/src/evaluation.py","file_url":"https://github.com/tLabruna/Adapt-LLM/blob/HEAD/contriever/src/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC-BY-4.0","inline_ok":false,"code_sha256_prefix":"637b51b8df78832a","mcp_get_code":{"code_sha256":"637b51b8df78832a"}},{"arxiv_id":"2403.15268","paper":"/paper/imagination-augmented-generation-learning-to","title":"Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering","date":"2024-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xnhyacinth/iag","path":"model/evaluation.py","file_url":"https://github.com/xnhyacinth/iag/blob/HEAD/model/evaluation.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":"637b51b8df78832a","mcp_get_code":{"code_sha256":"637b51b8df78832a"}},{"arxiv_id":"2402.18439","paper":"/paper/beyond-natural-language-llms-leveraging","title":"Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/autoform","path":"scripts/aqua/autoform-gemini.py","file_url":"https://github.com/thunlp/autoform/blob/HEAD/scripts/aqua/autoform-gemini.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4fd900f6aa5ac8b1","mcp_get_code":{"code_sha256":"4fd900f6aa5ac8b1"}},{"arxiv_id":"2402.11626","paper":"/paper/metacognitive-retrieval-augmented-large","title":"Metacognitive Retrieval-Augmented Large Language Models","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ignorejjj/metarag","path":"utils.py","file_url":"https://github.com/ignorejjj/metarag/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":"fa69772964833f8a","mcp_get_code":{"code_sha256":"fa69772964833f8a"}},{"arxiv_id":"2402.07867","paper":"/paper/poisonedrag-knowledge-poisoning-attacks-to","title":"PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models","date":"2024-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sleeepeer/poisonedrag","path":"src/contriever_src/evaluation.py","file_url":"https://github.com/sleeepeer/poisonedrag/blob/HEAD/src/contriever_src/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"637b51b8df78832a","mcp_get_code":{"code_sha256":"637b51b8df78832a"}},{"arxiv_id":"2402.05391","paper":"/paper/knowledge-graphs-meet-multi-modal-learning-a","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hackerchenzhuo/LaKo","path":"src/evaluation.py","file_url":"https://github.com/hackerchenzhuo/LaKo/blob/HEAD/src/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"637b51b8df78832a","mcp_get_code":{"code_sha256":"637b51b8df78832a"}},{"arxiv_id":"2402.03216","paper":"/paper/bge-m3-embedding-multi-lingual-multi","title":"BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allen-li1231/treehop-rag","path":"src/evaluation.py","file_url":"https://github.com/allen-li1231/treehop-rag/blob/HEAD/src/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9691cc44ab024ac1","mcp_get_code":{"code_sha256":"9691cc44ab024ac1"}},{"arxiv_id":"2402.02503","paper":"/paper/gerea-question-aware-prompt-captions-for","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","date":"2024-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"upper9527/gerea","path":"src/evaluation.py","file_url":"https://github.com/upper9527/gerea/blob/HEAD/src/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"637b51b8df78832a","mcp_get_code":{"code_sha256":"637b51b8df78832a"}},{"arxiv_id":"2401.16979","paper":"/paper/re3val-reinforced-and-reranked-generative","title":"Re3val: Reinforced and Reranked Generative Retrieval","date":"2024-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/FiD","path":"src/evaluation.py","file_url":"https://github.com/facebookresearch/FiD/blob/HEAD/src/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"637b51b8df78832a","mcp_get_code":{"code_sha256":"637b51b8df78832a"}},{"arxiv_id":"2401.11911","paper":"/paper/blinded-by-generated-contexts-how-language","title":"Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts?","date":"2024-01-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tan-hexiang/retrieveorgenerated","path":"src/evaluation.py","file_url":"https://github.com/tan-hexiang/retrieveorgenerated/blob/HEAD/src/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3871a296cce05628","mcp_get_code":{"code_sha256":"3871a296cce05628"}},{"arxiv_id":"2401.03568","paper":"/paper/agent-ai-surveying-the-horizons-of-multimodal","title":"Agent AI: Surveying the Horizons of Multimodal Interaction","date":"2024-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"guilk/kat","path":"src/evaluation.py","file_url":"https://github.com/guilk/kat/blob/HEAD/src/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"637b51b8df78832a","mcp_get_code":{"code_sha256":"637b51b8df78832a"}},{"arxiv_id":"2311.16452","paper":"/paper/can-generalist-foundation-models-outcompete","title":"Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/promptbase","path":"src/promptbase/math/math.py","file_url":"https://github.com/microsoft/promptbase/blob/HEAD/src/promptbase/math/math.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d9b6798e6642642a","mcp_get_code":{"code_sha256":"d9b6798e6642642a"}},{"arxiv_id":"2310.14393","paper":"/paper/merging-generated-and-retrieved-knowledge-for","title":"Merging Generated and Retrieved Knowledge for Open-Domain QA","date":"2023-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yunx-z/combo","path":"passage_matching/evaluation.py","file_url":"https://github.com/yunx-z/combo/blob/HEAD/passage_matching/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3c9429bad228b98b","mcp_get_code":{"code_sha256":"3c9429bad228b98b"}},{"arxiv_id":"2308.11730","paper":"/paper/knowledge-graph-prompting-for-multi-document","title":"Knowledge Graph Prompting for Multi-Document Question Answering","date":"2023-08-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuwvandy/kg-llm-mdqa","path":"DPR/evaluation.py","file_url":"https://github.com/yuwvandy/kg-llm-mdqa/blob/HEAD/DPR/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"25de4cd985d9cf87","mcp_get_code":{"code_sha256":"25de4cd985d9cf87"}},{"arxiv_id":"2112.08688","paper":"/paper/evidentiality-guided-generation-for-knowledge","title":"Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks","date":"2021-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akariasai/evidentiality_qa","path":"evi_gen/src/evaluation.py","file_url":"https://github.com/akariasai/evidentiality_qa/blob/HEAD/evi_gen/src/evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"637b51b8df78832a","mcp_get_code":{"code_sha256":"637b51b8df78832a"}},{"arxiv_id":"2025.findings-acl.673","paper":null,"title":"arXiv:2025.findings-acl.673","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"McGill-NLP/malicious-ir","path":"malicious_ir/retrieval/validation_utils.py","file_url":"https://github.com/McGill-NLP/malicious-ir/blob/HEAD/malicious_ir/retrieval/validation_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c08624fe02161ae4","mcp_get_code":{"code_sha256":"c08624fe02161ae4"}},{"arxiv_id":"2025.emnlp-main.192","paper":null,"title":"arXiv:2025.emnlp-main.192","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"FreedomIntelligence/RAG-Instruct","path":"retrieval_lm/src/evaluation.py","file_url":"https://github.com/FreedomIntelligence/RAG-Instruct/blob/HEAD/retrieval_lm/src/evaluation.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":"637b51b8df78832a","mcp_get_code":{"code_sha256":"637b51b8df78832a"}},{"arxiv_id":"2023.findings-emnlp.179","paper":null,"title":"arXiv:2023.findings-emnlp.179","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"noewangjy/SP-CoT","path":"src/utils.py","file_url":"https://github.com/noewangjy/SP-CoT/blob/HEAD/src/utils.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":"0795582d7138ceb4","mcp_get_code":{"code_sha256":"0795582d7138ceb4"}}]}