{"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/aggregate-metrics","entry":"aggregate_metrics","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":4,"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":4,"n_samples_fingerprinted":0,"n_places":13,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":3,"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":"2609.01511","paper":"/paper/arxiv-2609-01511","title":"Benchmarking Spatial, Spectral, and Self-Supervised Cues for Face Forgery Detection under Realistic Degradation","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"lucasdocunha/FaceForgery-Benchmark","path":"make_tables.py","file_url":"https://github.com/lucasdocunha/FaceForgery-Benchmark/blob/HEAD/make_tables.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"314b71af44b78625","mcp_get_code":{"code_sha256":"314b71af44b78625"}},{"arxiv_id":"2608.31009","paper":"/paper/arxiv-2608-31009","title":"Language-Informed Flow Matching for Trend-Guided Structure-Based 3D Molecular Generation","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"kasurl/LiFT","path":"src/generate.py","file_url":"https://github.com/kasurl/LiFT/blob/HEAD/src/generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77ddb1afea6e25ff","mcp_get_code":{"code_sha256":"77ddb1afea6e25ff"}},{"arxiv_id":"2606.07856","paper":"/paper/arxiv-2606-07856","title":"Teacher-Free Self-Training Amplifies but Does Not Compound: A Pass@K Crossover on a Free-Verifier Domain","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"izzortsi/trapdoor-loom","path":"aggregate_seeds.py","file_url":"https://github.com/izzortsi/trapdoor-loom/blob/HEAD/aggregate_seeds.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"25c7ab133d3809e8","mcp_get_code":{"code_sha256":"25c7ab133d3809e8"}},{"arxiv_id":"2605.10896","paper":"/paper/arxiv-2605-10896","title":"V4FinBench: Benchmarking Tabular Foundation Models, LLMs, and Standard Methods on Corporate Bankruptcy Prediction","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"genwro-ai/V4FinBench","path":"src/v4finbench/evaluation/results.py","file_url":"https://github.com/genwro-ai/V4FinBench/blob/HEAD/src/v4finbench/evaluation/results.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"096f3c88d898b899","mcp_get_code":{"code_sha256":"096f3c88d898b899"}},{"arxiv_id":"2602.17687","paper":"/paper/arxiv-2602-17687","title":"IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"weaviate/query-agent-benchmarking","path":"query_agent_benchmarking/internal/core/domain/analysis.py","file_url":"https://github.com/weaviate/query-agent-benchmarking/blob/HEAD/query_agent_benchmarking/internal/core/domain/analysis.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"c417197188899940","mcp_get_code":{"code_sha256":"c417197188899940"}},{"arxiv_id":"2509.23385","paper":"/paper/arxiv-2509-23385","title":"Flow Matching Calibration for Simulation-Based Inference under Model Misspecification","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"pruhlmann/FMCPE","path":"create_comparison_plots.py","file_url":"https://github.com/pruhlmann/FMCPE/blob/HEAD/create_comparison_plots.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cab7e77f61109439","mcp_get_code":{"code_sha256":"cab7e77f61109439"}},{"arxiv_id":"2506.20512","paper":"/paper/octothinker-mid-training-incentivizes","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","date":"2025-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gair-nlp/octothinker","path":"eval/summarize_results.py","file_url":"https://github.com/gair-nlp/octothinker/blob/HEAD/eval/summarize_results.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":"8b9e2baf73bb9a6f","mcp_get_code":{"code_sha256":"8b9e2baf73bb9a6f"}},{"arxiv_id":"2402.03300","paper":"/paper/deepseekmath-pushing-the-limits-of","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepseek-ai/deepseek-math","path":"evaluation/summarize_results.py","file_url":"https://github.com/deepseek-ai/deepseek-math/blob/HEAD/evaluation/summarize_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8b9e2baf73bb9a6f","mcp_get_code":{"code_sha256":"8b9e2baf73bb9a6f"}},{"arxiv_id":"2310.09163","paper":"/paper/jointly-learned-exit-and-inference-for-a","title":"Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN","date":"2023-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"networkslab/dynn","path":"src/collect_metric_iter.py","file_url":"https://github.com/networkslab/dynn/blob/HEAD/src/collect_metric_iter.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a13a08686e59be7a","mcp_get_code":{"code_sha256":"a13a08686e59be7a"}},{"arxiv_id":"2210.03347","paper":"/paper/pix2struct-screenshot-parsing-as-pretraining","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","date":"2022-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/pix2struct","path":"pix2struct/metrics.py","file_url":"https://github.com/google-research/pix2struct/blob/HEAD/pix2struct/metrics.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":"b4928537d2a4c2e0","mcp_get_code":{"code_sha256":"b4928537d2a4c2e0"}},{"arxiv_id":"2110.00534","paper":"/paper/teach-task-driven-embodied-agents-that-chat","title":"TEACh: Task-driven Embodied Agents that Chat","date":"2021-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alexa/teach","path":"src/teach/eval/compute_metrics.py","file_url":"https://github.com/alexa/teach/blob/HEAD/src/teach/eval/compute_metrics.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":"297d294427543dc6","mcp_get_code":{"code_sha256":"297d294427543dc6"}},{"arxiv_id":"1906.07132","paper":"/paper/avoiding-reasoning-shortcuts-adversarial","title":"Avoiding Reasoning Shortcuts: Adversarial Evaluation, Training, and Model Development for Multi-Hop QA","date":"2019-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiangycTarheel/Adversarial-MultiHopQA","path":"nectar/nectar/theanoutil/model.py","file_url":"https://github.com/jiangycTarheel/Adversarial-MultiHopQA/blob/HEAD/nectar/nectar/theanoutil/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"52f030918856dc44","mcp_get_code":{"code_sha256":"52f030918856dc44"}},{"arxiv_id":"2025.acl-long.1506","paper":null,"title":"arXiv:2025.acl-long.1506","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"deepseek-ai/DeepSeek-Math","path":"evaluation/summarize_results.py","file_url":"https://github.com/deepseek-ai/DeepSeek-Math/blob/HEAD/evaluation/summarize_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8b9e2baf73bb9a6f","mcp_get_code":{"code_sha256":"8b9e2baf73bb9a6f"}}]}