{"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/compute-exact","entry":"compute_exact","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":17,"n_papers_ran":16,"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":8,"n_samples_ran":7,"n_samples_fingerprinted":7,"n_places":18,"n_places_pointer_only":6,"by_status":{"ran_honours":3,"ran_violates":1,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"unverified":1},"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":"2605.29250","paper":"/paper/arxiv-2605-29250","title":"OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"JinheonBaek/OmniRetrieval","path":"src/evaluation/metrics.py","file_url":"https://github.com/JinheonBaek/OmniRetrieval/blob/HEAD/src/evaluation/metrics.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9026d9da5d085bd4","mcp_get_code":{"code_sha256":"9026d9da5d085bd4"}},{"arxiv_id":"2412.09560","paper":"/paper/foundational-large-language-models-for","title":"Foundational Large Language Models for Materials Research","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"M3RG-IITD/llamat","path":"src/Kshot-val.py","file_url":"https://github.com/M3RG-IITD/llamat/blob/HEAD/src/Kshot-val.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9026d9da5d085bd4","mcp_get_code":{"code_sha256":"9026d9da5d085bd4"}},{"arxiv_id":"2412.06206","paper":"/paper/sirerag-indexing-similar-and-related","title":"SiReRAG: Indexing Similar and Related Information for Multihop Reasoning","date":"2024-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SalesforceAIResearch/SiReRAG","path":"evaluate_musique.py","file_url":"https://github.com/SalesforceAIResearch/SiReRAG/blob/HEAD/evaluate_musique.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9026d9da5d085bd4","mcp_get_code":{"code_sha256":"9026d9da5d085bd4"}},{"arxiv_id":"2410.09629","paper":"/paper/synthetic-knowledge-ingestion-towards","title":"Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"intuit-ai-research/knowledge-infused-ai","path":"synthetic-knowledge-ingestion/finetuning/ft_llama_factory.py","file_url":"https://github.com/intuit-ai-research/knowledge-infused-ai/blob/HEAD/synthetic-knowledge-ingestion/finetuning/ft_llama_factory.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9026d9da5d085bd4","mcp_get_code":{"code_sha256":"9026d9da5d085bd4"}},{"arxiv_id":"2409.07394","paper":"/paper/adacad-adaptively-decoding-to-balance","title":"AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge","date":"2024-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hannight/adacad","path":"eval_qa.py","file_url":"https://github.com/hannight/adacad/blob/HEAD/eval_qa.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7084c60ca1ae3e47","mcp_get_code":{"code_sha256":"7084c60ca1ae3e47"}},{"arxiv_id":"2402.17124","paper":"/paper/fact-and-reflection-far-improves-confidence","title":"Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"colinzhaoust/fact-and-reflection","path":"public_code.py","file_url":"https://github.com/colinzhaoust/fact-and-reflection/blob/HEAD/public_code.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7065bc6a2b841da5","mcp_get_code":{"code_sha256":"7065bc6a2b841da5"}},{"arxiv_id":"2310.14503","paper":"/paper/diversify-question-generation-with-retrieval","title":"Diversify Question Generation with Retrieval-Augmented Style Transfer","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gouqi666/RAST","path":"eval_squad.py","file_url":"https://github.com/gouqi666/RAST/blob/HEAD/eval_squad.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"37b0d27f83566ecf","mcp_get_code":{"code_sha256":"37b0d27f83566ecf"}},{"arxiv_id":"2310.12836","paper":"/paper/knowledge-augmented-language-model","title":"Knowledge-Augmented Language Model Verification","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jinheonbaek/kalmv","path":"metrics.py","file_url":"https://github.com/jinheonbaek/kalmv/blob/HEAD/metrics.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9026d9da5d085bd4","mcp_get_code":{"code_sha256":"9026d9da5d085bd4"}},{"arxiv_id":"2310.12836","paper":"/paper/knowledge-augmented-language-model","title":"Knowledge-Augmented Language Model Verification","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JinheonBaek/KALMV","path":"models/verifiers.py","file_url":"https://github.com/JinheonBaek/KALMV/blob/HEAD/models/verifiers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"66722e30b46133ad","mcp_get_code":{"code_sha256":"66722e30b46133ad"}},{"arxiv_id":"2310.05157","paper":"/paper/menatqa-a-new-dataset-for-testing-the","title":"MenatQA: A New Dataset for Testing the Temporal Comprehension and Reasoning Abilities of Large Language Models","date":"2023-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"weiyifan1023/MenatQA","path":"src/utils.py","file_url":"https://github.com/weiyifan1023/MenatQA/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"084d22134d9bd7c4","mcp_get_code":{"code_sha256":"084d22134d9bd7c4"}},{"arxiv_id":"2308.08973","paper":"/paper/beam-retrieval-general-end-to-end-retrieval","title":"End-to-End Beam Retrieval for Multi-Hop Question Answering","date":"2023-08-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"canghongjian/beam_retriever","path":"train_reader.py","file_url":"https://github.com/canghongjian/beam_retriever/blob/HEAD/train_reader.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"c1478415449411ed","mcp_get_code":{"code_sha256":"c1478415449411ed"}},{"arxiv_id":"2109.08133","paper":"/paper/phrase-retrieval-learns-passage-retrieval-too","title":"Phrase Retrieval Learns Passage Retrieval, Too","date":"2021-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-nlp/DensePhrases","path":"densephrases/utils/squad_metrics.py","file_url":"https://github.com/princeton-nlp/DensePhrases/blob/HEAD/densephrases/utils/squad_metrics.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9026d9da5d085bd4","mcp_get_code":{"code_sha256":"9026d9da5d085bd4"}},{"arxiv_id":"2108.06314","paper":"/paper/a-dataset-for-answering-time-sensitive","title":"A Dataset for Answering Time-Sensitive Questions","date":"2021-08-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenhuchen/time-sensitive-qa","path":"utils.py","file_url":"https://github.com/wenhuchen/time-sensitive-qa/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"084d22134d9bd7c4","mcp_get_code":{"code_sha256":"084d22134d9bd7c4"}},{"arxiv_id":"2105.02692","paper":"/paper/learning-to-perturb-word-embeddings-for-out","title":"Learning to Perturb Word Embeddings for Out-of-distribution QA","date":"2021-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seanie12/SWEP","path":"squad_metrics.py","file_url":"https://github.com/seanie12/SWEP/blob/HEAD/squad_metrics.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9026d9da5d085bd4","mcp_get_code":{"code_sha256":"9026d9da5d085bd4"}},{"arxiv_id":"2010.04898","paper":"/paper/open-domain-question-answering-goes","title":"Open-Domain Question Answering Goes Conversational via Question Rewriting","date":"2020-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-qrecc","path":"utils/evaluate_qa.py","file_url":"https://github.com/apple/ml-qrecc/blob/HEAD/utils/evaluate_qa.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":"0d6a04e3f9c96f42","mcp_get_code":{"code_sha256":"0d6a04e3f9c96f42"}},{"arxiv_id":"2004.07347","paper":"/paper/hybridqa-a-dataset-of-multi-hop-question","title":"HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data","date":"2020-04-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenhuchen/HybridQA","path":"evaluate_script.py","file_url":"https://github.com/wenhuchen/HybridQA/blob/HEAD/evaluate_script.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9026d9da5d085bd4","mcp_get_code":{"code_sha256":"9026d9da5d085bd4"}},{"arxiv_id":"1902.01718","paper":"/paper/end-to-end-open-domain-question-answering","title":"End-to-End Open-Domain Question Answering with BERTserini","date":"2019-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rsvp-ai/bertserini","path":"bertserini/utils/utils_squad_metrics.py","file_url":"https://github.com/rsvp-ai/bertserini/blob/HEAD/bertserini/utils/utils_squad_metrics.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9026d9da5d085bd4","mcp_get_code":{"code_sha256":"9026d9da5d085bd4"}},{"arxiv_id":"2023.emnlp-main.803","paper":null,"title":"arXiv:2023.emnlp-main.803","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"yisunlp/Anti-CF","path":"utils/metrics.py","file_url":"https://github.com/yisunlp/Anti-CF/blob/HEAD/utils/metrics.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9026d9da5d085bd4","mcp_get_code":{"code_sha256":"9026d9da5d085bd4"}}]}