{"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/total-variation-loss","entry":"total_variation_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":18,"n_papers_ran":15,"n_papers_ran_no_instrument_failure":7,"n_papers_ran_instrument_only":8,"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":13,"n_samples_ran":10,"n_samples_constructed":0,"n_samples_ran_checked":7,"n_samples_instrument":3,"n_samples_unverified":3,"n_samples_fingerprinted":8,"n_places":19,"n_places_pointer_only":3,"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":1,"ran_violates":1,"ran_draft_wrong":1,"ran_fixture":2,"ran":5,"unverified":3},"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":"2606.31394","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2606-31394","title":"Resolving superposition in AI for interpretability and cross-modal alignment in patient-neuronal images","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"jijihihi/Bio_superposition","path":"concept_visulaize/activation_maximization.py","file_url":"https://github.com/jijihihi/Bio_superposition/blob/HEAD/concept_visulaize/activation_maximization.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","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, jijihihi/Bio_superposition when it was checked","code_sha256":"fd3eaca41be1f166","code_sha256_prefix":"fd3eaca41be1f166","mcp_get_code":{"code_sha256":"fd3eaca41be1f166"}},{"arxiv_id":"2602.03555","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-03555","title":"Cut to the Mix: Simple Data Augmentation Outperforms Elaborate Ones in Limited Organ Segmentation Datasets","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"Rebooorn/mosDAtoolkit","path":"inpaint/loss.py","file_url":"https://github.com/Rebooorn/mosDAtoolkit/blob/HEAD/inpaint/loss.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"dedfa1b69056bdc7","code_sha256_prefix":"dedfa1b69056bdc7","mcp_get_code":{"code_sha256":"dedfa1b69056bdc7"}},{"arxiv_id":"2506.05280","arxiv_id_is_arxiv":true,"paper":"/paper/unifying-appearance-codes-and-bilateral-grids","title":"Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting","date":"2025-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bigcileng/bilateral-driving","path":"project/models/modules.py","file_url":"https://github.com/bigcileng/bilateral-driving/blob/HEAD/project/models/modules.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"033dcc84593cabda","code_sha256_prefix":"033dcc84593cabda","mcp_get_code":{"code_sha256":"033dcc84593cabda"}},{"arxiv_id":"2505.05528","arxiv_id_is_arxiv":true,"paper":"/paper/x-transfer-attacks-towards-super-transferable","title":"X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP","date":"2025-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hanxunh/xtransferbench","path":"xtransfer/attacks/attack_generation.py","file_url":"https://github.com/hanxunh/xtransferbench/blob/HEAD/xtransfer/attacks/attack_generation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"d85c705653a8ceef","code_sha256_prefix":"d85c705653a8ceef","mcp_get_code":{"code_sha256":"d85c705653a8ceef"}},{"arxiv_id":"2502.01385","arxiv_id_is_arxiv":true,"paper":"/paper/detecting-backdoor-samples-in-contrastive","title":"Detecting Backdoor Samples in Contrastive Language Image Pretraining","date":"2025-02-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HanxunH/Detect-CLIP-Backdoor-Samples","path":"backdoor_sample_detector/cognitive_distillation.py","file_url":"https://github.com/HanxunH/Detect-CLIP-Backdoor-Samples/blob/HEAD/backdoor_sample_detector/cognitive_distillation.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"d85c705653a8ceef","code_sha256_prefix":"d85c705653a8ceef","mcp_get_code":{"code_sha256":"d85c705653a8ceef"}},{"arxiv_id":"2311.17910","arxiv_id_is_arxiv":true,"paper":"/paper/hugs-human-gaussian-splats","title":"HUGS: Human Gaussian Splats","date":"2023-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-hugs","path":"hugs/losses/utils.py","file_url":"https://github.com/apple/ml-hugs/blob/HEAD/hugs/losses/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, apple/ml-hugs (NOASSERTION)","code_sha256":"bcb05d8eb3e8a3e4","code_sha256_prefix":"bcb05d8eb3e8a3e4","mcp_get_code":{"code_sha256":"bcb05d8eb3e8a3e4"}},{"arxiv_id":"2302.08560","arxiv_id_is_arxiv":true,"paper":"/paper/imitation-from-arbitrary-experience-a-dual","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","date":"2023-02-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hari-sikchi/DVL","path":"offline/critic.py","file_url":"https://github.com/hari-sikchi/DVL/blob/HEAD/offline/critic.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","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, hari-sikchi/DVL when it was checked","code_sha256":"d773884e980e01c5","code_sha256_prefix":"d773884e980e01c5","mcp_get_code":{"code_sha256":"d773884e980e01c5"}},{"arxiv_id":"2109.07070","arxiv_id_is_arxiv":true,"paper":"/paper/inpainting-hydrodynamical-maps-with-deep","title":"Inpainting hydrodynamical maps with deep learning","date":null,"month_inferred_from_arxiv_id":"2021-09","title_source":"archive","repo":"fgmohammad/inpainting","path":"loss.py","file_url":"https://github.com/fgmohammad/inpainting/blob/HEAD/loss.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"dedfa1b69056bdc7","code_sha256_prefix":"dedfa1b69056bdc7","mcp_get_code":{"code_sha256":"dedfa1b69056bdc7"}},{"arxiv_id":"2104.11493","arxiv_id_is_arxiv":true,"paper":"/paper/stroke-based-scene-text-erasing-using","title":"Stroke-Based Scene Text Erasing Using Synthetic Data for Training","date":"2021-04-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tzm-tora/Stroke-Based-Scene-Text-Erasing","path":"src/loss.py","file_url":"https://github.com/tzm-tora/Stroke-Based-Scene-Text-Erasing/blob/HEAD/src/loss.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":"773d08e4e53da7a2","code_sha256_prefix":"773d08e4e53da7a2","mcp_get_code":{"code_sha256":"773d08e4e53da7a2"}},{"arxiv_id":"2103.17185","arxiv_id_is_arxiv":true,"paper":"/paper/rethinking-style-transfer-from-pixels-to","title":"Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes","date":"2021-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CompVis/brushstroke-parameterized-style-transfer","path":"model.py","file_url":"https://github.com/CompVis/brushstroke-parameterized-style-transfer/blob/HEAD/model.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":"0ff29180d1bf839d","code_sha256_prefix":"0ff29180d1bf839d","mcp_get_code":{"code_sha256":"0ff29180d1bf839d"}},{"arxiv_id":"2010.09750","arxiv_id_is_arxiv":true,"paper":"/paper/investigating-and-simplifying-masking-based-1","title":"Investigating and Simplifying Masking-based Saliency Methods for Model Interpretability","date":"2020-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zphang/saliency_investigation","path":"casme/ext/pytorch_inpainting_with_partial_conv.py","file_url":"https://github.com/zphang/saliency_investigation/blob/HEAD/casme/ext/pytorch_inpainting_with_partial_conv.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"dedfa1b69056bdc7","code_sha256_prefix":"dedfa1b69056bdc7","mcp_get_code":{"code_sha256":"dedfa1b69056bdc7"}},{"arxiv_id":"2009.08679","arxiv_id_is_arxiv":true,"paper":"/paper/face-sketch-synthesis-with-style-transfer","title":"Face Sketch Synthesis with Style Transfer using Pyramid Column Feature","date":"2020-09-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chaofengc/Face-Sketch","path":"utils/loss.py","file_url":"https://github.com/chaofengc/Face-Sketch/blob/HEAD/utils/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":"99b5ef9a37a89e47","code_sha256_prefix":"99b5ef9a37a89e47","mcp_get_code":{"code_sha256":"99b5ef9a37a89e47"}},{"arxiv_id":"2004.02788","arxiv_id_is_arxiv":true,"paper":"/paper/self-supervised-scene-de-occlusion","title":"Self-Supervised Scene De-occlusion","date":"2020-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ducminhkhoi/Amodal-Instance-Seg-ASBU","path":"models/losses.py","file_url":"https://github.com/ducminhkhoi/Amodal-Instance-Seg-ASBU/blob/HEAD/models/losses.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"dedfa1b69056bdc7","code_sha256_prefix":"dedfa1b69056bdc7","mcp_get_code":{"code_sha256":"dedfa1b69056bdc7"}},{"arxiv_id":"1804.07723","arxiv_id_is_arxiv":true,"paper":"/paper/image-inpainting-for-irregular-holes-using","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","date":"2018-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naoto0804/pytorch-inpainting-with-partial-conv","path":"loss.py","file_url":"https://github.com/naoto0804/pytorch-inpainting-with-partial-conv/blob/HEAD/loss.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"dedfa1b69056bdc7","code_sha256_prefix":"dedfa1b69056bdc7","mcp_get_code":{"code_sha256":"dedfa1b69056bdc7"}},{"arxiv_id":"1804.07723","arxiv_id_is_arxiv":true,"paper":"/paper/image-inpainting-for-irregular-holes-using","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","date":"2018-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yashk2000/SneakySketchers","path":"inpainting/loss.py","file_url":"https://github.com/yashk2000/SneakySketchers/blob/HEAD/inpainting/loss.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"48322e1ae6659815","code_sha256_prefix":"48322e1ae6659815","mcp_get_code":{"code_sha256":"48322e1ae6659815"}},{"arxiv_id":"1611.07004","arxiv_id_is_arxiv":true,"paper":"/paper/image-to-image-translation-with-conditional","title":"Image-to-Image Translation with Conditional Adversarial Networks","date":"2016-11-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Vious/LBAM_Pytorch","path":"loss/InpaintingLoss.py","file_url":"https://github.com/Vious/LBAM_Pytorch/blob/HEAD/loss/InpaintingLoss.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"dedfa1b69056bdc7","code_sha256_prefix":"dedfa1b69056bdc7","mcp_get_code":{"code_sha256":"dedfa1b69056bdc7"}},{"arxiv_id":"1601.04589","arxiv_id_is_arxiv":true,"paper":"/paper/combining-markov-random-fields-and","title":"Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis","date":"2016-01-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"awentzonline/image-analogies","path":"image_analogy/losses/core.py","file_url":"https://github.com/awentzonline/image-analogies/blob/HEAD/image_analogy/losses/core.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":"b2cde6a85dd994ae","code_sha256_prefix":"b2cde6a85dd994ae","mcp_get_code":{"code_sha256":"b2cde6a85dd994ae"}},{"arxiv_id":"ijcai2025_1122","arxiv_id_is_arxiv":false,"paper":null,"title":"IJCAI id ijcai2025_1122","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"mao-code/SmartSpatial","path":"SmartSpatial/utils.py","file_url":"https://github.com/mao-code/SmartSpatial/blob/HEAD/SmartSpatial/utils.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":"f737100570e9be4b","code_sha256_prefix":"f737100570e9be4b","mcp_get_code":{"code_sha256":"f737100570e9be4b"}},{"arxiv_id":"Schelling_RADU_Ray-Aligned_Depth_Update_Convolutions_for_ToF_Data_Denoising_CVPR_2022_paper","arxiv_id_is_arxiv":false,"paper":null,"title":"CVF open access id Schelling_RADU_Ray-Aligned_Depth_Update_Convolutions_for_ToF_Data_Denoising_CVPR_2022_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"schellmi42/RADU","path":"code_dl/training_utils.py","file_url":"https://github.com/schellmi42/RADU/blob/HEAD/code_dl/training_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"21a84c001a47a2a7","code_sha256_prefix":"21a84c001a47a2a7","mcp_get_code":{"code_sha256":"21a84c001a47a2a7"}}],"record_sha256":"a806138f81ab61a812135a07d0e4daa2e2bc320df6773ad0e27873ecac250050","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}