{"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/compute-loss","entry":"compute_loss","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":97,"n_papers_ran":58,"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":88,"n_samples_ran":48,"n_samples_fingerprinted":9,"n_places":102,"n_places_pointer_only":38,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":19,"ran_fixture":14,"ran":13,"unverified":40},"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":"2606.21447","paper":"/paper/arxiv-2606-21447","title":"Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"98lingchen/MICCAI2026","path":"modules/loss.py","file_url":"https://github.com/98lingchen/MICCAI2026/blob/HEAD/modules/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0bc1f8b3524f6b1b","mcp_get_code":{"code_sha256":"0bc1f8b3524f6b1b"}},{"arxiv_id":"2606.12733","paper":"/paper/arxiv-2606-12733","title":"Let's Ask Gauss: Improved One-Run Privacy Auditing","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"stoneboat/dpsgd-auditbench","path":"src/inference.py","file_url":"https://github.com/stoneboat/dpsgd-auditbench/blob/HEAD/src/inference.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e7c6b4309721f5e3","mcp_get_code":{"code_sha256":"e7c6b4309721f5e3"}},{"arxiv_id":"2606.07529","paper":"/paper/arxiv-2606-07529","title":"CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"fz-zsl/CAPruner","path":"model/loss.py","file_url":"https://github.com/fz-zsl/CAPruner/blob/HEAD/model/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"62885a5ffc303fa7","mcp_get_code":{"code_sha256":"62885a5ffc303fa7"}},{"arxiv_id":"2604.00012","paper":"/paper/arxiv-2604-00012","title":"Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms","date":"2026-03-10","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"homles11/SafeReAct","path":"src/lorra_safereact_twomodel.py","file_url":"https://github.com/homles11/SafeReAct/blob/HEAD/src/lorra_safereact_twomodel.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d1dd495be55f8726","mcp_get_code":{"code_sha256":"d1dd495be55f8726"}},{"arxiv_id":"2603.12478","paper":"/paper/arxiv-2603-12478","title":"Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"rujiewu/GDO","path":"gdo/extract_six_metrics.py","file_url":"https://github.com/rujiewu/GDO/blob/HEAD/gdo/extract_six_metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a71fb50b5b3bd84e","mcp_get_code":{"code_sha256":"a71fb50b5b3bd84e"}},{"arxiv_id":"2603.09187","paper":"/paper/arxiv-2603-09187","title":"The Costs of Reproducibility in Music Separation Research: a Replication of Band-Split RNN","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"magronp/bsrnn","path":"models/pl_module.py","file_url":"https://github.com/magronp/bsrnn/blob/HEAD/models/pl_module.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"758bc54b40e8eacb","mcp_get_code":{"code_sha256":"758bc54b40e8eacb"}},{"arxiv_id":"2603.06602","paper":"/paper/arxiv-2603-06602","title":"Khatri-Rao Clustering for Data Summarization","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"maciap/KhatriRaoClustering","path":"KathriRaokMeans/kr_k_means_space_efficient.py","file_url":"https://github.com/maciap/KhatriRaoClustering/blob/HEAD/KathriRaokMeans/kr_k_means_space_efficient.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0968a696dc7ad1ab","mcp_get_code":{"code_sha256":"0968a696dc7ad1ab"}},{"arxiv_id":"2602.12262","paper":"/paper/arxiv-2602-12262","title":"Few-Step Diffusion Language Models via Trajectory Self-Distillation","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Tyrion58/T3D","path":"train/self_ddo_sdar_full.py","file_url":"https://github.com/Tyrion58/T3D/blob/HEAD/train/self_ddo_sdar_full.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2702574928a47f9b","mcp_get_code":{"code_sha256":"2702574928a47f9b"}},{"arxiv_id":"2506.05454","paper":"/paper/zeroth-order-optimization-finds-flat-minima","title":"Zeroth-Order Optimization Finds Flat Minima","date":"2025-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Liang137/FlatZero","path":"svm_logreg/logreg.py","file_url":"https://github.com/Liang137/FlatZero/blob/HEAD/svm_logreg/logreg.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ebcc930731af124","mcp_get_code":{"code_sha256":"3ebcc930731af124"}},{"arxiv_id":"2506.03355","paper":"/paper/robustness-in-both-domains-clip-needs-a","title":"Robustness in Both Domains: CLIP Needs a Robust Text Encoder","date":"2025-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LIONS-EPFL/LEAF","path":"src/robust_vlm/train/adversarial_training_clip.py","file_url":"https://github.com/LIONS-EPFL/LEAF/blob/HEAD/src/robust_vlm/train/adversarial_training_clip.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3bdfc4201b35c55b","mcp_get_code":{"code_sha256":"3bdfc4201b35c55b"}},{"arxiv_id":"2506.02557","paper":null,"title":"arXiv:2506.02557","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"peterant330/KUEA","path":"train/align_training_clip.py","file_url":"https://github.com/peterant330/KUEA/blob/HEAD/train/align_training_clip.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"735c7110db767760","mcp_get_code":{"code_sha256":"735c7110db767760"}},{"arxiv_id":"2504.18425","paper":"/paper/kimi-audio-technical-report","title":"Kimi-Audio Technical Report","date":"2025-04-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"moonshotai/kimi-audio","path":"finetune.py","file_url":"https://github.com/moonshotai/kimi-audio/blob/HEAD/finetune.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"318777afeb70ea36","mcp_get_code":{"code_sha256":"318777afeb70ea36"}},{"arxiv_id":"2502.14910","paper":null,"title":"arXiv:2502.14910","date":null,"month_inferred_from_arxiv_id":"2025-02","title_source":null,"repo":"luffy06/EvoP","path":"src/utils/eval_utils.py","file_url":"https://github.com/luffy06/EvoP/blob/HEAD/src/utils/eval_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":"fe39fa61a150100a","mcp_get_code":{"code_sha256":"fe39fa61a150100a"}},{"arxiv_id":"2502.14829","paper":"/paper/measuring-faithfulness-of-chains-of-thought","title":"Measuring Faithfulness of Chains of Thought by Unlearning Reasoning Steps","date":"2025-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"technion-cs-nlp/parametric-faithfulness","path":"unlearn.py","file_url":"https://github.com/technion-cs-nlp/parametric-faithfulness/blob/HEAD/unlearn.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"38bd8b876fbfb660","mcp_get_code":{"code_sha256":"38bd8b876fbfb660"}},{"arxiv_id":"2502.13061","paper":"/paper/improved-fine-tuning-of-large-multimodal-1","title":"Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection","date":"2025-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JingbiaoMei/RGCL","path":"src/model/loss.py","file_url":"https://github.com/JingbiaoMei/RGCL/blob/HEAD/src/model/loss.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":"e29c3311f99491d1","mcp_get_code":{"code_sha256":"e29c3311f99491d1"}},{"arxiv_id":"2502.09990","paper":"/paper/x-boundary-establishing-exact-safety-boundary","title":"X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability","date":"2025-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ai45lab/x-boundary","path":"src/lorra_x_boundary.py","file_url":"https://github.com/ai45lab/x-boundary/blob/HEAD/src/lorra_x_boundary.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d11d2248331f1c58","mcp_get_code":{"code_sha256":"d11d2248331f1c58"}},{"arxiv_id":"2501.08508","paper":"/paper/score-based-3d-molecule-generation-with","title":"Score-based 3D molecule generation with neural fields","date":"2025-01-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"prescient-design/funcmol","path":"funcmol/train_fm.py","file_url":"https://github.com/prescient-design/funcmol/blob/HEAD/funcmol/train_fm.py","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"7b1a37ddac58dc58","mcp_get_code":{"code_sha256":"7b1a37ddac58dc58"}},{"arxiv_id":"2412.12865","paper":"/paper/preference-oriented-supervised-fine-tuning","title":"Preference-Oriented Supervised Fine-Tuning: Favoring Target Model Over Aligned Large Language Models","date":"2024-12-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Savannah120/alignment-handbook-PoFT","path":"generate_preference_scores.py","file_url":"https://github.com/Savannah120/alignment-handbook-PoFT/blob/HEAD/generate_preference_scores.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d1e156f54d1adeec","mcp_get_code":{"code_sha256":"d1e156f54d1adeec"}},{"arxiv_id":"2410.16531","paper":"/paper/bayesian-scaling-laws-for-in-context-learning","title":"Bayesian scaling laws for in-context learning","date":"2024-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aryamanarora/bayesian-laws-icl","path":"bayesian_laws_icl/analyse.py","file_url":"https://github.com/aryamanarora/bayesian-laws-icl/blob/HEAD/bayesian_laws_icl/analyse.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"303d355d2a45ca05","mcp_get_code":{"code_sha256":"303d355d2a45ca05"}},{"arxiv_id":"2409.17687","paper":"/paper/graph-edit-distance-with-general-costs-using","title":"Graph Edit Distance with General Costs Using Neural Set Divergence","date":"2024-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"structlearning/graphedx","path":"models/graphedx.py","file_url":"https://github.com/structlearning/graphedx/blob/HEAD/models/graphedx.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"310b4b2e126ed8b6","mcp_get_code":{"code_sha256":"310b4b2e126ed8b6"}},{"arxiv_id":"2407.11942","paper":"/paper/context-guided-diffusion-for-out-of","title":"Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design","date":"2024-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leojklarner/context-guided-diffusion","path":"materials/train_edm.py","file_url":"https://github.com/leojklarner/context-guided-diffusion/blob/HEAD/materials/train_edm.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"59178d244fffc6d5","mcp_get_code":{"code_sha256":"59178d244fffc6d5"}},{"arxiv_id":"2407.11756","paper":"/paper/a-theoretical-formulation-of-many-body","title":"A Theoretical Formulation of Many-body Message Passing Neural Networks","date":"2024-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jthh/many-body-mpnn","path":"utils.py","file_url":"https://github.com/jthh/many-body-mpnn/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"85f5e308f40e82df","mcp_get_code":{"code_sha256":"85f5e308f40e82df"}},{"arxiv_id":"2407.07564","paper":"/paper/trainable-highly-expressive-activation","title":"Trainable Highly-expressive Activation Functions","date":"2024-07-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bgu-cs-vil/ditac","path":"regression_example/evaluation.py","file_url":"https://github.com/bgu-cs-vil/ditac/blob/HEAD/regression_example/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"442198b32b497424","mcp_get_code":{"code_sha256":"442198b32b497424"}},{"arxiv_id":"2406.12128","paper":"/paper/ai-news-content-farms-are-easy-to-make-and","title":"AI \"News\" Content Farms Are Easy to Make and Hard to Detect: A Case Study in Italian","date":"2024-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gpucce/synthetic_llm_data","path":"src/synthetic_detection/detect_gpt/utils/detect_gpt_utils.py","file_url":"https://github.com/gpucce/synthetic_llm_data/blob/HEAD/src/synthetic_detection/detect_gpt/utils/detect_gpt_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2e7fdfbb51f8c89a","mcp_get_code":{"code_sha256":"2e7fdfbb51f8c89a"}},{"arxiv_id":"2406.06246","paper":"/paper/data-efficient-learning-with-neural-programs","title":"Data-Efficient Learning with Neural Programs","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alaiasolkobreslin/ised","path":"custom/sudoku/src/ised.py","file_url":"https://github.com/alaiasolkobreslin/ised/blob/HEAD/custom/sudoku/src/ised.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39b961f06732092a","mcp_get_code":{"code_sha256":"39b961f06732092a"}},{"arxiv_id":"2406.04313","paper":"/paper/improving-alignment-and-robustness-with-short","title":"Improving Alignment and Robustness with Circuit Breakers","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"grayswanai/circuit-breakers","path":"src/lorra_circuit_breaker.py","file_url":"https://github.com/grayswanai/circuit-breakers/blob/HEAD/src/lorra_circuit_breaker.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b5b12432e2c1124d","mcp_get_code":{"code_sha256":"b5b12432e2c1124d"}},{"arxiv_id":"2405.18406","paper":"/paper/raccoon-remove-add-and-change-video-content","title":"RACCooN: A Versatile Instructional Video Editing Framework with Auto-Generated Narratives","date":"2024-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adymaharana/adapt-inf","path":"llava/eval/model_data_scores_batched.py","file_url":"https://github.com/adymaharana/adapt-inf/blob/HEAD/llava/eval/model_data_scores_batched.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dc10f040adbba7f5","mcp_get_code":{"code_sha256":"dc10f040adbba7f5"}},{"arxiv_id":"2405.16435","paper":"/paper/structure-aware-semantic-node-identifiers-for","title":"Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LUOyk1999/NodeID","path":"SL/Graph_Classification/ID_MLP_f.py","file_url":"https://github.com/LUOyk1999/NodeID/blob/HEAD/SL/Graph_Classification/ID_MLP_f.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"135fdcc9a2764c3c","mcp_get_code":{"code_sha256":"135fdcc9a2764c3c"}},{"arxiv_id":"2405.00662","paper":"/paper/no-representation-no-trust-connecting","title":"No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO","date":"2024-05-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"claire-labo/no-representation-no-trust","path":"src/po_dynamics/toy_problem.py","file_url":"https://github.com/claire-labo/no-representation-no-trust/blob/HEAD/src/po_dynamics/toy_problem.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dfa6b6e94ad09908","mcp_get_code":{"code_sha256":"dfa6b6e94ad09908"}},{"arxiv_id":"2404.07991","paper":"/paper/gomavatar-efficient-animatable-human-modeling","title":"GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh","date":"2024-04-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wenj/GoMAvatar","path":"train_pose.py","file_url":"https://github.com/wenj/GoMAvatar/blob/HEAD/train_pose.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ef5d10bbaa353d56","mcp_get_code":{"code_sha256":"ef5d10bbaa353d56"}},{"arxiv_id":"2403.09085","paper":"/paper/meaningful-learning-advancing-abstract","title":"Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance","date":"2024-03-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Waste-Wood/MeanLearn","path":"reason_ppl.py","file_url":"https://github.com/Waste-Wood/MeanLearn/blob/HEAD/reason_ppl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e48818bea6862619","mcp_get_code":{"code_sha256":"e48818bea6862619"}},{"arxiv_id":"2403.06801","paper":"/paper/ct2rep-automated-radiology-report-generation","title":"CT2Rep: Automated Radiology Report Generation for 3D Medical Imaging","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ibrahimethemhamamci/ct2rep","path":"CT2Rep/modules/loss.py","file_url":"https://github.com/ibrahimethemhamamci/ct2rep/blob/HEAD/CT2Rep/modules/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0bc1f8b3524f6b1b","mcp_get_code":{"code_sha256":"0bc1f8b3524f6b1b"}},{"arxiv_id":"2403.03516","paper":"/paper/unsupervised-multilingual-dense-retrieval-via","title":"Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling","date":"2024-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MiuLab/UMR","path":"dpr/models/reader.py","file_url":"https://github.com/MiuLab/UMR/blob/HEAD/dpr/models/reader.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1df81ea9d2da7b70","mcp_get_code":{"code_sha256":"1df81ea9d2da7b70"}},{"arxiv_id":"2403.00543","paper":"/paper/sure-survey-recipes-for-building-reliable-and","title":"SURE: SUrvey REcipes for building reliable and robust deep networks","date":"2024-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YutingLi0606/SURE","path":"train_finetune.py","file_url":"https://github.com/YutingLi0606/SURE/blob/HEAD/train_finetune.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d577c874c4871163","mcp_get_code":{"code_sha256":"d577c874c4871163"}},{"arxiv_id":"2402.13532","paper":"/paper/backdoor-attacks-on-dense-passage-retrievers","title":"Whispers in Grammars: Injecting Covert Backdoors to Compromise Dense Retrieval Systems","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruyue0001/backdoor_dpr","path":"DPR/dpr/models/reader.py","file_url":"https://github.com/ruyue0001/backdoor_dpr/blob/HEAD/DPR/dpr/models/reader.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1df81ea9d2da7b70","mcp_get_code":{"code_sha256":"1df81ea9d2da7b70"}},{"arxiv_id":"2402.12336","paper":"/paper/robust-clip-unsupervised-adversarial-fine","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chs20/robustvlm","path":"train/adversarial_training_clip.py","file_url":"https://github.com/chs20/robustvlm/blob/HEAD/train/adversarial_training_clip.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"75f68885e2ff2684","mcp_get_code":{"code_sha256":"75f68885e2ff2684"}},{"arxiv_id":"2402.12336","paper":"/paper/robust-clip-unsupervised-adversarial-fine","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chs20/robustvlm","path":"train/adversarial_training_clip.py","file_url":"https://github.com/chs20/robustvlm/blob/HEAD/train/adversarial_training_clip.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b03f0274dabbb8c0","mcp_get_code":{"code_sha256":"b03f0274dabbb8c0"}},{"arxiv_id":"2402.09963","paper":"/paper/why-are-sensitive-functions-hard-for","title":"Why are Sensitive Functions Hard for Transformers?","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lacoco-lab/sensitivity-hardness","path":"src/utils.py","file_url":"https://github.com/lacoco-lab/sensitivity-hardness/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7f7f4130d5f9842f","mcp_get_code":{"code_sha256":"7f7f4130d5f9842f"}},{"arxiv_id":"2312.04693","paper":"/paper/graphmetro-mitigating-complex-distribution","title":"GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts","date":"2023-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wuyxin/graphmetro","path":"graphmetro/train/loss.py","file_url":"https://github.com/wuyxin/graphmetro/blob/HEAD/graphmetro/train/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3c726e8fd7a6c81d","mcp_get_code":{"code_sha256":"3c726e8fd7a6c81d"}},{"arxiv_id":"2311.17491","paper":"/paper/spherical-frustum-sparse-convolution-network","title":"Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation","date":"2023-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IRMVLab/SFCNet","path":"SFCNet/network/loss_func_layer.py","file_url":"https://github.com/IRMVLab/SFCNet/blob/HEAD/SFCNet/network/loss_func_layer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0205aa85d121cd2e","mcp_get_code":{"code_sha256":"0205aa85d121cd2e"}},{"arxiv_id":"2310.19011","paper":"/paper/efficient-test-time-adaptation-for-super-1","title":"Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction","date":"2023-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DengZeshuai/SRTTA","path":"src/srtta.py","file_url":"https://github.com/DengZeshuai/SRTTA/blob/HEAD/src/srtta.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"06a1ef9308233244","mcp_get_code":{"code_sha256":"06a1ef9308233244"}},{"arxiv_id":"2310.16944","paper":"/paper/zephyr-direct-distillation-of-lm-alignment","title":"Zephyr: Direct Distillation of LM Alignment","date":"2023-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"d1e156f54d1adeec","mcp_get_code":{"code_sha256":"d1e156f54d1adeec"}},{"arxiv_id":"2310.02779","paper":"/paper/expected-flow-networks-in-stochastic","title":"Expected flow networks in stochastic environments and two-player zero-sum games","date":"2023-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gfnorg/adversarialflownetworks","path":"src/tb.py","file_url":"https://github.com/gfnorg/adversarialflownetworks/blob/HEAD/src/tb.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9fc358145de34f48","mcp_get_code":{"code_sha256":"9fc358145de34f48"}},{"arxiv_id":"2310.01405","paper":"/paper/representation-engineering-a-top-down","title":"Representation Engineering: A Top-Down Approach to AI Transparency","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"andyzoujm/representation-engineering","path":"lorra_finetune/src/llama2_lorra.py","file_url":"https://github.com/andyzoujm/representation-engineering/blob/HEAD/lorra_finetune/src/llama2_lorra.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"acc281fc1d7b77bc","mcp_get_code":{"code_sha256":"acc281fc1d7b77bc"}},{"arxiv_id":"2309.16298","paper":"/paper/at-which-training-stage-does-cocde-data-help","title":"At Which Training Stage Does Code Data Help LLMs Reasoning?","date":"2023-09-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yingweima2022/codellm","path":"src/generate.py","file_url":"https://github.com/yingweima2022/codellm/blob/HEAD/src/generate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b45cbca36a0a377","mcp_get_code":{"code_sha256":"9b45cbca36a0a377"}},{"arxiv_id":"2309.03409","paper":"/paper/large-language-models-as-optimizers","title":"Large Language Models as Optimizers","date":"2023-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunderous77/glape","path":"utils.py","file_url":"https://github.com/thunderous77/glape/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ab2577b54a5de0f2","mcp_get_code":{"code_sha256":"ab2577b54a5de0f2"}},{"arxiv_id":"2308.10741","paper":"/paper/on-the-adversarial-robustness-of-multi-modal","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","date":"2023-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"75f68885e2ff2684","mcp_get_code":{"code_sha256":"75f68885e2ff2684"}},{"arxiv_id":"2308.08774","paper":"/paper/differential-privacy-linguistic-fairness-and","title":"Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models","date":"2023-08-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xplip/multilingual-lm-objectives","path":"finetuning/pos/tracin_pos.py","file_url":"https://github.com/xplip/multilingual-lm-objectives/blob/HEAD/finetuning/pos/tracin_pos.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"88380f81794a2565","mcp_get_code":{"code_sha256":"88380f81794a2565"}},{"arxiv_id":"2306.08553","paper":"/paper/noise-stability-optimization-for-flat-minima","title":"Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach","date":"2023-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"virtuosoresearch/noise-stability-optimization","path":"exps_on_graph_datasets/compute_noise_stability.py","file_url":"https://github.com/virtuosoresearch/noise-stability-optimization/blob/HEAD/exps_on_graph_datasets/compute_noise_stability.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bf7e2a77d22565f7","mcp_get_code":{"code_sha256":"bf7e2a77d22565f7"}},{"arxiv_id":"2305.17303","paper":"/paper/distilling-blackbox-to-interpretable-models","title":"Distilling BlackBox to Interpretable models for Efficient Transfer Learning","date":"2023-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"batmanlab/miccai-2023-route-interpret-repeat-cxrs","path":"src/codebase/experiments_t_mimic_cxr.py","file_url":"https://github.com/batmanlab/miccai-2023-route-interpret-repeat-cxrs/blob/HEAD/src/codebase/experiments_t_mimic_cxr.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"17952015a6e895eb","mcp_get_code":{"code_sha256":"17952015a6e895eb"}},{"arxiv_id":"2305.13282","paper":"/paper/is-fine-tuning-needed-pre-trained-language","title":"Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection","date":"2023-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Uppaal/lm-ood","path":"model.py","file_url":"https://github.com/Uppaal/lm-ood/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d4befec42a19db00","mcp_get_code":{"code_sha256":"d4befec42a19db00"}},{"arxiv_id":"2305.10722","paper":"/paper/discriminative-diffusion-models-as-few-shot","title":"Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners","date":"2023-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eric-ai-lab/dsd","path":"utils/losses.py","file_url":"https://github.com/eric-ai-lab/dsd/blob/HEAD/utils/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2aa969a20b25a144","mcp_get_code":{"code_sha256":"2aa969a20b25a144"}},{"arxiv_id":"2304.13571","paper":"/paper/quantum-natural-policy-gradients-towards","title":"Quantum Natural Policy Gradients: Towards Sample-Efficient Reinforcement Learning","date":"2023-04-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nicomeyer96/quantum-natural-policy-gradients","path":"utils.py","file_url":"https://github.com/nicomeyer96/quantum-natural-policy-gradients/blob/HEAD/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":"f0603b7cf43f016e","mcp_get_code":{"code_sha256":"f0603b7cf43f016e"}},{"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":"generation_api/loss.py","file_url":"https://github.com/mlii0117/dcl/blob/HEAD/generation_api/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0bc1f8b3524f6b1b","mcp_get_code":{"code_sha256":"0bc1f8b3524f6b1b"}},{"arxiv_id":"2212.02098","paper":"/paper/a-machine-with-short-term-episodic-and","title":"A Machine with Short-Term, Episodic, and Semantic Memory Systems","date":"2022-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"humemai/agent-room-env-v1","path":"agent/dqn/utils.py","file_url":"https://github.com/humemai/agent-room-env-v1/blob/HEAD/agent/dqn/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"16559d8f2cc916ae","mcp_get_code":{"code_sha256":"16559d8f2cc916ae"}},{"arxiv_id":"2210.03150","paper":"/paper/towards-out-of-distribution-adversarial","title":"Towards Out-of-Distribution Adversarial Robustness","date":"2022-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AIproj/Towards-Out-of-Distribution-Adversarial-Robustness","path":"experiments/MNIST/MLP/final/pretrain_MSD/REx_waterfall_lr_init_0.01beta4_early/MNIST_REx_pretrained_MSD.py","file_url":"https://github.com/AIproj/Towards-Out-of-Distribution-Adversarial-Robustness/blob/HEAD/experiments/MNIST/MLP/final/pretrain_MSD/REx_waterfall_lr_init_0.01beta4_early/MNIST_REx_pretrained_MSD.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a99591e938dd780e","mcp_get_code":{"code_sha256":"a99591e938dd780e"}},{"arxiv_id":"2206.14607","paper":"/paper/nerda-con-extending-ner-models-for-continual","title":"NERDA-Con: Extending NER models for Continual Learning -- Integrating Distinct Tasks and Updating Distribution Shifts","date":"2022-06-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"supritivijay/nerda-con","path":"src/NERDA_Con/training.py","file_url":"https://github.com/supritivijay/nerda-con/blob/HEAD/src/NERDA_Con/training.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"193acceb49ed1761","mcp_get_code":{"code_sha256":"193acceb49ed1761"}},{"arxiv_id":"2205.09843","paper":"/paper/table-retrieval-may-not-necessitate-table","title":"Table Retrieval May Not Necessitate Table-specific Model Design","date":"2022-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zorazrw/nqt-retrieval","path":"dpr/models/reader.py","file_url":"https://github.com/zorazrw/nqt-retrieval/blob/HEAD/dpr/models/reader.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1df81ea9d2da7b70","mcp_get_code":{"code_sha256":"1df81ea9d2da7b70"}},{"arxiv_id":"2205.03665","paper":"/paper/variational-sparse-coding-with-learned","title":"Variational Sparse Coding with Learned Thresholding","date":"2022-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kfallah/manifold-contrastive","path":"src/model/manifold/vi_encoder.py","file_url":"https://github.com/kfallah/manifold-contrastive/blob/HEAD/src/model/manifold/vi_encoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"81df6932691462ff","mcp_get_code":{"code_sha256":"81df6932691462ff"}},{"arxiv_id":"2204.09914","paper":"/paper/cpgnet-cascade-point-grid-fusion-network-for","title":"CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation","date":"2022-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huixiancheng/PCB-RandNet","path":"network/loss_func.py","file_url":"https://github.com/huixiancheng/PCB-RandNet/blob/HEAD/network/loss_func.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c6a276314cd17dea","mcp_get_code":{"code_sha256":"c6a276314cd17dea"}},{"arxiv_id":"2203.12979","paper":"/paper/is-geometry-enough-for-matching-in-visual","title":"Is Geometry Enough for Matching in Visual Localization?","date":"2022-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvl-tum/gomatch","path":"gomatch/utils/loss.py","file_url":"https://github.com/dvl-tum/gomatch/blob/HEAD/gomatch/utils/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a051e9c9c8c17f3c","mcp_get_code":{"code_sha256":"a051e9c9c8c17f3c"}},{"arxiv_id":"2112.13734","paper":"/paper/multi-domain-balanced-sampling-improves-out","title":"Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models","date":"2021-12-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"etetteh/ood_gen-chest_xray","path":"chest.py","file_url":"https://github.com/etetteh/ood_gen-chest_xray/blob/HEAD/chest.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5efda4073dec67aa","mcp_get_code":{"code_sha256":"5efda4073dec67aa"}},{"arxiv_id":"2112.13734","paper":"/paper/multi-domain-balanced-sampling-improves-out","title":"Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models","date":"2021-12-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"etetteh/OoD_Gen-Chest_Xray","path":"chest.py","file_url":"https://github.com/etetteh/OoD_Gen-Chest_Xray/blob/HEAD/chest.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9becd36f7438299d","mcp_get_code":{"code_sha256":"9becd36f7438299d"}},{"arxiv_id":"2111.01177","paper":"/paper/don-t-generate-me-training-differentially","title":"Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence","date":"2021-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nv-tlabs/dp-sinkhorn_code","path":"sinkhorn_poisson.py","file_url":"https://github.com/nv-tlabs/dp-sinkhorn_code/blob/HEAD/sinkhorn_poisson.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"521c72871d96e0c1","mcp_get_code":{"code_sha256":"521c72871d96e0c1"}},{"arxiv_id":"2110.15122","paper":"/paper/cafe-catastrophic-data-leakage-in-vertical","title":"CAFE: Catastrophic Data Leakage in Vertical Federated Learning","date":"2021-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"derafael/cafe","path":"utils.py","file_url":"https://github.com/derafael/cafe/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7f22ab2c8e8dccd","mcp_get_code":{"code_sha256":"a7f22ab2c8e8dccd"}},{"arxiv_id":"2110.14118","paper":"/paper/object-aware-regularization-for-addressing","title":"Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning","date":"2021-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alinlab/oreo","path":"atari_beta_vae.py","file_url":"https://github.com/alinlab/oreo/blob/HEAD/atari_beta_vae.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"234d80e79472bd96","mcp_get_code":{"code_sha256":"234d80e79472bd96"}},{"arxiv_id":"2110.05789","paper":"/paper/learning-discrete-representations-via-1","title":"Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval","date":"2021-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jingtaozhan/JPQ","path":"jpq/run_train.py","file_url":"https://github.com/jingtaozhan/JPQ/blob/HEAD/jpq/run_train.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b2c86c4e199eeb01","mcp_get_code":{"code_sha256":"b2c86c4e199eeb01"}},{"arxiv_id":"2110.03611","paper":"/paper/adversarial-retriever-ranker-for-dense-text","title":"Adversarial Retriever-Ranker for dense text retrieval","date":"2021-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/AR2","path":"AR2/model/models.py","file_url":"https://github.com/microsoft/AR2/blob/HEAD/AR2/model/models.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1df81ea9d2da7b70","mcp_get_code":{"code_sha256":"1df81ea9d2da7b70"}},{"arxiv_id":"2109.04014","paper":"/paper/weakly-supervised-visual-retriever-reader-for","title":"Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering","date":"2021-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"1df81ea9d2da7b70","mcp_get_code":{"code_sha256":"1df81ea9d2da7b70"}},{"arxiv_id":"2108.07386","paper":"/paper/bobcat-bilevel-optimization-based","title":"BOBCAT: Bilevel Optimization-Based Computerized Adaptive Testing","date":"2021-08-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arghosh/bobcat","path":"model.py","file_url":"https://github.com/arghosh/bobcat/blob/HEAD/model.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ddaa3dd8a024013d","mcp_get_code":{"code_sha256":"ddaa3dd8a024013d"}},{"arxiv_id":"2106.15962","paper":"/paper/on-the-generative-utility-of-cyclic","title":"On the Generative Utility of Cyclic Conditionals","date":"2021-06-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"changliu00/cygen","path":"main_image.py","file_url":"https://github.com/changliu00/cygen/blob/HEAD/main_image.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bca7eb82cff3d2d","mcp_get_code":{"code_sha256":"3bca7eb82cff3d2d"}},{"arxiv_id":"2106.14103","paper":"/paper/phycrnet-physics-informed-convolutional","title":"PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs","date":"2021-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"isds-neu/PhyCRNet","path":"Codes/PhyCRNet_burgers.py","file_url":"https://github.com/isds-neu/PhyCRNet/blob/HEAD/Codes/PhyCRNet_burgers.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39ed029c556af56b","mcp_get_code":{"code_sha256":"39ed029c556af56b"}},{"arxiv_id":"2106.10905","paper":"/paper/bayesian-inference-of-odes-with-gaussian","title":"Variational multiple shooting for Bayesian ODEs with Gaussian processes","date":"2021-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hegdepashupati/gaussian-process-odes","path":"src/gpode/model_builder.py","file_url":"https://github.com/hegdepashupati/gaussian-process-odes/blob/HEAD/src/gpode/model_builder.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f646ae6ea7ba1ae0","mcp_get_code":{"code_sha256":"f646ae6ea7ba1ae0"}},{"arxiv_id":"2106.06135","paper":"/paper/douzero-mastering-doudizhu-with-self-play","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","date":"2021-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Liberations/DouZero_For_HLDDZ_FullAuto","path":"douzero/dmc/dmc.py","file_url":"https://github.com/Liberations/DouZero_For_HLDDZ_FullAuto/blob/HEAD/douzero/dmc/dmc.py","status":"unverified","verification_level":0,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7a21191505af1ea4","mcp_get_code":{"code_sha256":"7a21191505af1ea4"}},{"arxiv_id":"2106.02225","paper":"/paper/materials-representation-and-transfer","title":"Materials Representation and Transfer Learning for Multi-Property Prediction","date":"2021-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gomes-lab/H-CLMP","path":"HCLMP/HCLMP.py","file_url":"https://github.com/gomes-lab/H-CLMP/blob/HEAD/HCLMP/HCLMP.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3bd2c9e276e69964","mcp_get_code":{"code_sha256":"3bd2c9e276e69964"}},{"arxiv_id":"2103.12171","paper":"/paper/adversarial-feature-augmentation-and","title":"Adversarial Feature Augmentation and Normalization for Visual Recognition","date":"2021-03-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VITA-Group/CV_A-FAN","path":"Detection/attack_algo.py","file_url":"https://github.com/VITA-Group/CV_A-FAN/blob/HEAD/Detection/attack_algo.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"435fe2f837c1215a","mcp_get_code":{"code_sha256":"435fe2f837c1215a"}},{"arxiv_id":"2101.00828","paper":"/paper/transformer-based-conditional-variational","title":"Transformer-based Conditional Variational Autoencoder for Controllable Story Generation","date":"2021-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fangleai/TransformerCVAE","path":"eval_ppl.py","file_url":"https://github.com/fangleai/TransformerCVAE/blob/HEAD/eval_ppl.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a0d28893b7a128bf","mcp_get_code":{"code_sha256":"a0d28893b7a128bf"}},{"arxiv_id":"2007.06889","paper":"/paper/knowledge-distillation-for-multi-task","title":"Knowledge Distillation for Multi-task Learning","date":"2020-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"9d99831edbfb2a6d","mcp_get_code":{"code_sha256":"9d99831edbfb2a6d"}},{"arxiv_id":"2007.06889","paper":"/paper/knowledge-distillation-for-multi-task","title":"Knowledge Distillation for Multi-task Learning","date":"2020-07-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"05f4ecd442041e15","mcp_get_code":{"code_sha256":"05f4ecd442041e15"}},{"arxiv_id":"2006.04727","paper":"/paper/theoretical-guarantees-for-learning","title":"Neural Jump Ordinary Differential Equations: Consistent Continuous-Time Prediction and Filtering","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HerreraKrachTeichmann/ControlledODERNN","path":"NJODE/models.py","file_url":"https://github.com/HerreraKrachTeichmann/ControlledODERNN/blob/HEAD/NJODE/models.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"12d22dac3d5ee45c","mcp_get_code":{"code_sha256":"12d22dac3d5ee45c"}},{"arxiv_id":"2006.00104","paper":"/paper/ot-flow-fast-and-accurate-continuous","title":"OT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transport","date":"2020-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"emorymlip/cot-flow","path":"evaluateTabularOTflowCond.py","file_url":"https://github.com/emorymlip/cot-flow/blob/HEAD/evaluateTabularOTflowCond.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9c917e40239330dc","mcp_get_code":{"code_sha256":"9c917e40239330dc"}},{"arxiv_id":"2006.00104","paper":"/paper/ot-flow-fast-and-accurate-continuous","title":"OT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transport","date":"2020-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EmoryMLIP/OT-Flow","path":"trainToyOTflow.py","file_url":"https://github.com/EmoryMLIP/OT-Flow/blob/HEAD/trainToyOTflow.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fa06178561e307d5","mcp_get_code":{"code_sha256":"fa06178561e307d5"}},{"arxiv_id":"2004.10078","paper":"/paper/amp-net-denoising-based-deep-unfolding-for","title":"AMP-Net: Denoising based Deep Unfolding for Compressive Image Sensing","date":"2020-04-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhonghaoZ/AMP-Net_TIP","path":"train_AMP_Net.py","file_url":"https://github.com/ZhonghaoZ/AMP-Net_TIP/blob/HEAD/train_AMP_Net.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"018f6875145e6221","mcp_get_code":{"code_sha256":"018f6875145e6221"}},{"arxiv_id":"2004.03080","paper":"/paper/end-to-end-pseudo-lidar-for-image-based-3d","title":"End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection","date":"2020-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mileyan/pseudo-LiDAR_e2e","path":"PIXOR/train_pixor_e2e.py","file_url":"https://github.com/mileyan/pseudo-LiDAR_e2e/blob/HEAD/PIXOR/train_pixor_e2e.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0cdfd9167825b209","mcp_get_code":{"code_sha256":"0cdfd9167825b209"}},{"arxiv_id":"1911.11236","paper":"/paper/191111236","title":"RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds","date":"2019-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tsunghan-mama/RandLA-Net-pytorch","path":"network/loss_func.py","file_url":"https://github.com/tsunghan-mama/RandLA-Net-pytorch/blob/HEAD/network/loss_func.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"53945af353c77c7d","mcp_get_code":{"code_sha256":"53945af353c77c7d"}},{"arxiv_id":"1910.00359","paper":"/paper/truth-or-backpropaganda-an-empirical-1","title":"Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory","date":"2019-10-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"goldblum/TruthOrBackpropaganda","path":"NTK_and_local_optima/dl_myths/routines/training.py","file_url":"https://github.com/goldblum/TruthOrBackpropaganda/blob/HEAD/NTK_and_local_optima/dl_myths/routines/training.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a5f86dc6f88e40d","mcp_get_code":{"code_sha256":"0a5f86dc6f88e40d"}},{"arxiv_id":"1909.05378","paper":"/paper/cosql-a-conversational-text-to-sql-challenge","title":"CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases","date":"2019-09-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amolk/editsql","path":"model/torch_utils.py","file_url":"https://github.com/amolk/editsql/blob/HEAD/model/torch_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7e2d038f758acc4a","mcp_get_code":{"code_sha256":"7e2d038f758acc4a"}},{"arxiv_id":"1905.06933","paper":"/paper/dynamically-fused-graph-network-for-multi-hop","title":"Dynamically Fused Graph Network for Multi-hop Reasoning","date":"2019-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"woshiyyya/DFGN-pytorch","path":"DFGN/predict.py","file_url":"https://github.com/woshiyyya/DFGN-pytorch/blob/HEAD/DFGN/predict.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"32954af8794c1637","mcp_get_code":{"code_sha256":"32954af8794c1637"}},{"arxiv_id":"1904.02113","paper":"/paper/point-cloud-oversegmentation-with-graph","title":"Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning","date":"2019-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"loicland/superpoint_graph","path":"supervized_partition/losses.py","file_url":"https://github.com/loicland/superpoint_graph/blob/HEAD/supervized_partition/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"851ed5d8a57bf8c7","mcp_get_code":{"code_sha256":"851ed5d8a57bf8c7"}},{"arxiv_id":"1902.06326","paper":"/paper/pixor-real-time-3d-object-detection-from","title":"PIXOR: Real-time 3D Object Detection from Point Clouds","date":"2019-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"0cdfd9167825b209","mcp_get_code":{"code_sha256":"0cdfd9167825b209"}},{"arxiv_id":"1807.09856","paper":"/paper/where-are-the-blobs-counting-by-localization","title":"Where are the Blobs: Counting by Localization with Point Supervision","date":"2018-07-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ElementAI/LCFCN","path":"lcfcn/lcfcn_loss.py","file_url":"https://github.com/ElementAI/LCFCN/blob/HEAD/lcfcn/lcfcn_loss.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":"2da876cd325bf204","mcp_get_code":{"code_sha256":"2da876cd325bf204"}},{"arxiv_id":"1806.03185","paper":"/paper/wave-u-net-a-multi-scale-neural-network-for","title":"Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation","date":"2018-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"f90/Wave-U-Net-Pytorch","path":"model/utils.py","file_url":"https://github.com/f90/Wave-U-Net-Pytorch/blob/HEAD/model/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"950864364ec0b8d2","mcp_get_code":{"code_sha256":"950864364ec0b8d2"}},{"arxiv_id":"1803.10704","paper":"/paper/end-to-end-multi-task-learning-with-attention","title":"End-to-End Multi-Task Learning with Attention","date":"2018-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akarimoon/xtask_mt","path":"main_cross_cs.py","file_url":"https://github.com/akarimoon/xtask_mt/blob/HEAD/main_cross_cs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9d99831edbfb2a6d","mcp_get_code":{"code_sha256":"9d99831edbfb2a6d"}},{"arxiv_id":"1803.10704","paper":"/paper/end-to-end-multi-task-learning-with-attention","title":"End-to-End Multi-Task Learning with Attention","date":"2018-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akarimoon/xtask_mt","path":"main_cross_nyu.py","file_url":"https://github.com/akarimoon/xtask_mt/blob/HEAD/main_cross_nyu.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"05f4ecd442041e15","mcp_get_code":{"code_sha256":"05f4ecd442041e15"}},{"arxiv_id":"1803.02999","paper":"/paper/on-first-order-meta-learning-algorithms","title":"On First-Order Meta-Learning Algorithms","date":"2018-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hfahrudin/reptile_implement_tf2","path":"Reptile.py","file_url":"https://github.com/hfahrudin/reptile_implement_tf2/blob/HEAD/Reptile.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ac866a5f88b92797","mcp_get_code":{"code_sha256":"ac866a5f88b92797"}},{"arxiv_id":"1605.09304","paper":"/paper/synthesizing-the-preferred-inputs-for-neurons","title":"Synthesizing the preferred inputs for neurons in neural networks via deep generator networks","date":"2016-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ndey96/deep-generator-network","path":"loss_stub.py","file_url":"https://github.com/ndey96/deep-generator-network/blob/HEAD/loss_stub.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b0e6e987c2ef0cfb","mcp_get_code":{"code_sha256":"b0e6e987c2ef0cfb"}},{"arxiv_id":"1509.06461","paper":"/paper/deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"near32/regym","path":"regym/rl_algorithms/algorithms/DQN/ddqn_loss.py","file_url":"https://github.com/near32/regym/blob/HEAD/regym/rl_algorithms/algorithms/DQN/ddqn_loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e04b6449372dffb4","mcp_get_code":{"code_sha256":"e04b6449372dffb4"}},{"arxiv_id":"aaai_25934","paper":null,"title":"arXiv:aaai_25934","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"arghosh/DiFA","path":"src/models/model_utils.py","file_url":"https://github.com/arghosh/DiFA/blob/HEAD/src/models/model_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d05db34e86f0a4d7","mcp_get_code":{"code_sha256":"d05db34e86f0a4d7"}},{"arxiv_id":"Marks_Tree_Skeletonization_from_3D_Point_Clouds_by_Denoising_Diffusion_ICCV_2025_paper","paper":null,"title":"arXiv:Marks_Tree_Skeletonization_from_3D_Point_Clouds_by_Denoising_Diffusion_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"PRBonn/DiffTS","path":"DiffTS/smart_tree/model/loss.py","file_url":"https://github.com/PRBonn/DiffTS/blob/HEAD/DiffTS/smart_tree/model/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4540830efc85c4d0","mcp_get_code":{"code_sha256":"4540830efc85c4d0"}},{"arxiv_id":"2025.findings-emnlp.282","paper":null,"title":"arXiv:2025.findings-emnlp.282","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"AI45Lab/X-Boundary","path":"src/lorra_x_boundary.py","file_url":"https://github.com/AI45Lab/X-Boundary/blob/HEAD/src/lorra_x_boundary.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d11d2248331f1c58","mcp_get_code":{"code_sha256":"d11d2248331f1c58"}},{"arxiv_id":"2024.findings-acl.708","paper":null,"title":"arXiv:2024.findings-acl.708","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"process-cxr/AGR","path":"dpr/models/reader.py","file_url":"https://github.com/process-cxr/AGR/blob/HEAD/dpr/models/reader.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"1df81ea9d2da7b70","mcp_get_code":{"code_sha256":"1df81ea9d2da7b70"}},{"arxiv_id":"2021.acl-long.459","paper":null,"title":"arXiv:2021.acl-long.459","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"cuhksz-nlp/R2GenCMN","path":"modules/loss.py","file_url":"https://github.com/cuhksz-nlp/R2GenCMN/blob/HEAD/modules/loss.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":"0bc1f8b3524f6b1b","mcp_get_code":{"code_sha256":"0bc1f8b3524f6b1b"}}]}