{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/loss-2","entry":"Loss","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+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 = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":19,"n_papers_ran":11,"n_papers_ran_no_instrument_failure":10,"n_papers_ran_instrument_only":1,"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":19,"n_samples_ran":11,"n_samples_constructed":8,"n_samples_ran_checked":10,"n_samples_instrument":1,"n_samples_unverified":8,"n_samples_fingerprinted":3,"n_places":19,"n_places_pointer_only":7,"n_places_pointer_only_link_open":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":10,"unverified":8},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"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":"2608.19735","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2608-19735","title":"RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"SAP-samples/tabular-ai-recpfn","path":"src/architecture/recpfn.py","file_url":"https://github.com/SAP-samples/tabular-ai-recpfn/blob/HEAD/src/architecture/recpfn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"1c50e650efdee51d","code_sha256_prefix":"1c50e650efdee51d","mcp_get_code":{"code_sha256":"1c50e650efdee51d"}},{"arxiv_id":"2605.00195","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2605-00195","title":"Diversity in Large Language Models under Supervised Fine-Tuning","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"rsklypa/TOFU","path":"train/loss_sft.py","file_url":"https://github.com/rsklypa/TOFU/blob/HEAD/train/loss_sft.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, rsklypa/TOFU when it was checked","code_sha256":"6deb6c11dc3cea38","code_sha256_prefix":"6deb6c11dc3cea38","mcp_get_code":{"code_sha256":"6deb6c11dc3cea38"}},{"arxiv_id":"2602.03390","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-03390","title":"From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"hynnsk/SRL","path":"srl/losses.py","file_url":"https://github.com/hynnsk/SRL/blob/HEAD/srl/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"69b03cb1053aa22e","code_sha256_prefix":"69b03cb1053aa22e","mcp_get_code":{"code_sha256":"69b03cb1053aa22e"}},{"arxiv_id":"2602.03039","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-03039","title":"HP-GAN: Harnessing Pretrained Networks for GAN Improvement with FakeTwins and Discriminator Consistency","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"higun2/HP-GAN","path":"training/loss.py","file_url":"https://github.com/higun2/HP-GAN/blob/HEAD/training/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2ad520fab504e31d","code_sha256_prefix":"2ad520fab504e31d","mcp_get_code":{"code_sha256":"2ad520fab504e31d"}},{"arxiv_id":"2505.23363","arxiv_id_is_arxiv":true,"paper":"/paper/discriminative-policy-optimization-for-token","title":"Discriminative Policy Optimization for Token-Level Reward Models","date":"2025-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"homzer/q-rm","path":"src/rewards/strategy.py","file_url":"https://github.com/homzer/q-rm/blob/HEAD/src/rewards/strategy.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, homzer/q-rm when it was checked","code_sha256":"ae4c4703ba50654a","code_sha256_prefix":"ae4c4703ba50654a","mcp_get_code":{"code_sha256":"ae4c4703ba50654a"}},{"arxiv_id":"2505.20853","arxiv_id_is_arxiv":true,"paper":null,"title":"arXiv:2505.20853","date":null,"month_inferred_from_arxiv_id":"2025-05","title_source":null,"repo":"strangeAlan/CoE","path":"Cooperation.py","file_url":"https://github.com/strangeAlan/CoE/blob/HEAD/Cooperation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, strangeAlan/CoE when it was checked","code_sha256":"29605b5553e453a0","code_sha256_prefix":"29605b5553e453a0","mcp_get_code":{"code_sha256":"29605b5553e453a0"}},{"arxiv_id":"2505.17384","arxiv_id_is_arxiv":true,"paper":null,"title":"arXiv:2505.17384","date":null,"month_inferred_from_arxiv_id":"2025-05","title_source":null,"repo":"tyuxie/VADD","path":"diffusion.py","file_url":"https://github.com/tyuxie/VADD/blob/HEAD/diffusion.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0ac157120e5fa303","code_sha256_prefix":"0ac157120e5fa303","mcp_get_code":{"code_sha256":"0ac157120e5fa303"}},{"arxiv_id":"2503.00307","arxiv_id_is_arxiv":true,"paper":"/paper/remasking-discrete-diffusion-models-with","title":"Remasking Discrete Diffusion Models with Inference-Time Scaling","date":"2025-03-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kuleshov-group/remdm","path":"diffusion.py","file_url":"https://github.com/kuleshov-group/remdm/blob/HEAD/diffusion.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f0c0a2810b675abb","code_sha256_prefix":"f0c0a2810b675abb","mcp_get_code":{"code_sha256":"f0c0a2810b675abb"}},{"arxiv_id":"2402.05639","arxiv_id_is_arxiv":true,"paper":"/paper/nonparametric-instrumental-variable-2","title":"Nonparametric Instrumental Variable Regression through Stochastic Approximate Gradients","date":"2024-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"caioflp/sagd-iv","path":"src/models/sagdiv.py","file_url":"https://github.com/caioflp/sagd-iv/blob/HEAD/src/models/sagdiv.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, caioflp/sagd-iv when it was checked","code_sha256":"1ddde67db867d479","code_sha256_prefix":"1ddde67db867d479","mcp_get_code":{"code_sha256":"1ddde67db867d479"}},{"arxiv_id":"2401.16702","arxiv_id_is_arxiv":true,"paper":"/paper/multi-granularity-correspondence-learning-1","title":"Multi-granularity Correspondence Learning from Long-term Noisy Videos","date":"2024-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XLearning-SCU/2024-ICLR-Norton","path":"mmpt/losses/nce.py","file_url":"https://github.com/XLearning-SCU/2024-ICLR-Norton/blob/HEAD/mmpt/losses/nce.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"3c604915121f5194","code_sha256_prefix":"3c604915121f5194","mcp_get_code":{"code_sha256":"3c604915121f5194"}},{"arxiv_id":"2306.04829","arxiv_id_is_arxiv":true,"paper":"/paper/object-centric-learning-for-real-world-videos","title":"Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities","date":"2023-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"martius-lab/videosaur","path":"videosaur/losses.py","file_url":"https://github.com/martius-lab/videosaur/blob/HEAD/videosaur/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e177df2aa610cdc9","code_sha256_prefix":"e177df2aa610cdc9","mcp_get_code":{"code_sha256":"e177df2aa610cdc9"}},{"arxiv_id":"2305.08296","arxiv_id_is_arxiv":true,"paper":"/paper/neural-face-rigging-for-animating-and","title":"Neural Face Rigging for Animating and Retargeting Facial Meshes in the Wild","date":"2023-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dafei-qin/NFR_pytorch","path":"dataset_preprocess.py","file_url":"https://github.com/dafei-qin/NFR_pytorch/blob/HEAD/dataset_preprocess.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"ba53eec4cd8756e5","code_sha256_prefix":"ba53eec4cd8756e5","mcp_get_code":{"code_sha256":"ba53eec4cd8756e5"}},{"arxiv_id":"2304.01662","arxiv_id_is_arxiv":true,"paper":"/paper/cross-domain-image-captioning-with","title":"Cross-Domain Image Captioning with Discriminative Finetuning","date":"2023-04-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/EGG","path":"egg/zoo/emcom_as_ssl/losses.py","file_url":"https://github.com/facebookresearch/EGG/blob/HEAD/egg/zoo/emcom_as_ssl/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"edd2ab1fbde938be","code_sha256_prefix":"edd2ab1fbde938be","mcp_get_code":{"code_sha256":"edd2ab1fbde938be"}},{"arxiv_id":"2203.05272","arxiv_id_is_arxiv":true,"paper":"/paper/contrastive-boundary-learning-for-point-cloud","title":"Contrastive Boundary Learning for Point Cloud Segmentation","date":"2022-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LiyaoTang/contrastBoundary","path":"pytorch/model/pointtransformer_seg.py","file_url":"https://github.com/LiyaoTang/contrastBoundary/blob/HEAD/pytorch/model/pointtransformer_seg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2c72d93f06bf45a3","code_sha256_prefix":"2c72d93f06bf45a3","mcp_get_code":{"code_sha256":"2c72d93f06bf45a3"}},{"arxiv_id":"2201.12558","arxiv_id_is_arxiv":true,"paper":"/paper/the-kfiou-loss-for-rotated-object-detection-1","title":"The KFIoU Loss for Rotated Object Detection","date":"2022-01-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yangxue0827/RotationDetection","path":"alpharotate/libs/models/losses/losses_kfiou.py","file_url":"https://github.com/yangxue0827/RotationDetection/blob/HEAD/alpharotate/libs/models/losses/losses_kfiou.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0699e01c78ee6d82","code_sha256_prefix":"0699e01c78ee6d82","mcp_get_code":{"code_sha256":"0699e01c78ee6d82"}},{"arxiv_id":"2103.14332","arxiv_id_is_arxiv":true,"paper":"/paper/building-reliable-explanations-of-unreliable","title":"Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation","date":"2021-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JBNU-VL/RelEx","path":"models/saliency/optim_methods/relex.py","file_url":"https://github.com/JBNU-VL/RelEx/blob/HEAD/models/saliency/optim_methods/relex.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, JBNU-VL/RelEx when it was checked","code_sha256":"73b2b4d12392b434","code_sha256_prefix":"73b2b4d12392b434","mcp_get_code":{"code_sha256":"73b2b4d12392b434"}},{"arxiv_id":"2101.05068","arxiv_id_is_arxiv":true,"paper":"/paper/probabilistic-embeddings-for-cross-modal","title":"Probabilistic Embeddings for Cross-Modal Retrieval","date":"2021-01-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"VL-Group/2022-NeurIPS-DAA","path":"model.py","file_url":"https://github.com/VL-Group/2022-NeurIPS-DAA/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"bc0cd89064229f55","code_sha256_prefix":"bc0cd89064229f55","mcp_get_code":{"code_sha256":"bc0cd89064229f55"}},{"arxiv_id":"2007.15255","arxiv_id_is_arxiv":true,"paper":"/paper/instance-selection-for-gans","title":"Instance Selection for GANs","date":"2020-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"snap-research/3dgp","path":"src/training/loss.py","file_url":"https://github.com/snap-research/3dgp/blob/HEAD/src/training/loss.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, snap-research/3dgp when it was checked","code_sha256":"cec2fa3cb3bf036c","code_sha256_prefix":"cec2fa3cb3bf036c","mcp_get_code":{"code_sha256":"cec2fa3cb3bf036c"}},{"arxiv_id":"2007.13197","arxiv_id_is_arxiv":true,"paper":"/paper/efficient-generation-of-structured-objects-1","title":"Efficient Generation of Structured Objects with Constrained Adversarial Networks","date":"2020-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"unitn-sml/CAN","path":"src/fuzzy/losses.py","file_url":"https://github.com/unitn-sml/CAN/blob/HEAD/src/fuzzy/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, unitn-sml/CAN when it was checked","code_sha256":"a13b7e1268b3cb8d","code_sha256_prefix":"a13b7e1268b3cb8d","mcp_get_code":{"code_sha256":"a13b7e1268b3cb8d"}}],"record_sha256":"06497a0467a4daf2ae0a00361ceba5a3d75164e70569bf4671c9db6bdc15b9e7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}