{"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/whiten","entry":"whiten","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":13,"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":9,"n_samples_fingerprinted":4,"n_places":16,"n_places_pointer_only":3,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":3,"ran":4,"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":"2410.18870","paper":"/paper/end-to-end-training-for-recommendation-with","title":"End-to-end Training for Recommendation with Language-based User Profiles","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaolingao/langptune","path":"src/langptune_gemma.py","file_url":"https://github.com/zhaolingao/langptune/blob/HEAD/src/langptune_gemma.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ed8c389873520a26","mcp_get_code":{"code_sha256":"ed8c389873520a26"}},{"arxiv_id":"2410.18870","paper":"/paper/end-to-end-training-for-recommendation-with","title":"End-to-end Training for Recommendation with Language-based User Profiles","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaolingao/langptune","path":"src/langptune_gemma.py","file_url":"https://github.com/zhaolingao/langptune/blob/HEAD/src/langptune_gemma.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e78dac11b89dad63","mcp_get_code":{"code_sha256":"e78dac11b89dad63"}},{"arxiv_id":"2410.04612","paper":"/paper/regressing-the-relative-future-efficient","title":"Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF","date":"2024-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaolingao/refuel","path":"setting_two/anthropic_hh/refuel.py","file_url":"https://github.com/zhaolingao/refuel/blob/HEAD/setting_two/anthropic_hh/refuel.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e78dac11b89dad63","mcp_get_code":{"code_sha256":"e78dac11b89dad63"}},{"arxiv_id":"2410.01692","paper":"/paper/u-shaped-and-inverted-u-scaling-behind","title":"U-shaped and Inverted-U Scaling behind Emergent Abilities of Large Language Models","date":"2024-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tony10101105/ExpEmergence","path":"utils.py","file_url":"https://github.com/tony10101105/ExpEmergence/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc1e46e58d7a1d2d","mcp_get_code":{"code_sha256":"bc1e46e58d7a1d2d"}},{"arxiv_id":"2406.11280","paper":"/paper/i-srt-aligning-large-multimodal-models-for","title":"ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yonseivnl/vlm-rlaif","path":"RLAIF/models/ppo_trainer.py","file_url":"https://github.com/yonseivnl/vlm-rlaif/blob/HEAD/RLAIF/models/ppo_trainer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9a0b92f09a2d6c76","mcp_get_code":{"code_sha256":"9a0b92f09a2d6c76"}},{"arxiv_id":"2406.10977","paper":"/paper/toward-optimal-llm-alignments-using-two","title":"Toward Optimal LLM Alignments Using Two-Player Games","date":"2024-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruizheng20/gpo","path":"utils.py","file_url":"https://github.com/ruizheng20/gpo/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b60c18c9b0c0e819","mcp_get_code":{"code_sha256":"b60c18c9b0c0e819"}},{"arxiv_id":"2404.16767","paper":"/paper/rebel-reinforcement-learning-via-regressing","title":"REBEL: Reinforcement Learning via Regressing Relative Rewards","date":"2024-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaolingao/rebel","path":"src/nectar/rebel.py","file_url":"https://github.com/zhaolingao/rebel/blob/HEAD/src/nectar/rebel.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"e78dac11b89dad63","mcp_get_code":{"code_sha256":"e78dac11b89dad63"}},{"arxiv_id":"2404.08495","paper":"/paper/dataset-reset-policy-optimization-for-rlhf","title":"Dataset Reset Policy Optimization for RLHF","date":"2024-04-12","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":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"e78dac11b89dad63","mcp_get_code":{"code_sha256":"e78dac11b89dad63"}},{"arxiv_id":"2401.06080","paper":"/paper/secrets-of-rlhf-in-large-language-models-part-1","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","date":"2024-01-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openlmlab/moss-rlhf","path":"utils.py","file_url":"https://github.com/openlmlab/moss-rlhf/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b60c18c9b0c0e819","mcp_get_code":{"code_sha256":"b60c18c9b0c0e819"}},{"arxiv_id":"2310.05910","paper":"/paper/salmon-self-alignment-with-principle","title":"SALMON: Self-Alignment with Instructable Reward Models","date":"2023-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ibm/salmon","path":"training/models/ppo_trainer.py","file_url":"https://github.com/ibm/salmon/blob/HEAD/training/models/ppo_trainer.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":"9a0b92f09a2d6c76","mcp_get_code":{"code_sha256":"9a0b92f09a2d6c76"}},{"arxiv_id":"2310.00052","paper":"/paper/ai-ensemble-for-signal-detection-of-higher","title":"AI ensemble for signal detection of higher order gravitational wave modes of quasi-circular, spinning, non-precessing binary black hole mergers","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mtian8/higher_order_gw_spatiotemporal_gnn","path":"data_generators.py","file_url":"https://github.com/mtian8/higher_order_gw_spatiotemporal_gnn/blob/HEAD/data_generators.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e324c4900d5614a0","mcp_get_code":{"code_sha256":"e324c4900d5614a0"}},{"arxiv_id":"2308.02223","paper":"/paper/esrl-efficient-sampling-based-reinforcement","title":"ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation","date":"2023-08-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangclnlp/DeepSpeed-Chat-Extension","path":"rlhf_llama/deepspeed_chat/training/step3_rlhf_finetuning/ppo_trainer.py","file_url":"https://github.com/wangclnlp/DeepSpeed-Chat-Extension/blob/HEAD/rlhf_llama/deepspeed_chat/training/step3_rlhf_finetuning/ppo_trainer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"fa3a56183c58c15d","mcp_get_code":{"code_sha256":"fa3a56183c58c15d"}},{"arxiv_id":"2306.01693","paper":"/paper/fine-grained-human-feedback-gives-better","title":"Fine-Grained Human Feedback Gives Better Rewards for Language Model Training","date":"2023-06-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/FineGrainedRLHF","path":"fgrlhf/ppo.py","file_url":"https://github.com/allenai/FineGrainedRLHF/blob/HEAD/fgrlhf/ppo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dd7c1d9c7f00c714","mcp_get_code":{"code_sha256":"dd7c1d9c7f00c714"}},{"arxiv_id":"2210.03078","paper":"/paper/rainier-reinforced-knowledge-introspector-for","title":"Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering","date":"2022-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liujch1998/rainier","path":"rainier/ppo.py","file_url":"https://github.com/liujch1998/rainier/blob/HEAD/rainier/ppo.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f22da26515d11255","mcp_get_code":{"code_sha256":"f22da26515d11255"}},{"arxiv_id":"2108.07478","paper":"/paper/instance-segmentation-in-3d-scenes-using","title":"Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks","date":"2021-08-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Gorilla-Lab-SCUT/SSTNet","path":"sstnet/lib/cluster/vq.py","file_url":"https://github.com/Gorilla-Lab-SCUT/SSTNet/blob/HEAD/sstnet/lib/cluster/vq.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7d2986395116fae6","mcp_get_code":{"code_sha256":"7d2986395116fae6"}},{"arxiv_id":"1608.00530","paper":"/paper/early-methods-for-detecting-adversarial","title":"Early Methods for Detecting Adversarial Images","date":"2016-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hendrycks/fooling","path":"CIFAR/fooler_generator_constrained.py","file_url":"https://github.com/hendrycks/fooling/blob/HEAD/CIFAR/fooler_generator_constrained.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ee03f4b0eaf7da6","mcp_get_code":{"code_sha256":"7ee03f4b0eaf7da6"}}]}