{"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/transformerlayer","entry":"TransformerLayer","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":34,"n_papers_ran":19,"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":37,"n_samples_ran":19,"n_samples_fingerprinted":1,"n_places":37,"n_places_pointer_only":18,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":19,"unverified":18},"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":"2607.13103","paper":"/paper/arxiv-2607-13103","title":"Disentangling Knowledge States with Ability and Proficiency Modeling for Knowledge Tracing","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"ThaliaBee/PAKT","path":"models/pakt.py","file_url":"https://github.com/ThaliaBee/PAKT/blob/HEAD/models/pakt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"22828c10500ddd3a","mcp_get_code":{"code_sha256":"22828c10500ddd3a"}},{"arxiv_id":"2606.18672","paper":"/paper/arxiv-2606-18672","title":"scGTN: Deep Siamese Graph Transformer Network for Single-cell RNA Sequencing Clustering","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"W-RMSL/scGTN","path":"model.py","file_url":"https://github.com/W-RMSL/scGTN/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e0c21b6130fa6e7e","mcp_get_code":{"code_sha256":"e0c21b6130fa6e7e"}},{"arxiv_id":"2605.18534","paper":"/paper/arxiv-2605-18534","title":"XCTFormer: Leveraging Cross-Channel and Cross-Time Dependencies for Enhanced Time-Series Analysis","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"azencot-group/XCTFormer","path":"models/XCTFormer.py","file_url":"https://github.com/azencot-group/XCTFormer/blob/HEAD/models/XCTFormer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"53f7ed2675efb82f","mcp_get_code":{"code_sha256":"53f7ed2675efb82f"}},{"arxiv_id":"2603.26515","paper":"/paper/arxiv-2603-26515","title":"JAL-Turn: Joint Acoustic-Linguistic Modeling for Real-Time and Robust Turn-Taking Detection in Full-Duplex Spoken Dialogue Systems","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"inokoj/VAP-Realtime","path":"vap_realtime/model.py","file_url":"https://github.com/inokoj/VAP-Realtime/blob/HEAD/vap_realtime/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9ac8298798c97a60","mcp_get_code":{"code_sha256":"9ac8298798c97a60"}},{"arxiv_id":"2601.12261","paper":"/paper/arxiv-2601-12261","title":"DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"zb12138/DALD_PCAC","path":"DALD_PCAC.py","file_url":"https://github.com/zb12138/DALD_PCAC/blob/HEAD/DALD_PCAC.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6694904c3f3628e6","mcp_get_code":{"code_sha256":"6694904c3f3628e6"}},{"arxiv_id":"2505.13489","paper":"/paper/contrastive-cross-course-knowledge-tracing","title":"Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer","date":"2025-05-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DQYZHWK/TransKT","path":"model/TransKT.py","file_url":"https://github.com/DQYZHWK/TransKT/blob/HEAD/model/TransKT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b1352ba81722cb9","mcp_get_code":{"code_sha256":"4b1352ba81722cb9"}},{"arxiv_id":"2411.12872","paper":"/paper/from-text-to-pose-to-image-improving","title":"From Text to Pose to Image: Improving Diffusion Model Control and Quality","date":"2024-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clement-bonnet/text-to-pose","path":"t2p/model.py","file_url":"https://github.com/clement-bonnet/text-to-pose/blob/HEAD/t2p/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"17aeb94103ec6da9","mcp_get_code":{"code_sha256":"17aeb94103ec6da9"}},{"arxiv_id":"2411.08706","paper":"/paper/searching-latent-program-spaces","title":"Searching Latent Program Spaces","date":"2024-11-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clement-bonnet/lpn","path":"src/models/lpn.py","file_url":"https://github.com/clement-bonnet/lpn/blob/HEAD/src/models/lpn.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":"5bdc653acd891cd4","mcp_get_code":{"code_sha256":"5bdc653acd891cd4"}},{"arxiv_id":"2410.10012","paper":"/paper/naraim-native-aspect-ratio-autoregressive","title":"NARAIM: Native Aspect Ratio Autoregressive Image Models","date":"2024-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"daniel-gallo/naraim","path":"model/pretraining.py","file_url":"https://github.com/daniel-gallo/naraim/blob/HEAD/model/pretraining.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cdf9a7e7270191af","mcp_get_code":{"code_sha256":"cdf9a7e7270191af"}},{"arxiv_id":"2406.10354","paper":"/paper/sigdiffusions-score-based-diffusion-models","title":"SigDiffusions: Score-Based Diffusion Models for Long Time Series via Log-Signature Embeddings","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Barb0ra/SigDiffusions","path":"model.py","file_url":"https://github.com/Barb0ra/SigDiffusions/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9605b4044e0b00ed","mcp_get_code":{"code_sha256":"9605b4044e0b00ed"}},{"arxiv_id":"2405.03943","paper":"/paper/predictive-modeling-with-temporal-graphical","title":"Predictive Modeling with Temporal Graphical Representation on Electronic Health Records","date":"2024-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"The-Real-JerryChen/TRANS","path":"models/Seqmodels.py","file_url":"https://github.com/The-Real-JerryChen/TRANS/blob/HEAD/models/Seqmodels.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c2885bbdafcf8e2b","mcp_get_code":{"code_sha256":"c2885bbdafcf8e2b"}},{"arxiv_id":"2404.04557","paper":"/paper/learning-instance-aware-correspondences-for","title":"Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes","date":"2024-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhiyuanYU134/MIRETR","path":"release/robi/modules.py","file_url":"https://github.com/zhiyuanYU134/MIRETR/blob/HEAD/release/robi/modules.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7cf0e33df6359534","mcp_get_code":{"code_sha256":"7cf0e33df6359534"}},{"arxiv_id":"2401.08567","paper":"/paper/connect-collapse-corrupt-learning-cross-modal","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","date":"2024-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuhui-zh15/c3","path":"image_captioning/src/models/transformer_mapper.py","file_url":"https://github.com/yuhui-zh15/c3/blob/HEAD/image_captioning/src/models/transformer_mapper.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"35a267d7f92c479e","mcp_get_code":{"code_sha256":"35a267d7f92c479e"}},{"arxiv_id":"2308.15512","paper":"/paper/shatter-and-gather-learning-referring-image","title":"Shatter and Gather: Learning Referring Image Segmentation with Text Supervision","date":"2023-08-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kdwonn/SaG","path":"model/cross_modal_attention.py","file_url":"https://github.com/kdwonn/SaG/blob/HEAD/model/cross_modal_attention.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"096e6b33de7b678c","mcp_get_code":{"code_sha256":"096e6b33de7b678c"}},{"arxiv_id":"2307.16525","paper":"/paper/transferable-decoding-with-visual-entities","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","date":"2023-07-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"feielysia/viecap","path":"ClipCap.py","file_url":"https://github.com/feielysia/viecap/blob/HEAD/ClipCap.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6436669ce470a3fd","mcp_get_code":{"code_sha256":"6436669ce470a3fd"}},{"arxiv_id":"2306.13643","paper":"/paper/lightglue-local-feature-matching-at-light","title":"LightGlue: Local Feature Matching at Light Speed","date":"2023-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fabio-sim/LightGlue-ONNX","path":"lightglue_dynamo/models/lightglue.py","file_url":"https://github.com/fabio-sim/LightGlue-ONNX/blob/HEAD/lightglue_dynamo/models/lightglue.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":"ab4f90d2792e9808","mcp_get_code":{"code_sha256":"ab4f90d2792e9808"}},{"arxiv_id":"2306.13643","paper":"/paper/lightglue-local-feature-matching-at-light","title":"LightGlue: Local Feature Matching at Light Speed","date":"2023-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cvg/LightGlue","path":"lightglue/lightglue.py","file_url":"https://github.com/cvg/LightGlue/blob/HEAD/lightglue/lightglue.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":"0a5c71b088578afa","mcp_get_code":{"code_sha256":"0a5c71b088578afa"}},{"arxiv_id":"2306.11641","paper":"/paper/salsa-verde-a-machine-learning-attack-on","title":"SALSA VERDE: a machine learning attack on Learning With Errors with sparse small secrets","date":null,"month_inferred_from_arxiv_id":"2023-06","title_source":"archive","repo":"facebookresearch/verde","path":"src/train/model/transformer.py","file_url":"https://github.com/facebookresearch/verde/blob/HEAD/src/train/model/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"166dadb82071acb9","mcp_get_code":{"code_sha256":"166dadb82071acb9"}},{"arxiv_id":"2305.06588","paper":"/paper/hahe-hierarchical-attention-for-hyper","title":"HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level","date":"2023-05-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lhrlab/hahe","path":"src/transformer.py","file_url":"https://github.com/lhrlab/hahe/blob/HEAD/src/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"61b713fd88663e63","mcp_get_code":{"code_sha256":"61b713fd88663e63"}},{"arxiv_id":"2303.09268","paper":"/paper/stylerdalle-language-guided-style-transfer","title":"StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model","date":"2023-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zipengxuc/StylerDALLE","path":"module.py","file_url":"https://github.com/zipengxuc/StylerDALLE/blob/HEAD/module.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d8a8105c0e3bfb0","mcp_get_code":{"code_sha256":"0d8a8105c0e3bfb0"}},{"arxiv_id":"2302.06881","paper":"/paper/simplekt-a-simple-but-tough-to-beat-baseline","title":"simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge Tracing","date":"2023-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pykt-team/pykt-toolkit","path":"pykt/models/simplekt.py","file_url":"https://github.com/pykt-team/pykt-toolkit/blob/HEAD/pykt/models/simplekt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"29b9654280d01c8a","mcp_get_code":{"code_sha256":"29b9654280d01c8a"}},{"arxiv_id":"2205.03806","paper":"/paper/transformer-tracking-with-cyclic-shifting","title":"Transformer Tracking with Cyclic Shifting Window Attention","date":"2022-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SkyeSong38/CSWinTT","path":"lib/models/cswintt/transformer_cs.py","file_url":"https://github.com/SkyeSong38/CSWinTT/blob/HEAD/lib/models/cswintt/transformer_cs.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9a4b8a925c8b46b4","mcp_get_code":{"code_sha256":"9a4b8a925c8b46b4"}},{"arxiv_id":"2203.13131","paper":"/paper/make-a-scene-scene-based-text-to-image","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","date":"2022-03-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CasualGANPapers/Make-A-Scene","path":"models/transformer.py","file_url":"https://github.com/CasualGANPapers/Make-A-Scene/blob/HEAD/models/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a73f4b74b84d9692","mcp_get_code":{"code_sha256":"a73f4b74b84d9692"}},{"arxiv_id":"2202.06028","paper":"/paper/octattention-octree-based-large-scale","title":"OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression","date":"2022-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zb12138/OctAttention","path":"octAttention.py","file_url":"https://github.com/zb12138/OctAttention/blob/HEAD/octAttention.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":"fe7c5d69d63b47f1","mcp_get_code":{"code_sha256":"fe7c5d69d63b47f1"}},{"arxiv_id":"2202.00259","paper":"/paper/detecting-human-object-interactions-with-2","title":"Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics","date":"2022-02-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JacobYuan7/OCN-HOI-Benchmark","path":"models/hoi.py","file_url":"https://github.com/JacobYuan7/OCN-HOI-Benchmark/blob/HEAD/models/hoi.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":"dafcb62dbe894ef0","mcp_get_code":{"code_sha256":"dafcb62dbe894ef0"}},{"arxiv_id":"2107.03502","paper":"/paper/csdi-conditional-score-based-diffusion-models","title":"CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation","date":"2021-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adrianatienza1996/DiffusionModels","path":"CSDI/model.py","file_url":"https://github.com/adrianatienza1996/DiffusionModels/blob/HEAD/CSDI/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4a2a993673dda35a","mcp_get_code":{"code_sha256":"4a2a993673dda35a"}},{"arxiv_id":"2105.11269","paper":"/paper/neural-machine-translation-with-monolingual","title":"Neural Machine Translation with Monolingual Translation Memory","date":"2021-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jcyk/copyisallyouneed","path":"generator.py","file_url":"https://github.com/jcyk/copyisallyouneed/blob/HEAD/generator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c30426c3b9c4f48a","mcp_get_code":{"code_sha256":"c30426c3b9c4f48a"}},{"arxiv_id":"2103.04256","paper":"/paper/robust-point-cloud-registration-framework","title":"Robust Point Cloud Registration Framework Based on Deep Graph Matching","date":"2021-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhileichen99/utopic","path":"models/architecture.py","file_url":"https://github.com/zhileichen99/utopic/blob/HEAD/models/architecture.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7c8bbdde4d49d75f","mcp_get_code":{"code_sha256":"7c8bbdde4d49d75f"}},{"arxiv_id":"2010.11929","paper":"/paper/an-image-is-worth-16x16-words-transformers-1","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","date":"2020-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"explainingai-code/VIT-Pytorch","path":"model/transformer.py","file_url":"https://github.com/explainingai-code/VIT-Pytorch/blob/HEAD/model/transformer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"39a0e7e04a621bfd","mcp_get_code":{"code_sha256":"39a0e7e04a621bfd"}},{"arxiv_id":"2005.00697","paper":"/paper/deformer-decomposing-pre-trained-transformers","title":"DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering","date":"2020-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"StonyBrookNLP/deformer","path":"models/layers/transformer.py","file_url":"https://github.com/StonyBrookNLP/deformer/blob/HEAD/models/layers/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"28514670ab26db66","mcp_get_code":{"code_sha256":"28514670ab26db66"}},{"arxiv_id":"2004.05572","paper":"/paper/amr-parsing-via-graph-sequence-iterative","title":"AMR Parsing via Graph-Sequence Iterative Inference","date":"2020-04-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bjascob/amrlib","path":"amrlib/models/parse_gsii/modules/parser.py","file_url":"https://github.com/bjascob/amrlib/blob/HEAD/amrlib/models/parse_gsii/modules/parser.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8e5d31580fcebd5a","mcp_get_code":{"code_sha256":"8e5d31580fcebd5a"}},{"arxiv_id":"1909.11942","paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xinyooo/ALBERT4Rec","path":"models/albert_modules/albert.py","file_url":"https://github.com/xinyooo/ALBERT4Rec/blob/HEAD/models/albert_modules/albert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d36a9fea67ab62a3","mcp_get_code":{"code_sha256":"d36a9fea67ab62a3"}},{"arxiv_id":"1909.11942","paper":"/paper/albert-a-lite-bert-for-self-supervised","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","date":"2019-09-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vvvm23/albert","path":"albert/model.py","file_url":"https://github.com/vvvm23/albert/blob/HEAD/albert/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3fbbc185d6497778","mcp_get_code":{"code_sha256":"3fbbc185d6497778"}},{"arxiv_id":"1901.02860","paper":"/paper/transformer-xl-attentive-language-models","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","date":"2019-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opendilab/DI-engine","path":"ding/torch_utils/network/transformer.py","file_url":"https://github.com/opendilab/DI-engine/blob/HEAD/ding/torch_utils/network/transformer.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":"b28585d20fefea46","mcp_get_code":{"code_sha256":"b28585d20fefea46"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qywu/Chinese-GPT","path":"chinese_gpt/gpt_modeling.py","file_url":"https://github.com/qywu/Chinese-GPT/blob/HEAD/chinese_gpt/gpt_modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"07f05b67a5afe0dd","mcp_get_code":{"code_sha256":"07f05b67a5afe0dd"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agentdr1/la_mil","path":"tmil/t_mil.py","file_url":"https://github.com/agentdr1/la_mil/blob/HEAD/tmil/t_mil.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3c71470e7821b3d0","mcp_get_code":{"code_sha256":"3c71470e7821b3d0"}},{"arxiv_id":"1706.03762","paper":"/paper/attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vpj/jax_transformer","path":"transformer.py","file_url":"https://github.com/vpj/jax_transformer/blob/HEAD/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"61e50e597800c80e","mcp_get_code":{"code_sha256":"61e50e597800c80e"}}]}