{"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/avg","entry":"avg","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":10,"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":8,"n_samples_ran":7,"n_samples_fingerprinted":5,"n_places":11,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":0,"ran_fixture":0,"ran":6,"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":"2608.10528","paper":"/paper/arxiv-2608-10528","title":"When Do Anchor-Based Pointwise LLM Rerankers Help? Retriever Quality, Statistical Scope, and Anchor Design","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"utshabkg/GCCP-reproduce","path":"experiments/decoder_only_models/run_decoder.py","file_url":"https://github.com/utshabkg/GCCP-reproduce/blob/HEAD/experiments/decoder_only_models/run_decoder.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6c400decd573e0ca","mcp_get_code":{"code_sha256":"6c400decd573e0ca"}},{"arxiv_id":"2608.10528","paper":"/paper/arxiv-2608-10528","title":"When Do Anchor-Based Pointwise LLM Rerankers Help? Retriever Quality, Statistical Scope, and Anchor Design","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"utshabkg/GCCP-reproduce","path":"experiments/decoder_only_models/run_decoder_beir.py","file_url":"https://github.com/utshabkg/GCCP-reproduce/blob/HEAD/experiments/decoder_only_models/run_decoder_beir.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d75f633822e894a3","mcp_get_code":{"code_sha256":"d75f633822e894a3"}},{"arxiv_id":"2512.11391","paper":"/paper/arxiv-2512-11391","title":"Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"ivanniu/NSPO","path":"evaluation/eval_sorrybench.py","file_url":"https://github.com/ivanniu/NSPO/blob/HEAD/evaluation/eval_sorrybench.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9ba031d07c0634c0","mcp_get_code":{"code_sha256":"9ba031d07c0634c0"}},{"arxiv_id":"2408.10343","paper":"/paper/legalbench-rag-a-benchmark-for-retrieval","title":"LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain","date":"2024-08-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zeroentropy-cc/legalbenchrag","path":"legalbenchrag/run_benchmark.py","file_url":"https://github.com/zeroentropy-cc/legalbenchrag/blob/HEAD/legalbenchrag/run_benchmark.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"827171693ba8c487","mcp_get_code":{"code_sha256":"827171693ba8c487"}},{"arxiv_id":"2407.02880","paper":"/paper/knowledge-composition-using-task-vectors-with","title":"Knowledge Composition using Task Vectors with Learned Anisotropic Scaling","date":"2024-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fredzzhang/atlas","path":"src/learn_task_addition.py","file_url":"https://github.com/fredzzhang/atlas/blob/HEAD/src/learn_task_addition.py","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aab9d967b4f428fa","mcp_get_code":{"code_sha256":"aab9d967b4f428fa"}},{"arxiv_id":"2406.04216","paper":"/paper/what-do-language-models-learn-in-context-the","title":"What Do Language Models Learn in Context? The Structured Task Hypothesis","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eth-lre/llm_icl","path":"src/utils.py","file_url":"https://github.com/eth-lre/llm_icl/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"272fccc7faf0215a","mcp_get_code":{"code_sha256":"272fccc7faf0215a"}},{"arxiv_id":"2401.06866","paper":"/paper/health-llm-large-language-models-for-health","title":"Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mitmedialab/health-llm","path":"gen_dataset.py","file_url":"https://github.com/mitmedialab/health-llm/blob/HEAD/gen_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e65837da534b4304","mcp_get_code":{"code_sha256":"e65837da534b4304"}},{"arxiv_id":"2310.17645","paper":"/paper/defending-against-transfer-attacks-from","title":"PubDef: Defending Against Transfer Attacks From Public Models","date":"2023-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhengyuZhao/TransferAttackEval","path":"attacks/feature_disruption_attacks.py","file_url":"https://github.com/ZhengyuZhao/TransferAttackEval/blob/HEAD/attacks/feature_disruption_attacks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7a1a277b5455acbd","mcp_get_code":{"code_sha256":"7a1a277b5455acbd"}},{"arxiv_id":"2310.14491","paper":"/paper/towards-a-mechanistic-interpretation-of-multi","title":"Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yifan-h/mechanisticprobe","path":"src/utils.py","file_url":"https://github.com/yifan-h/mechanisticprobe/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"272fccc7faf0215a","mcp_get_code":{"code_sha256":"272fccc7faf0215a"}},{"arxiv_id":"2310.13590","paper":"/paper/relm-leveraging-language-models-for-enhanced","title":"ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction","date":"2023-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"syr-cn/relm","path":"utils.py","file_url":"https://github.com/syr-cn/relm/blob/HEAD/utils.py","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aab9d967b4f428fa","mcp_get_code":{"code_sha256":"aab9d967b4f428fa"}},{"arxiv_id":"2104.08303","paper":"/paper/capturing-row-and-column-semantics-in","title":"Capturing Row and Column Semantics in Transformer Based Question Answering over Tables","date":"2021-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/row-column-intersection","path":"tableqa/aggregation_integration.py","file_url":"https://github.com/IBM/row-column-intersection/blob/HEAD/tableqa/aggregation_integration.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":"7a1a277b5455acbd","mcp_get_code":{"code_sha256":"7a1a277b5455acbd"}}]}