{"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/stack-dicts","entry":"stack_dicts","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":11,"n_papers_ran":8,"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":6,"n_samples_ran":5,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":3,"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":"2501.06911","paper":"/paper/risk-averse-finetuning-of-large-language","title":"Risk-Averse Finetuning of Large Language Models","date":"2025-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sapanachaudhary/ra-rlhf","path":"trl/core.py","file_url":"https://github.com/sapanachaudhary/ra-rlhf/blob/HEAD/trl/core.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":"7dc16cc69c54c94d","mcp_get_code":{"code_sha256":"7dc16cc69c54c94d"}},{"arxiv_id":"2410.17637","paper":"/paper/mia-dpo-multi-image-augmented-direct","title":"MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuziyu77/mia-dpo","path":"LLaVA-Hound-DPO/llava_hound_dpo/trl/core.py","file_url":"https://github.com/liuziyu77/mia-dpo/blob/HEAD/LLaVA-Hound-DPO/llava_hound_dpo/trl/core.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":"085e70e0bd6e492d","mcp_get_code":{"code_sha256":"085e70e0bd6e492d"}},{"arxiv_id":"2410.16198","paper":"/paper/improve-vision-language-model-chain-of","title":"Improve Vision Language Model Chain-of-thought Reasoning","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"riflezhang/llava-hound-dpo","path":"llava_hound_dpo/trl/core.py","file_url":"https://github.com/riflezhang/llava-hound-dpo/blob/HEAD/llava_hound_dpo/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"085e70e0bd6e492d","mcp_get_code":{"code_sha256":"085e70e0bd6e492d"}},{"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":"snumprlab/SRT","path":"trl/core.py","file_url":"https://github.com/snumprlab/SRT/blob/HEAD/trl/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"085e70e0bd6e492d","mcp_get_code":{"code_sha256":"085e70e0bd6e492d"}},{"arxiv_id":"2403.06754","paper":"/paper/alarm-align-language-models-via-hierarchical","title":"ALaRM: Align Language Models via Hierarchical Rewards Modeling","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"halfrot/ALaRM","path":"trl/trl/core.py","file_url":"https://github.com/halfrot/ALaRM/blob/HEAD/trl/trl/core.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":"7dc16cc69c54c94d","mcp_get_code":{"code_sha256":"7dc16cc69c54c94d"}},{"arxiv_id":"2402.11078","paper":"/paper/model-editing-by-pure-fine-tuning","title":"Model Editing by Standard Fine-Tuning","date":"2024-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"au-revoir/model-editing-ft","path":"trl/core.py","file_url":"https://github.com/au-revoir/model-editing-ft/blob/HEAD/trl/core.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7dc16cc69c54c94d","mcp_get_code":{"code_sha256":"7dc16cc69c54c94d"}},{"arxiv_id":"2311.09312","paper":"/paper/h-packer-holographic-rotationally-equivariant","title":"H-Packer: Holographic Rotationally Equivariant Convolutional Neural Network for Protein Side-Chain Packing","date":"2023-11-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gvisani/hpacker","path":"hpacker/hpacker.py","file_url":"https://github.com/gvisani/hpacker/blob/HEAD/hpacker/hpacker.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6f83fa1a9fd166e8","mcp_get_code":{"code_sha256":"6f83fa1a9fd166e8"}},{"arxiv_id":"2310.14503","paper":"/paper/diversify-question-generation-with-retrieval","title":"Diversify Question Generation with Retrieval-Augmented Style Transfer","date":"2023-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gouqi666/RAST","path":"rag/core.py","file_url":"https://github.com/gouqi666/RAST/blob/HEAD/rag/core.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":"c421e6f0c295b7fb","mcp_get_code":{"code_sha256":"c421e6f0c295b7fb"}},{"arxiv_id":"2309.12253","paper":"/paper/salsa-clrs-a-sparse-and-scalable-benchmark","title":"SALSA-CLRS: A Sparse and Scalable Benchmark for Algorithmic Reasoning","date":"2023-09-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jkminder/salsa-clrs","path":"baselines/core/utils.py","file_url":"https://github.com/jkminder/salsa-clrs/blob/HEAD/baselines/core/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":"1e034dd26fd03851","mcp_get_code":{"code_sha256":"1e034dd26fd03851"}},{"arxiv_id":"2206.00761","paper":"/paper/on-reinforcement-learning-and-distribution","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","date":"2022-06-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver/gdc","path":"cdpg/cdpg/core.py","file_url":"https://github.com/naver/gdc/blob/HEAD/cdpg/cdpg/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"c421e6f0c295b7fb","mcp_get_code":{"code_sha256":"c421e6f0c295b7fb"}},{"arxiv_id":"2012.11635","paper":"/paper/2012-11635","title":"A Distributional Approach to Controlled Text Generation","date":"2020-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver/gdc","path":"dpg/gdc/gdc/core.py","file_url":"https://github.com/naver/gdc/blob/HEAD/dpg/gdc/gdc/core.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0757e25958eb0a41","mcp_get_code":{"code_sha256":"0757e25958eb0a41"}},{"arxiv_id":"2012.11635","paper":"/paper/2012-11635","title":"A Distributional Approach to Controlled Text Generation","date":"2020-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"c421e6f0c295b7fb","mcp_get_code":{"code_sha256":"c421e6f0c295b7fb"}}]}