{"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/pre-caption","entry":"pre_caption","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":17,"n_papers_ran":9,"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":4,"n_samples_ran":3,"n_samples_fingerprinted":2,"n_places":17,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"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":"2506.05890","paper":"/paper/unleashing-the-potential-of-consistency-1","title":"Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation","date":"2025-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liyih/CSCL","path":"code/MultiModal-DeepFake-main/dataset/utils.py","file_url":"https://github.com/liyih/CSCL/blob/HEAD/code/MultiModal-DeepFake-main/dataset/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a57c3e7d1cf36c7","mcp_get_code":{"code_sha256":"8a57c3e7d1cf36c7"}},{"arxiv_id":"2505.05528","paper":"/paper/x-transfer-attacks-towards-super-transferable","title":"X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP","date":"2025-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanxunh/xtransferbench","path":"xtransfer/datasets/caption_dataset.py","file_url":"https://github.com/hanxunh/xtransferbench/blob/HEAD/xtransfer/datasets/caption_dataset.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2ed5f99d405e8fbe","mcp_get_code":{"code_sha256":"2ed5f99d405e8fbe"}},{"arxiv_id":"2411.02669","paper":"/paper/semantic-aligned-adversarial-evolution","title":"Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack","date":"2024-11-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiaxiaojunqaq/sa-aet","path":"dataset.py","file_url":"https://github.com/jiaxiaojunqaq/sa-aet/blob/HEAD/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a57c3e7d1cf36c7","mcp_get_code":{"code_sha256":"8a57c3e7d1cf36c7"}},{"arxiv_id":"2409.17958","paper":"/paper/the-hard-positive-truth-about-vision-language","title":"The Hard Positive Truth about Vision-Language Compositionality","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amitakamath/hard_positives","path":"dataset_zoo/retrieval.py","file_url":"https://github.com/amitakamath/hard_positives/blob/HEAD/dataset_zoo/retrieval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d760ca65749dc14","mcp_get_code":{"code_sha256":"0d760ca65749dc14"}},{"arxiv_id":"2407.16658","paper":"/paper/egocvr-an-egocentric-benchmark-for-fine","title":"EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval","date":"2024-07-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"explainableml/egocvr","path":"model/utils.py","file_url":"https://github.com/explainableml/egocvr/blob/HEAD/model/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d760ca65749dc14","mcp_get_code":{"code_sha256":"0d760ca65749dc14"}},{"arxiv_id":"2406.05491","paper":"/paper/one-perturbation-is-enough-on-generating","title":"One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models","date":"2024-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ffhibnese/cpgc_vlp_universal_attacks","path":"dataset.py","file_url":"https://github.com/ffhibnese/cpgc_vlp_universal_attacks/blob/HEAD/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a57c3e7d1cf36c7","mcp_get_code":{"code_sha256":"8a57c3e7d1cf36c7"}},{"arxiv_id":"2310.19785","paper":"/paper/what-s-up-with-vision-language-models","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","date":"2023-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amitakamath/whatsup_vlms","path":"dataset_zoo/retrieval.py","file_url":"https://github.com/amitakamath/whatsup_vlms/blob/HEAD/dataset_zoo/retrieval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d760ca65749dc14","mcp_get_code":{"code_sha256":"0d760ca65749dc14"}},{"arxiv_id":"2310.17530","paper":"/paper/evaluating-bias-and-fairness-in-gender","title":"Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models","date":"2023-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"coastalcph/gender-neutral-vl","path":"src/ALBEF/predict.py","file_url":"https://github.com/coastalcph/gender-neutral-vl/blob/HEAD/src/ALBEF/predict.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":"01b53990698e354e","mcp_get_code":{"code_sha256":"01b53990698e354e"}},{"arxiv_id":"2310.07972","paper":"/paper/interpretable-diffusion-via-information","title":"Interpretable Diffusion via Information Decomposition","date":"2023-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kxh001/info-decomp","path":"utils/aro_datasets.py","file_url":"https://github.com/kxh001/info-decomp/blob/HEAD/utils/aro_datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d760ca65749dc14","mcp_get_code":{"code_sha256":"0d760ca65749dc14"}},{"arxiv_id":"2309.14203","paper":"/paper/detecting-and-grounding-multi-modal-media-1","title":"Detecting and Grounding Multi-Modal Media Manipulation and Beyond","date":"2023-09-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rshaojimmy/multimodal-deepfake","path":"dataset/utils.py","file_url":"https://github.com/rshaojimmy/multimodal-deepfake/blob/HEAD/dataset/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8a57c3e7d1cf36c7","mcp_get_code":{"code_sha256":"8a57c3e7d1cf36c7"}},{"arxiv_id":"2308.04380","paper":"/paper/your-negative-may-not-be-true-negative","title":"Your Negative May not Be True Negative: Boosting Image-Text Matching with False Negative Elimination","date":"2023-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luminosityx/fne","path":"data.py","file_url":"https://github.com/luminosityx/fne/blob/HEAD/data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"8a57c3e7d1cf36c7","mcp_get_code":{"code_sha256":"8a57c3e7d1cf36c7"}},{"arxiv_id":"2307.14061","paper":"/paper/set-level-guidance-attack-boosting","title":"Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models","date":"2023-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Zoky-2020/Set-level_Guidance_Attack","path":"dataset.py","file_url":"https://github.com/Zoky-2020/Set-level_Guidance_Attack/blob/HEAD/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a57c3e7d1cf36c7","mcp_get_code":{"code_sha256":"8a57c3e7d1cf36c7"}},{"arxiv_id":"2305.13653","paper":"/paper/rasa-relation-and-sensitivity-aware","title":"RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Flame-Chasers/RaSa","path":"dataset/utils.py","file_url":"https://github.com/Flame-Chasers/RaSa/blob/HEAD/dataset/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a57c3e7d1cf36c7","mcp_get_code":{"code_sha256":"8a57c3e7d1cf36c7"}},{"arxiv_id":"2305.07558","paper":"/paper/measuring-progress-in-fine-grained-vision-and","title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","date":"2023-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"e-bug/fine-grained-evals","path":"models/ALBEF/predict.py","file_url":"https://github.com/e-bug/fine-grained-evals/blob/HEAD/models/ALBEF/predict.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":"01b53990698e354e","mcp_get_code":{"code_sha256":"01b53990698e354e"}},{"arxiv_id":"2303.10323","paper":"/paper/dynamic-graph-enhanced-contrastive-learning","title":"Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation","date":"2023-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mlii0117/dcl","path":"blip_original/utils.py","file_url":"https://github.com/mlii0117/dcl/blob/HEAD/blip_original/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d760ca65749dc14","mcp_get_code":{"code_sha256":"0d760ca65749dc14"}},{"arxiv_id":"2210.01936","paper":"/paper/when-and-why-vision-language-models-behave","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","date":"2022-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mertyg/vision-language-models-are-bows","path":"dataset_zoo/retrieval.py","file_url":"https://github.com/mertyg/vision-language-models-are-bows/blob/HEAD/dataset_zoo/retrieval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d760ca65749dc14","mcp_get_code":{"code_sha256":"0d760ca65749dc14"}},{"arxiv_id":"2207.05333","paper":"/paper/idea-increasing-text-diversity-via-online","title":"IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training","date":"2022-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xinyu1205/idea-pytorch","path":"dataset/utils.py","file_url":"https://github.com/xinyu1205/idea-pytorch/blob/HEAD/dataset/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a57c3e7d1cf36c7","mcp_get_code":{"code_sha256":"8a57c3e7d1cf36c7"}}]}