{"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/get-cast-dtype","entry":"get_cast_dtype","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":67,"n_papers_ran":66,"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":5,"n_samples_ran":4,"n_samples_fingerprinted":0,"n_places":70,"n_places_pointer_only":43,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":4,"ran_fixture":0,"ran":0,"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":"2609.12454","paper":"/paper/arxiv-2609-12454","title":"Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"JuzhengMiao/Spatial-FAD","path":"CLIP/model.py","file_url":"https://github.com/JuzhengMiao/Spatial-FAD/blob/HEAD/CLIP/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2601.16498","paper":"/paper/arxiv-2601-16498","title":"Expert Knowledge-Guided Decision Calibration for Accurate Fine-Grained Tree Species Classification","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"WHU-USI3DV/TreeCLS","path":"models/open_clip/model.py","file_url":"https://github.com/WHU-USI3DV/TreeCLS/blob/HEAD/models/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2505.15816","paper":"/paper/streamline-without-sacrifice-squeeze-out","title":"Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM","date":"2025-05-21","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":"61d9ad9efd32efee","mcp_get_code":{"code_sha256":"61d9ad9efd32efee"}},{"arxiv_id":"2505.15816","paper":"/paper/streamline-without-sacrifice-squeeze-out","title":"Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM","date":"2025-05-21","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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2503.19900","paper":"/paper/cafe-unifying-representation-and-generation","title":"CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning","date":"2025-03-25","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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2503.08048","paper":"/paper/longprolip-a-probabilistic-vision-language","title":"LongProLIP: A Probabilistic Vision-Language Model with Long Context Text","date":"2025-03-11","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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2503.08048","paper":"/paper/longprolip-a-probabilistic-vision-language","title":"LongProLIP: A Probabilistic Vision-Language Model with Long Context Text","date":"2025-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"0529ec3d12d83d1c","mcp_get_code":{"code_sha256":"0529ec3d12d83d1c"}},{"arxiv_id":"2503.06312","paper":"/paper/geolangbind-unifying-earth-observation-with","title":"GeoLangBind: Unifying Earth Observation with Agglomerative Vision-Language Foundation Models","date":"2025-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiong-zhitong/geolb-siglip","path":"open_clip/src/open_clip/model.py","file_url":"https://github.com/xiong-zhitong/geolb-siglip/blob/HEAD/open_clip/src/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2501.13926","paper":"/paper/can-we-generate-images-with-cot-let-s-verify","title":"Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step","date":"2025-01-23","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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2412.06014","paper":"/paper/post-hoc-probabilistic-vision-language-models","title":"Post-hoc Probabilistic Vision-Language Models","date":"2024-12-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver-ai/prolip","path":"src/prolip/model.py","file_url":"https://github.com/naver-ai/prolip/blob/HEAD/src/prolip/model.py","status":"unverified","verification_level":0,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"0529ec3d12d83d1c","mcp_get_code":{"code_sha256":"0529ec3d12d83d1c"}},{"arxiv_id":"2412.04653","paper":"/paper/hidden-in-the-noise-two-stage-robust","title":"Hidden in the Noise: Two-Stage Robust Watermarking for Images","date":"2024-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kasraarabi/Hidden-in-the-Noise","path":"open_clip/model.py","file_url":"https://github.com/Kasraarabi/Hidden-in-the-Noise/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2412.03561","paper":"/paper/flair-vlm-with-fine-grained-language-informed","title":"FLAIR: VLM with Fine-grained Language-informed Image Representations","date":"2024-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"explainableml/flair","path":"src/flair/model.py","file_url":"https://github.com/explainableml/flair/blob/HEAD/src/flair/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2411.15024","paper":"/paper/dycoke-dynamic-compression-of-tokens-for-fast","title":"DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models","date":"2024-11-22","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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2411.05195","paper":"/paper/on-erroneous-agreements-of-clip-image","title":"On Erroneous Agreements of CLIP Image Embeddings","date":"2024-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lst627/CLIP-Embeds","path":"open_clip/src/open_clip/model.py","file_url":"https://github.com/lst627/CLIP-Embeds/blob/HEAD/open_clip/src/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2411.03862","paper":"/paper/robin-robust-and-invisible-watermarks-for","title":"ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization","date":"2024-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Hannah1102/ROBIN","path":"open_clip/model.py","file_url":"https://github.com/Hannah1102/ROBIN/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2411.03554","paper":"/paper/benchmarking-vision-language-model-unlearning","title":"Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"safolab-wisc/fiubench","path":"utils.py","file_url":"https://github.com/safolab-wisc/fiubench/blob/HEAD/utils.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2411.03313","paper":"/paper/classification-done-right-for-vision-language","title":"Classification Done Right for Vision-Language Pre-Training","date":"2024-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"x-cls/superclass","path":"opencls/open_clip/model.py","file_url":"https://github.com/x-cls/superclass/blob/HEAD/opencls/open_clip/model.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":"1f22cc0143fbf7d1","mcp_get_code":{"code_sha256":"1f22cc0143fbf7d1"}},{"arxiv_id":"2411.00132","paper":"/paper/beyond-accuracy-ensuring-correct-predictions","title":"Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deep-real/DCP","path":"utils/model.py","file_url":"https://github.com/deep-real/DCP/blob/HEAD/utils/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2410.18857","paper":"/paper/probabilistic-language-image-pre-training","title":"Probabilistic Language-Image Pre-Training","date":"2024-10-24","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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2410.18472","paper":"/paper/what-if-the-input-is-expanded-in-ood","title":"What If the Input is Expanded in OOD Detection?","date":"2024-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tmlr-group/CoVer","path":"open_clip/model.py","file_url":"https://github.com/tmlr-group/CoVer/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2410.14170","paper":"/paper/personalized-image-generation-with-large","title":"Personalized Image Generation with Large Multimodal Models","date":"2024-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yiyanxu/pigeon","path":"Pigeon/models/modeling_visual_encoder.py","file_url":"https://github.com/yiyanxu/pigeon/blob/HEAD/Pigeon/models/modeling_visual_encoder.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2410.10034","paper":"/paper/tulip-token-length-upgraded-clip","title":"TULIP: Token-length Upgraded CLIP","date":"2024-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ivonajdenkoska/tulip","path":"open_clip/model.py","file_url":"https://github.com/ivonajdenkoska/tulip/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2410.05255","paper":"/paper/seppo-semi-policy-preference-optimization-for","title":"SePPO: Semi-Policy Preference Optimization for Diffusion Alignment","date":"2024-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dwanzhang-ai/seppo","path":"utils/open_clip/model.py","file_url":"https://github.com/dwanzhang-ai/seppo/blob/HEAD/utils/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2410.01768","paper":"/paper/segearth-ov-towards-traning-free-open","title":"SegEarth-OV: Towards Training-Free Open-Vocabulary Segmentation for Remote Sensing Images","date":"2024-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"likyoo/SegEarth-OV","path":"open_clip/model.py","file_url":"https://github.com/likyoo/SegEarth-OV/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2410.00320","paper":"/paper/pointad-comprehending-3d-anomalies-from","title":"PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection","date":"2024-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zqhang/accurate-winclip-pytorch","path":"src/open_clip/model.py","file_url":"https://github.com/zqhang/accurate-winclip-pytorch/blob/HEAD/src/open_clip/model.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":"1bc68318bf26bdf0","mcp_get_code":{"code_sha256":"1bc68318bf26bdf0"}},{"arxiv_id":"2409.13079","paper":"/paper/embedding-geometries-of-contrastive-language","title":"Embedding Geometries of Contrastive Language-Image Pre-Training","date":"2024-09-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eify/open_clip","path":"src/open_clip/model.py","file_url":"https://github.com/eify/open_clip/blob/HEAD/src/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2408.08849","paper":"/paper/ecg-chat-a-large-ecg-language-model-for","title":"ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosis","date":"2024-08-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YubaoZhao/ECG-Chat","path":"open_clip/open_clip/model.py","file_url":"https://github.com/YubaoZhao/ECG-Chat/blob/HEAD/open_clip/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2408.04883","paper":"/paper/proxyclip-proxy-attention-improves-clip-for","title":"ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation","date":"2024-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mc-lan/proxyclip","path":"open_clip/model.py","file_url":"https://github.com/mc-lan/proxyclip/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2407.18559","paper":"/paper/vssd-vision-mamba-with-non-casual-state-space","title":"VSSD: Vision Mamba with Non-Causal State Space Duality","date":"2024-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YuHengsss/Trident","path":"open_clip/model.py","file_url":"https://github.com/YuHengsss/Trident/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2407.15795","paper":"/paper/adaclip-adapting-clip-with-hybrid-learnable","title":"AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection","date":"2024-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"caoyunkang/adaclip","path":"method/clip_model.py","file_url":"https://github.com/caoyunkang/adaclip/blob/HEAD/method/clip_model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2407.06491","paper":"/paper/videoeval-comprehensive-benchmark-suite-for","title":"VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model","date":"2024-07-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leexinhao/VideoEval","path":"VidTAB_Zeroshot/eva_clip/model.py","file_url":"https://github.com/leexinhao/VideoEval/blob/HEAD/VidTAB_Zeroshot/eva_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2406.17639","paper":"/paper/mitigate-the-gap-investigating-approaches-for","title":"Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sarahesl/alignclip","path":"align_clip/model.py","file_url":"https://github.com/sarahesl/alignclip/blob/HEAD/align_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2406.11327","paper":"/paper/clawmachine-fetching-visual-tokens-as-an","title":"ClawMachine: Learning to Fetch Visual Tokens for Referential Comprehension","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"martian422/ClawMachine","path":"ClawMachine/model/multimodal_encoder/add_modeling_visual_encoder.py","file_url":"https://github.com/martian422/ClawMachine/blob/HEAD/ClawMachine/model/multimodal_encoder/add_modeling_visual_encoder.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2406.07543","paper":"/paper/vision-model-pre-training-on-interleaved","title":"Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opengvlab/lcl","path":"src/open_clip/model.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2406.07476","paper":"/paper/videollama-2-advancing-spatial-temporal","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"damo-nlp-sg/inf-clip","path":"inf_clip/models/clip_arch.py","file_url":"https://github.com/damo-nlp-sg/inf-clip/blob/HEAD/inf_clip/models/clip_arch.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2404.16022","paper":"/paper/pulid-pure-and-lightning-id-customization-via","title":"PuLID: Pure and Lightning ID Customization via Contrastive Alignment","date":"2024-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ToTheBeginning/PuLID","path":"eva_clip/model.py","file_url":"https://github.com/ToTheBeginning/PuLID/blob/HEAD/eva_clip/model.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":"61d9ad9efd32efee","mcp_get_code":{"code_sha256":"61d9ad9efd32efee"}},{"arxiv_id":"2404.16022","paper":"/paper/pulid-pure-and-lightning-id-customization-via","title":"PuLID: Pure and Lightning ID Customization via Contrastive Alignment","date":"2024-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zsxkib/PuLID","path":"eva_clip/model.py","file_url":"https://github.com/zsxkib/PuLID/blob/HEAD/eva_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2404.14055","paper":"/paper/ringid-rethinking-tree-ring-watermarking-for","title":"RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification","date":"2024-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/ringid","path":"open_clip/model.py","file_url":"https://github.com/showlab/ringid/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2404.13671","paper":"/paper/filo-zero-shot-anomaly-detection-by-fine","title":"FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization","date":"2024-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"casia-iva-lab/filo","path":"models/vv_open_clip/model.py","file_url":"https://github.com/casia-iva-lab/filo/blob/HEAD/models/vv_open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2404.05231","paper":"/paper/promptad-learning-prompts-with-only-normal","title":"PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection","date":"2024-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"funz-0/promptad","path":"PromptAD/CLIPAD/model.py","file_url":"https://github.com/funz-0/promptad/blob/HEAD/PromptAD/CLIPAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Unlicense","inline_ok":true,"code_sha256_prefix":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2404.04956","paper":"/paper/gaussian-shading-provable-performance","title":"Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models","date":"2024-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bsmhmmlf/Gaussian-Shading","path":"open_clip/model.py","file_url":"https://github.com/bsmhmmlf/Gaussian-Shading/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2404.02132","paper":"/paper/vitamin-designing-scalable-vision-models-in","title":"ViTamin: Designing Scalable Vision Models in the Vision-Language Era","date":"2024-04-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beckschen/vitamin","path":"ViTamin/open_clip/model.py","file_url":"https://github.com/beckschen/vitamin/blob/HEAD/ViTamin/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2403.17007","paper":"/paper/dreamlip-language-image-pre-training-with","title":"DreamLIP: Language-Image Pre-training with Long Captions","date":"2024-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zyf0619sjtu/DreamLIP","path":"open_clip/model.py","file_url":"https://github.com/zyf0619sjtu/DreamLIP/blob/HEAD/open_clip/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"CC-BY-4.0","inline_ok":false,"code_sha256_prefix":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2403.16831","paper":"/paper/urbanvlp-a-multi-granularity-vision-language","title":"UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction","date":"2024-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"citymind-lab/urbanvlp","path":"open_clip_mine/model.py","file_url":"https://github.com/citymind-lab/urbanvlp/blob/HEAD/open_clip_mine/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2403.15378","paper":"/paper/long-clip-unlocking-the-long-text-capability","title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP","date":"2024-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"beichenzbc/long-clip","path":"open_clip_long/model.py","file_url":"https://github.com/beichenzbc/long-clip/blob/HEAD/open_clip_long/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2403.12570","paper":"/paper/adapting-visual-language-models-for","title":"Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images","date":"2024-03-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mediabrain-sjtu/mvfa-ad","path":"CLIP/model.py","file_url":"https://github.com/mediabrain-sjtu/mvfa-ad/blob/HEAD/CLIP/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2403.06495","paper":"/paper/toward-generalist-anomaly-detection-via-in","title":"Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mala-lab/WinCLIP","path":"open_clip/model.py","file_url":"https://github.com/mala-lab/WinCLIP/blob/HEAD/open_clip/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2402.03161","paper":"/paper/video-lavit-unified-video-language-pre","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jy0205/lavit","path":"LaVIT/models/modeling_visual_encoder.py","file_url":"https://github.com/jy0205/lavit/blob/HEAD/LaVIT/models/modeling_visual_encoder.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2401.02955","paper":"/paper/open-vocabulary-sam-segment-and-recognize","title":"Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively","date":"2024-01-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"harboryuan/ovsam","path":"ext/open_clip/model.py","file_url":"https://github.com/harboryuan/ovsam/blob/HEAD/ext/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2312.12856","paper":"/paper/skyscript-a-large-and-semantically-diverse","title":"SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing","date":"2023-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangzhecheng/skyscript","path":"src/open_clip/model.py","file_url":"https://github.com/wangzhecheng/skyscript/blob/HEAD/src/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2312.01886","paper":"/paper/instructta-instruction-tuned-targeted-attack","title":"InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xunguangwang/instructta","path":"EVA-CLIP/rei/eva_clip/model.py","file_url":"https://github.com/xunguangwang/instructta/blob/HEAD/EVA-CLIP/rei/eva_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2311.18803","paper":"/paper/bioclip-a-vision-foundation-model-for-the","title":"BioCLIP: A Vision Foundation Model for the Tree of Life","date":"2023-11-30","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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2311.12908","paper":"/paper/diffusion-model-alignment-using-direct","title":"Diffusion Model Alignment Using Direct Preference Optimization","date":"2023-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SalesforceAIResearch/DiffusionDPO","path":"utils/open_clip/model.py","file_url":"https://github.com/SalesforceAIResearch/DiffusionDPO/blob/HEAD/utils/open_clip/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2311.04219","paper":"/paper/otterhd-a-high-resolution-multi-modality","title":"OtterHD: A High-Resolution Multi-modality Model","date":"2023-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luodian/otter","path":"pipeline/benchmarks/public_datasets_suite/models/otter.py","file_url":"https://github.com/luodian/otter/blob/HEAD/pipeline/benchmarks/public_datasets_suite/models/otter.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2310.18961","paper":"/paper/anomalyclip-object-agnostic-prompt-learning","title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","date":"2023-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zqhang/WinCLIP-pytorch","path":"src/open_clip/model.py","file_url":"https://github.com/zqhang/WinCLIP-pytorch/blob/HEAD/src/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2310.03744","paper":"/paper/improved-baselines-with-visual-instruction","title":"Improved Baselines with Visual Instruction Tuning","date":"2023-10-05","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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2309.17002","paper":"/paper/understanding-and-mitigating-the-label-noise","title":"Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Hhhhhhao/Noisy-Model-Learning","path":"open_clip/open_clip/model.py","file_url":"https://github.com/Hhhhhhao/Noisy-Model-Learning/blob/HEAD/open_clip/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2308.15939","paper":"/paper/anovl-adapting-vision-language-models-for","title":"Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization","date":"2023-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hq-deng/AnoVL","path":"open_clip/model.py","file_url":"https://github.com/hq-deng/AnoVL/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2307.12732","paper":"/paper/clip-kd-an-empirical-study-of-distilling-clip","title":"CLIP-KD: An Empirical Study of CLIP Model Distillation","date":"2023-07-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"winycg/clip-kd","path":"src/open_clip/model.py","file_url":"https://github.com/winycg/clip-kd/blob/HEAD/src/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2306.17203","paper":"/paper/diff-foley-synchronized-video-to-audio-1","title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","date":"2023-06-29","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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2305.17382","paper":"/paper/a-zero-few-shot-anomaly-classification-and","title":"APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD","date":"2023-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bychelsea/vand-april-gan","path":"open_clip/model.py","file_url":"https://github.com/bychelsea/vand-april-gan/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2304.05884","paper":"/paper/unicom-universal-and-compact-representation","title":"Unicom: Universal and Compact Representation Learning for Image Retrieval","date":"2023-04-12","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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2303.14814","paper":"/paper/winclip-zero-few-shot-anomaly-classification","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","date":"2023-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"caoyunkang/WinClip","path":"WinCLIP/CLIPAD/model.py","file_url":"https://github.com/caoyunkang/WinClip/blob/HEAD/WinCLIP/CLIPAD/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2302.03668","paper":"/paper/hard-prompts-made-easy-gradient-based-1","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","date":"2023-02-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YuxinWenRick/hard-prompts-made-easy","path":"open_clip/model.py","file_url":"https://github.com/YuxinWenRick/hard-prompts-made-easy/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2301.07094","paper":"/paper/learning-customized-visual-models-with","title":"Learning Customized Visual Models with Retrieval-Augmented Knowledge","date":"2023-01-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/react","path":"react_customization/src/open_clip/model.py","file_url":"https://github.com/microsoft/react/blob/HEAD/react_customization/src/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2212.07143","paper":"/paper/reproducible-scaling-laws-for-contrastive","title":"Reproducible scaling laws for contrastive language-image learning","date":"2022-12-14","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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2210.08402","paper":"/paper/laion-5b-an-open-large-scale-dataset-for-1","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","date":"2022-10-16","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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"2103.00020","paper":"/paper/learning-transferable-visual-models-from","title":"Learning Transferable Visual Models From Natural Language Supervision","date":"2021-02-26","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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"Ma_ReMP-AD_Retrieval-enhanced_Multi-modal_Prompt_Fusion_for_Few-Shot_Industrial_Visual_Anomaly_ICCV_2025_paper","paper":null,"title":"arXiv:Ma_ReMP-AD_Retrieval-enhanced_Multi-modal_Prompt_Fusion_for_Few-Shot_Industrial_Visual_Anomaly_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"cshcma/ReMP-AD","path":"open_clip/model.py","file_url":"https://github.com/cshcma/ReMP-AD/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"arxiv_id":"Hertz_Style_Aligned_Image_Generation_via_Shared_Attention_CVPR_2024_paper","paper":null,"title":"arXiv:Hertz_Style_Aligned_Image_Generation_via_Shared_Attention_CVPR_2024_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"aim-uofa/StyleDrop-PyTorch","path":"open_clip/model.py","file_url":"https://github.com/aim-uofa/StyleDrop-PyTorch/blob/HEAD/open_clip/model.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":"dcd422d66b0581d8","mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}}]}