{"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/combine-coco-captions","entry":"combine_coco_captions","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-25T09:33:49+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":11,"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":2,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":0,"unverified":0},"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":"2609.01888","paper":"/paper/arxiv-2609-01888","title":"Does Playing it Safe Count as Faithfulness? Reassessing LVLM Hallucination Mitigation Methods","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"mehrdadfazli/AssessHalVLM","path":"eval/chair.py","file_url":"https://github.com/mehrdadfazli/AssessHalVLM/blob/HEAD/eval/chair.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":"25585704d77cafb4","mcp_get_code":{"code_sha256":"25585704d77cafb4"}},{"arxiv_id":"2504.13169","paper":"/paper/generate-but-verify-reducing-hallucination-in","title":"Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling","date":"2025-04-17","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":"25585704d77cafb4","mcp_get_code":{"code_sha256":"25585704d77cafb4"}},{"arxiv_id":"2502.03628","paper":"/paper/the-hidden-life-of-tokens-reducing","title":"The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering","date":"2025-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LzVv123456/VISTA","path":"chair_ans.py","file_url":"https://github.com/LzVv123456/VISTA/blob/HEAD/chair_ans.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"25585704d77cafb4","mcp_get_code":{"code_sha256":"25585704d77cafb4"}},{"arxiv_id":"2501.16629","paper":"/paper/chip-cross-modal-hierarchical-direct","title":"CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs","date":"2025-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lvugai/chip","path":"eval/eval_gpt_obj_halbench.py","file_url":"https://github.com/lvugai/chip/blob/HEAD/eval/eval_gpt_obj_halbench.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"25585704d77cafb4","mcp_get_code":{"code_sha256":"25585704d77cafb4"}},{"arxiv_id":"2412.06474","paper":"/paper/from-uncertainty-to-trust-enhancing","title":"From Uncertainty to Trust: Enhancing Reliability in Vision-Language Models with Uncertainty-Guided Dropout Decoding","date":"2024-12-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kigb/DropoutDecoding","path":"chair_test/chair_metrics/chair.py","file_url":"https://github.com/kigb/DropoutDecoding/blob/HEAD/chair_test/chair_metrics/chair.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":"25585704d77cafb4","mcp_get_code":{"code_sha256":"25585704d77cafb4"}},{"arxiv_id":"2411.16724","paper":"/paper/devils-in-middle-layers-of-large-vision","title":"Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens","date":"2024-11-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhangqijiang07/middle_layers_indicating_hallucinations","path":"chair.py","file_url":"https://github.com/zhangqijiang07/middle_layers_indicating_hallucinations/blob/HEAD/chair.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":"25585704d77cafb4","mcp_get_code":{"code_sha256":"25585704d77cafb4"}},{"arxiv_id":"2405.17220","paper":"/paper/rlaif-v-aligning-mllms-through-open-source-ai","title":"RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rlhf-v/rlhf-v","path":"eval/eval_gpt_obj_halbench.py","file_url":"https://github.com/rlhf-v/rlhf-v/blob/HEAD/eval/eval_gpt_obj_halbench.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":"25585704d77cafb4","mcp_get_code":{"code_sha256":"25585704d77cafb4"}},{"arxiv_id":"2402.14545","paper":"/paper/less-is-more-mitigating-multimodal","title":"Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective","date":"2024-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuezih/less-is-more","path":"CHAIR-eval/chair.py","file_url":"https://github.com/yuezih/less-is-more/blob/HEAD/CHAIR-eval/chair.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"25585704d77cafb4","mcp_get_code":{"code_sha256":"25585704d77cafb4"}},{"arxiv_id":"2110.01705","paper":"/paper/let-there-be-a-clock-on-the-beach-reducing","title":"Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning","date":"2021-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"furkanbiten/object-bias","path":"chair/utils/chair.py","file_url":"https://github.com/furkanbiten/object-bias/blob/HEAD/chair/utils/chair.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ee0eaa40d818b077","mcp_get_code":{"code_sha256":"ee0eaa40d818b077"}},{"arxiv_id":"Huang_OPERA_Alleviating_Hallucination_in_Multi-Modal_Large_Language_Models_via_Over-Trust_CVPR_2024_paper","paper":null,"title":"arXiv:Huang_OPERA_Alleviating_Hallucination_in_Multi-Modal_Large_Language_Models_via_Over-Trust_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"shikiw/OPERA","path":"chair.py","file_url":"https://github.com/shikiw/OPERA/blob/HEAD/chair.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"25585704d77cafb4","mcp_get_code":{"code_sha256":"25585704d77cafb4"}},{"arxiv_id":"2025.acl-long.175","paper":null,"title":"arXiv:2025.acl-long.175","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"jinghan1he/VHR","path":"eval/chair.py","file_url":"https://github.com/jinghan1he/VHR/blob/HEAD/eval/chair.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"25585704d77cafb4","mcp_get_code":{"code_sha256":"25585704d77cafb4"}}]}