{"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/temperature-scaling","entry":"temperature_scaling","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":5,"n_papers_ran":3,"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":5,"n_samples_ran":3,"n_samples_fingerprinted":2,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":1,"unverified":2},"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":"2506.05047","paper":"/paper/reliably-detecting-model-failures-in","title":"Reliably detecting model failures in deployment without labels","date":"2025-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"teivng/d3m","path":"d3m/monitors/bayesian_monitor.py","file_url":"https://github.com/teivng/d3m/blob/HEAD/d3m/monitors/bayesian_monitor.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6688a7f57e8828e0","mcp_get_code":{"code_sha256":"6688a7f57e8828e0"}},{"arxiv_id":"2407.12784","paper":"/paper/agentpoison-red-teaming-llm-agents-via","title":"AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases","date":"2024-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BillChan226/AgentPoison","path":"ReAct/uncertainty_utils.py","file_url":"https://github.com/BillChan226/AgentPoison/blob/HEAD/ReAct/uncertainty_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6afa15a99203f372","mcp_get_code":{"code_sha256":"6afa15a99203f372"}},{"arxiv_id":"2307.02390","paper":"/paper/causal-discovery-with-language-models-as","title":"Causal Discovery with Language Models as Imperfect Experts","date":"2023-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"StephLong614/Causal-disco","path":"utils/language_models.py","file_url":"https://github.com/StephLong614/Causal-disco/blob/HEAD/utils/language_models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"954a5daeed6f677f","mcp_get_code":{"code_sha256":"954a5daeed6f677f"}},{"arxiv_id":"2106.07998","paper":"/paper/revisiting-the-calibration-of-modern-neural","title":"Revisiting the Calibration of Modern Neural Networks","date":"2021-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-research/robustness_metrics","path":"robustness_metrics/models/rescaling.py","file_url":"https://github.com/google-research/robustness_metrics/blob/HEAD/robustness_metrics/models/rescaling.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":"599a561fab65db80","mcp_get_code":{"code_sha256":"599a561fab65db80"}},{"arxiv_id":"2003.07329","paper":"/paper/mix-n-match-ensemble-and-compositional","title":"Mix-n-Match: Ensemble and Compositional Methods for Uncertainty Calibration in Deep Learning","date":"2020-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhang64-llnl/Mix-n-Match-Calibration","path":"util_calibration.py","file_url":"https://github.com/zhang64-llnl/Mix-n-Match-Calibration/blob/HEAD/util_calibration.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7c2ff72a09fddd9","mcp_get_code":{"code_sha256":"a7c2ff72a09fddd9"}}]}