{"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/remove-special-tokens","entry":"remove_special_tokens","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":10,"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":7,"n_samples_ran":3,"n_samples_fingerprinted":3,"n_places":12,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":4},"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":"2506.07520","paper":"/paper/levo-high-quality-song-generation-with-multi","title":"LeVo: High-Quality Song Generation with Multi-Preference Alignment","date":"2025-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RifleZhang/LLaVA-Hound-DPO","path":"llava_hound_dpo/inference/inference.py","file_url":"https://github.com/RifleZhang/LLaVA-Hound-DPO/blob/HEAD/llava_hound_dpo/inference/inference.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4354061aab23f5b9","mcp_get_code":{"code_sha256":"4354061aab23f5b9"}},{"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":null,"path":"","file_url":null,"status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"4354061aab23f5b9","mcp_get_code":{"code_sha256":"4354061aab23f5b9"}},{"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/chatuniv/chatuniv_utils.py","file_url":"https://github.com/liuziyu77/mia-dpo/blob/HEAD/LLaVA-Hound-DPO/chatuniv/chatuniv_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":"663e3b5a6740fa0d","mcp_get_code":{"code_sha256":"663e3b5a6740fa0d"}},{"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/llama_vid/llamavid_utils.py","file_url":"https://github.com/liuziyu77/mia-dpo/blob/HEAD/LLaVA-Hound-DPO/llama_vid/llamavid_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":"160197f694bfebd8","mcp_get_code":{"code_sha256":"160197f694bfebd8"}},{"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/inference/inference.py","file_url":"https://github.com/riflezhang/llava-hound-dpo/blob/HEAD/llava_hound_dpo/inference/inference.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4354061aab23f5b9","mcp_get_code":{"code_sha256":"4354061aab23f5b9"}},{"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":"inference/inference.py","file_url":"https://github.com/snumprlab/SRT/blob/HEAD/inference/inference.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4354061aab23f5b9","mcp_get_code":{"code_sha256":"4354061aab23f5b9"}},{"arxiv_id":"2404.01258","paper":"/paper/direct-preference-optimization-of-video-large","title":"Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward","date":"2024-04-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"4354061aab23f5b9","mcp_get_code":{"code_sha256":"4354061aab23f5b9"}},{"arxiv_id":"2403.20127","paper":"/paper/the-impact-of-prompts-on-zero-shot-detection","title":"The Impact of Prompts on Zero-Shot Detection of AI-Generated Text","date":"2024-03-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kaito25atugich/detector","path":"tmp/paraphraser.py","file_url":"https://github.com/kaito25atugich/detector/blob/HEAD/tmp/paraphraser.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f6d96afa1d60eb61","mcp_get_code":{"code_sha256":"f6d96afa1d60eb61"}},{"arxiv_id":"2311.08348","paper":"/paper/mc-2-a-multilingual-corpus-of-minority","title":"MC$^2$: Towards Transparent and Culturally-Aware NLP for Minority Languages in China","date":"2023-11-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luciusssss/mlic-eval","path":"infer.py","file_url":"https://github.com/luciusssss/mlic-eval/blob/HEAD/infer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dc6235427befec3f","mcp_get_code":{"code_sha256":"dc6235427befec3f"}},{"arxiv_id":"2004.05150","paper":"/paper/longformer-the-long-document-transformer","title":"Longformer: The Long-Document Transformer","date":"2020-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"a-rios/ats-models","path":"ats_models/finetune_mbart.py","file_url":"https://github.com/a-rios/ats-models/blob/HEAD/ats_models/finetune_mbart.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":"bce6838014c76d1e","mcp_get_code":{"code_sha256":"bce6838014c76d1e"}},{"arxiv_id":"1502.03044","paper":"/paper/show-attend-and-tell-neural-image-caption","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","date":"2015-02-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yurayli/image_caption_pytorch","path":"eval_metrics.py","file_url":"https://github.com/yurayli/image_caption_pytorch/blob/HEAD/eval_metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9bfeeae84da4c830","mcp_get_code":{"code_sha256":"9bfeeae84da4c830"}},{"arxiv_id":"1411.4555","paper":"/paper/show-and-tell-a-neural-image-caption","title":"Show and Tell: A Neural Image Caption Generator","date":"2014-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yurayli/image-caption-pytorch","path":"eval_metrics.py","file_url":"https://github.com/yurayli/image-caption-pytorch/blob/HEAD/eval_metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9bfeeae84da4c830","mcp_get_code":{"code_sha256":"9bfeeae84da4c830"}}]}