{"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/process-row","entry":"process_row","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":14,"n_papers_ran":10,"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":11,"n_samples_ran":7,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":6,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":1,"ran":3,"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":"2606.02578","paper":"/paper/arxiv-2606-02578","title":"Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"kaist-cvml/perception-judge","path":"prepare-datasets/post_processing_filter_after_gen.py","file_url":"https://github.com/kaist-cvml/perception-judge/blob/HEAD/prepare-datasets/post_processing_filter_after_gen.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8d0040b5ee433fc9","mcp_get_code":{"code_sha256":"8d0040b5ee433fc9"}},{"arxiv_id":"2505.12632","paper":"/paper/scalable-video-to-dataset-generation-for","title":"Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"runamu/monday","path":"data_processing/extract_scenes.py","file_url":"https://github.com/runamu/monday/blob/HEAD/data_processing/extract_scenes.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":"f0ee53e5b2feb7e6","mcp_get_code":{"code_sha256":"f0ee53e5b2feb7e6"}},{"arxiv_id":"2504.19373","paper":"/paper/doxing-via-the-lens-revealing-privacy-leakage","title":"Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models","date":"2025-04-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SaFo-Lab/DoxBench","path":"code/data_process/get_address.py","file_url":"https://github.com/SaFo-Lab/DoxBench/blob/HEAD/code/data_process/get_address.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":"34072bb68d556f69","mcp_get_code":{"code_sha256":"34072bb68d556f69"}},{"arxiv_id":"2410.15553","paper":"/paper/multi-if-benchmarking-llms-on-multi-turn-and","title":"Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/Multi-IF","path":"multi_turn_instruct_following_eval_api.py","file_url":"https://github.com/facebookresearch/Multi-IF/blob/HEAD/multi_turn_instruct_following_eval_api.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":"d94ee85769420d1d","mcp_get_code":{"code_sha256":"d94ee85769420d1d"}},{"arxiv_id":"2410.02751","paper":"/paper/relic-a-recipe-for-64k-steps-of-in-context","title":"ReLIC: A Recipe for 64k Steps of In-Context Reinforcement Learning for Embodied AI","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aielawady/relic","path":"relic/evaluator/process_eval_data.py","file_url":"https://github.com/aielawady/relic/blob/HEAD/relic/evaluator/process_eval_data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eb5c375822b6e0ae","mcp_get_code":{"code_sha256":"eb5c375822b6e0ae"}},{"arxiv_id":"2407.06947","paper":"/paper/audio-language-datasets-of-scenes-and-events","title":"Audio-Language Datasets of Scenes and Events: A Survey","date":null,"month_inferred_from_arxiv_id":"2024-07","title_source":"archive","repo":"gljs/audio-datasets","path":"dataset_to_files.py","file_url":"https://github.com/gljs/audio-datasets/blob/HEAD/dataset_to_files.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"32c255a9dc33cbfe","mcp_get_code":{"code_sha256":"32c255a9dc33cbfe"}},{"arxiv_id":"2406.13264","paper":"/paper/do-multimodal-foundation-models-understand","title":"WONDERBREAD: A Benchmark for Evaluating Multimodal Foundation Models on Business Process Management Tasks","date":"2024-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hazyresearch/wonderbread","path":"wonderbread/collect/download.py","file_url":"https://github.com/hazyresearch/wonderbread/blob/HEAD/wonderbread/collect/download.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a9a200c442872344","mcp_get_code":{"code_sha256":"a9a200c442872344"}},{"arxiv_id":"2405.11874","paper":"/paper/xfinder-robust-and-pinpoint-answer-extraction","title":"xFinder: Robust and Pinpoint Answer Extraction for Large Language Models","date":"2024-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IAAR-Shanghai/xFinder","path":"scripts/dataset_construction/create_benchmark_dataset.py","file_url":"https://github.com/IAAR-Shanghai/xFinder/blob/HEAD/scripts/dataset_construction/create_benchmark_dataset.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"ca90f4c9f084240f","mcp_get_code":{"code_sha256":"ca90f4c9f084240f"}},{"arxiv_id":"2310.06675","paper":"/paper/seer-a-knapsack-approach-to-exemplar","title":"SEER : A Knapsack approach to Exemplar Selection for In-Context HybridQA","date":"2023-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jtonglet/SEER","path":"evaluate_finqa.py","file_url":"https://github.com/jtonglet/SEER/blob/HEAD/evaluate_finqa.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23577faa1c9d855a","mcp_get_code":{"code_sha256":"23577faa1c9d855a"}},{"arxiv_id":"2307.00175","paper":"/paper/still-no-lie-detector-for-language-models","title":"Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks","date":"2023-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"cc6f60b3b538e888","mcp_get_code":{"code_sha256":"cc6f60b3b538e888"}},{"arxiv_id":"2304.13734","paper":"/paper/the-internal-state-of-an-llm-knows-when-its","title":"The Internal State of an LLM Knows When It's Lying","date":"2023-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"balevinstein/probes","path":"Generate_Embeddings.py","file_url":"https://github.com/balevinstein/probes/blob/HEAD/Generate_Embeddings.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc6f60b3b538e888","mcp_get_code":{"code_sha256":"cc6f60b3b538e888"}},{"arxiv_id":"2109.00122","paper":"/paper/finqa-a-dataset-of-numerical-reasoning-over","title":"FinQA: A Dataset of Numerical Reasoning over Financial Data","date":"2021-09-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"czyssrs/finqa","path":"code/evaluate/evaluate.py","file_url":"https://github.com/czyssrs/finqa/blob/HEAD/code/evaluate/evaluate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23577faa1c9d855a","mcp_get_code":{"code_sha256":"23577faa1c9d855a"}},{"arxiv_id":"openreview_uEvT8fMsgx","paper":null,"title":"arXiv:openreview_uEvT8fMsgx","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"kmsgk0/BEST","path":"process/calculate.py","file_url":"https://github.com/kmsgk0/BEST/blob/HEAD/process/calculate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cd767f1ff25f58ac","mcp_get_code":{"code_sha256":"cd767f1ff25f58ac"}},{"arxiv_id":"2024.findings-naacl.294","paper":null,"title":"arXiv:2024.findings-naacl.294","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"balevinstein/Probes","path":"Generate_Embeddings.py","file_url":"https://github.com/balevinstein/Probes/blob/HEAD/Generate_Embeddings.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc6f60b3b538e888","mcp_get_code":{"code_sha256":"cc6f60b3b538e888"}}]}