{"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/get-probs","entry":"get_probs","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":15,"n_papers_ran":7,"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":15,"n_samples_ran":6,"n_samples_fingerprinted":1,"n_places":16,"n_places_pointer_only":9,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":9},"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":"2605.12813","paper":"/paper/arxiv-2605-12813","title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Buyun-Liang/REALISTA","path":"src/realista.py","file_url":"https://github.com/Buyun-Liang/REALISTA/blob/HEAD/src/realista.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"33179574bc5bb0fb","mcp_get_code":{"code_sha256":"33179574bc5bb0fb"}},{"arxiv_id":"2510.04398","paper":"/paper/arxiv-2510-04398","title":"SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"Buyun-Liang/SECA","path":"src/seca.py","file_url":"https://github.com/Buyun-Liang/SECA/blob/HEAD/src/seca.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c908cca1a7b8292d","mcp_get_code":{"code_sha256":"c908cca1a7b8292d"}},{"arxiv_id":"2412.19513","paper":"/paper/confidence-v-s-critique-a-decomposition-of","title":"Confidence v.s. Critique: A Decomposition of Self-Correction Capability for LLMs","date":"2024-12-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Zhe-Young/SelfCorrectDecompose","path":"eval_logits.py","file_url":"https://github.com/Zhe-Young/SelfCorrectDecompose/blob/HEAD/eval_logits.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fcc620fb7cb1bb32","mcp_get_code":{"code_sha256":"fcc620fb7cb1bb32"}},{"arxiv_id":"2411.02628","paper":"/paper/the-fundamental-limit-of-jet-tagging","title":"The Fundamental Limit of Jet Tagging","date":null,"month_inferred_from_arxiv_id":"2024-11","title_source":"archive","repo":"hreyes91/fun-jet-tagging","path":"evaluate_probabilities.py","file_url":"https://github.com/hreyes91/fun-jet-tagging/blob/HEAD/evaluate_probabilities.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"85eabcf1cc1d64de","mcp_get_code":{"code_sha256":"85eabcf1cc1d64de"}},{"arxiv_id":"2406.02354","paper":"/paper/label-wise-aleatoric-and-epistemic","title":"Label-wise Aleatoric and Epistemic Uncertainty Quantification","date":"2024-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YSale/label-uq","path":"holdout/data.py","file_url":"https://github.com/YSale/label-uq/blob/HEAD/holdout/data.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"259d23a3b6e83ce7","mcp_get_code":{"code_sha256":"259d23a3b6e83ce7"}},{"arxiv_id":"2405.08363","paper":"/paper/unmarker-a-universal-attack-on-defensive","title":"UnMarker: A Universal Attack on Defensive Image Watermarking","date":"2024-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andrekassis/ai-watermark","path":"modules/metrics.py","file_url":"https://github.com/andrekassis/ai-watermark/blob/HEAD/modules/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"1fcfde9ab79b02fa","mcp_get_code":{"code_sha256":"1fcfde9ab79b02fa"}},{"arxiv_id":"2311.09648","paper":"/paper/event-causality-is-key-to-computational-story","title":"Event Causality Is Key to Computational Story Understanding","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"insundaycathy/event-causality-extraction","path":"copes/src/metric_utils.py","file_url":"https://github.com/insundaycathy/event-causality-extraction/blob/HEAD/copes/src/metric_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"50bc28c5417a08cb","mcp_get_code":{"code_sha256":"50bc28c5417a08cb"}},{"arxiv_id":"2307.15054","paper":"/paper/a-geometric-notion-of-causal-probing","title":"A Geometric Notion of Causal Probing","date":"2023-07-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rycolab/causalgeom","path":"src/evals/eval_utils.py","file_url":"https://github.com/rycolab/causalgeom/blob/HEAD/src/evals/eval_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2b8954785d15209e","mcp_get_code":{"code_sha256":"2b8954785d15209e"}},{"arxiv_id":"2305.05191","paper":"/paper/cola-contextualized-commonsense-causal","title":"COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective","date":"2023-05-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hkust-knowcomp/cola","path":"src/metric_utils.py","file_url":"https://github.com/hkust-knowcomp/cola/blob/HEAD/src/metric_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"50bc28c5417a08cb","mcp_get_code":{"code_sha256":"50bc28c5417a08cb"}},{"arxiv_id":"2210.03920","paper":"/paper/detecting-label-errors-in-token","title":"Detecting Label Errors in Token Classification Data","date":"2022-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cleanlab/token-label-error-benchmarks","path":"utils.py","file_url":"https://github.com/cleanlab/token-label-error-benchmarks/blob/HEAD/utils.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":"3c41a5bdbdfce314","mcp_get_code":{"code_sha256":"3c41a5bdbdfce314"}},{"arxiv_id":"2203.08597","paper":"/paper/less-is-more-summary-of-long-instructions-is","title":"Less is More: Summary of Long Instructions is Better for Program Synthesis","date":"2022-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kurbster/prompt-summarization","path":"src/lib/experiment_results.py","file_url":"https://github.com/kurbster/prompt-summarization/blob/HEAD/src/lib/experiment_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":"757f47477f49345b","mcp_get_code":{"code_sha256":"757f47477f49345b"}},{"arxiv_id":"2008.02275","paper":"/paper/aligning-ai-with-shared-human-values","title":"Aligning AI With Shared Human Values","date":"2020-08-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hendrycks/ethics","path":"commonsense/tune.py","file_url":"https://github.com/hendrycks/ethics/blob/HEAD/commonsense/tune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2f5b3526f6ef2843","mcp_get_code":{"code_sha256":"2f5b3526f6ef2843"}},{"arxiv_id":"1911.00068","paper":"/paper/confident-learning-estimating-uncertainty-in","title":"Confident Learning: Estimating Uncertainty in Dataset Labels","date":"2019-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cgnorthcutt/confidentlearning-reproduce","path":"cifar10/cifar10_train_crossval.py","file_url":"https://github.com/cgnorthcutt/confidentlearning-reproduce/blob/HEAD/cifar10/cifar10_train_crossval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"c84054e10c7be2c8","mcp_get_code":{"code_sha256":"c84054e10c7be2c8"}},{"arxiv_id":"1911.00068","paper":"/paper/confident-learning-estimating-uncertainty-in","title":"Confident Learning: Estimating Uncertainty in Dataset Labels","date":"2019-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chang-yue/ctrl","path":"cifar10/cifar10_train.py","file_url":"https://github.com/chang-yue/ctrl/blob/HEAD/cifar10/cifar10_train.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2a12b21504e8e284","mcp_get_code":{"code_sha256":"2a12b21504e8e284"}},{"arxiv_id":"1906.00816","paper":"/paper/190600816","title":"Bayesian Evidential Deep Learning with PAC Regularization","date":"2019-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"manuelhaussmann/bedl","path":"exp_classification.py","file_url":"https://github.com/manuelhaussmann/bedl/blob/HEAD/exp_classification.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6397d83663620ac0","mcp_get_code":{"code_sha256":"6397d83663620ac0"}},{"arxiv_id":"1708.00489","paper":"/paper/active-learning-for-convolutional-neural","title":"Active Learning for Convolutional Neural Networks: A Core-Set Approach","date":"2017-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"svdesai/coreset-al","path":"active_learn.py","file_url":"https://github.com/svdesai/coreset-al/blob/HEAD/active_learn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fd7c9e6b29c78cbd","mcp_get_code":{"code_sha256":"fd7c9e6b29c78cbd"}}]}