{"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/no-grad-trunc-normal","entry":"_no_grad_trunc_normal_","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":16,"n_papers_ran":16,"n_papers_ran_no_instrument_failure":0,"n_papers_ran_instrument_only":16,"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":16,"n_samples_ran":16,"n_samples_constructed":0,"n_samples_ran_checked":0,"n_samples_instrument":16,"n_samples_unverified":0,"n_samples_fingerprinted":0,"n_places":16,"n_places_pointer_only":6,"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":2,"ran_fixture":14,"ran":0,"unverified":0},"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":"2602.02603","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2602-02603","title":"EchoJEPA: A Latent Predictive Foundation Model for Echocardiography","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"bowang-lab/EchoJEPA","path":"src/models/predictor.py","file_url":"https://github.com/bowang-lab/EchoJEPA/blob/HEAD/src/models/predictor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e7c3b600144accb0","code_sha256_prefix":"e7c3b600144accb0","mcp_get_code":{"code_sha256":"e7c3b600144accb0"}},{"arxiv_id":"2601.17883","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2601-17883","title":"EEG-FM-Compass: Progress, Benchmarking, and Future Directions for EEG Foundation Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Dingkun0817/EEG-FM-Benchmark","path":"models/FM/EEGPT/Model_EEGPT.py","file_url":"https://github.com/Dingkun0817/EEG-FM-Benchmark/blob/HEAD/models/FM/EEGPT/Model_EEGPT.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"307242ac3279e182","code_sha256_prefix":"307242ac3279e182","mcp_get_code":{"code_sha256":"307242ac3279e182"}},{"arxiv_id":"2506.03110","arxiv_id_is_arxiv":true,"paper":null,"title":"arXiv:2506.03110","date":null,"month_inferred_from_arxiv_id":"2025-06","title_source":null,"repo":"shuaiyi308/ReCIT","path":"methods/visiontransformer.py","file_url":"https://github.com/shuaiyi308/ReCIT/blob/HEAD/methods/visiontransformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, shuaiyi308/ReCIT when it was checked","code_sha256":"32d549c7c63738c0","code_sha256_prefix":"32d549c7c63738c0","mcp_get_code":{"code_sha256":"32d549c7c63738c0"}},{"arxiv_id":"2506.00129","arxiv_id_is_arxiv":true,"paper":"/paper/geo-sign-hyperbolic-contrastive-1","title":"Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation","date":"2025-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ed-fish/Geo-Sign","path":"models.py","file_url":"https://github.com/ed-fish/Geo-Sign/blob/HEAD/models.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","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, ed-fish/Geo-Sign when it was checked","code_sha256":"3f7062bb9233a958","code_sha256_prefix":"3f7062bb9233a958","mcp_get_code":{"code_sha256":"3f7062bb9233a958"}},{"arxiv_id":"2410.09633","arxiv_id_is_arxiv":true,"paper":"/paper/duodiff-accelerating-diffusion-models-with-a","title":"DuoDiff: Accelerating Diffusion Models with a Dual-Backbone Approach","date":"2024-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"razvanmatisan/duodiff","path":"models/early_exit.py","file_url":"https://github.com/razvanmatisan/duodiff/blob/HEAD/models/early_exit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","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, razvanmatisan/duodiff when it was checked","code_sha256":"a682db89c810ed54","code_sha256_prefix":"a682db89c810ed54","mcp_get_code":{"code_sha256":"a682db89c810ed54"}},{"arxiv_id":"2406.07966","arxiv_id_is_arxiv":true,"paper":"/paper/real-world-image-dehazing-with-coherence","title":"Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cnyvfang/corun-colabator","path":"corun_colabator/archs/corun_arch.py","file_url":"https://github.com/cnyvfang/corun-colabator/blob/HEAD/corun_colabator/archs/corun_arch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","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, cnyvfang/corun-colabator when it was checked","code_sha256":"7eb8f921afc80af3","code_sha256_prefix":"7eb8f921afc80af3","mcp_get_code":{"code_sha256":"7eb8f921afc80af3"}},{"arxiv_id":"2405.16419","arxiv_id_is_arxiv":true,"paper":"/paper/enhancing-feature-diversity-boosts-channel","title":"Enhancing Feature Diversity Boosts Channel-Adaptive Vision Transformers","date":"2024-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chaudatascience/diverse_channel_vit","path":"models/dichavit.py","file_url":"https://github.com/chaudatascience/diverse_channel_vit/blob/HEAD/models/dichavit.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"d05e018c317ed42b","code_sha256_prefix":"d05e018c317ed42b","mcp_get_code":{"code_sha256":"d05e018c317ed42b"}},{"arxiv_id":"2308.10814","arxiv_id_is_arxiv":true,"paper":"/paper/jumping-through-local-minima-quantization-in","title":"Jumping through Local Minima: Quantization in the Loss Landscape of Vision Transformers","date":"2023-08-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"enyac-group/evol-q","path":"joint_evol_opt.py","file_url":"https://github.com/enyac-group/evol-q/blob/HEAD/joint_evol_opt.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"ed7e8d54fc7c6786","code_sha256_prefix":"ed7e8d54fc7c6786","mcp_get_code":{"code_sha256":"ed7e8d54fc7c6786"}},{"arxiv_id":"2308.09951","arxiv_id_is_arxiv":true,"paper":"/paper/semantics-meets-temporal-correspondence-self","title":"Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos","date":"2023-08-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shvdiwnkozbw/SMTC","path":"src/model/model_action.py","file_url":"https://github.com/shvdiwnkozbw/SMTC/blob/HEAD/src/model/model_action.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","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, shvdiwnkozbw/SMTC when it was checked","code_sha256":"cffc671a6c09decc","code_sha256_prefix":"cffc671a6c09decc","mcp_get_code":{"code_sha256":"cffc671a6c09decc"}},{"arxiv_id":"2308.03322","arxiv_id_is_arxiv":true,"paper":"/paper/part-aware-transformer-for-generalizable","title":"Part-Aware Transformer for Generalizable Person Re-identification","date":"2023-08-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liyuke65535/part-aware-transformer","path":"model/backbones/vit_pytorch.py","file_url":"https://github.com/liyuke65535/part-aware-transformer/blob/HEAD/model/backbones/vit_pytorch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","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, liyuke65535/part-aware-transformer when it was checked","code_sha256":"9143fd74c66cf68d","code_sha256_prefix":"9143fd74c66cf68d","mcp_get_code":{"code_sha256":"9143fd74c66cf68d"}},{"arxiv_id":"2204.07683","arxiv_id_is_arxiv":true,"paper":"/paper/safe-self-refinement-for-transformer-based","title":"Safe Self-Refinement for Transformer-based Domain Adaptation","date":"2022-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tsun/SSRT","path":"model/SSRT.py","file_url":"https://github.com/tsun/SSRT/blob/HEAD/model/SSRT.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"fa2dd3be10cf9804","code_sha256_prefix":"fa2dd3be10cf9804","mcp_get_code":{"code_sha256":"fa2dd3be10cf9804"}},{"arxiv_id":"2201.04676","arxiv_id_is_arxiv":true,"paper":"/paper/uniformer-unified-transformer-for-efficient-1","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","date":"2022-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"towhee-io/towhee","path":"towhee/models/uniformer/uniformer.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/uniformer/uniformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"607038475fdc388b","code_sha256_prefix":"607038475fdc388b","mcp_get_code":{"code_sha256":"607038475fdc388b"}},{"arxiv_id":"2108.10257","arxiv_id_is_arxiv":true,"paper":"/paper/swinir-image-restoration-using-swin","title":"SwinIR: Image Restoration Using Swin Transformer","date":"2021-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"XPixelGroup/BasicSR","path":"basicsr/archs/swinir_arch.py","file_url":"https://github.com/XPixelGroup/BasicSR/blob/HEAD/basicsr/archs/swinir_arch.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"c30c007e9c6365e0","code_sha256_prefix":"c30c007e9c6365e0","mcp_get_code":{"code_sha256":"c30c007e9c6365e0"}},{"arxiv_id":"2105.14432","arxiv_id_is_arxiv":true,"paper":"/paper/transformer-based-deep-image-matching-for","title":"TransMatcher: Deep Image Matching Through Transformers for Generalizable Person Re-identification","date":"2021-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JDAI-CV/fast-reid","path":"fastreid/modeling/backbones/vision_transformer.py","file_url":"https://github.com/JDAI-CV/fast-reid/blob/HEAD/fastreid/modeling/backbones/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"813ed3a96c17cf42","code_sha256_prefix":"813ed3a96c17cf42","mcp_get_code":{"code_sha256":"813ed3a96c17cf42"}},{"arxiv_id":"2103.14030","arxiv_id_is_arxiv":true,"paper":"/paper/swin-transformer-hierarchical-vision","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","date":"2021-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"towhee-io/towhee","path":"towhee/models/swin_transformer/model.py","file_url":"https://github.com/towhee-io/towhee/blob/HEAD/towhee/models/swin_transformer/model.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"730a23e2dd3abea0","code_sha256_prefix":"730a23e2dd3abea0","mcp_get_code":{"code_sha256":"730a23e2dd3abea0"}},{"arxiv_id":"2012.12877","arxiv_id_is_arxiv":true,"paper":"/paper/training-data-efficient-image-transformers","title":"Training data-efficient image transformers & distillation through attention","date":"2020-12-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba/EasyCV","path":"easycv/models/backbones/vision_transformer.py","file_url":"https://github.com/alibaba/EasyCV/blob/HEAD/easycv/models/backbones/vision_transformer.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"5bcbd988b672cf32","code_sha256_prefix":"5bcbd988b672cf32","mcp_get_code":{"code_sha256":"5bcbd988b672cf32"}}],"record_sha256":"3b518220f8950278dbd15548eb76ad5b850498556ae48a9a80c5401725773099","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}