{"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/bertintermediate","entry":"BertIntermediate","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":15,"n_papers_ran":15,"n_papers_ran_no_instrument_failure":15,"n_papers_ran_instrument_only":0,"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":20,"n_samples_ran":20,"n_samples_constructed":17,"n_samples_ran_checked":20,"n_samples_instrument":0,"n_samples_unverified":0,"n_samples_fingerprinted":18,"n_places":20,"n_places_pointer_only":9,"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":0,"ran_fixture":0,"ran":20,"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":"2603.05969","arxiv_id_is_arxiv":true,"paper":"/paper/arxiv-2603-05969","title":"Imagine How To Change: Explicit Procedure Modeling for Change Captioning","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"BlueberryOreo/ProCap","path":"src/rtransformer/model.py","file_url":"https://github.com/BlueberryOreo/ProCap/blob/HEAD/src/rtransformer/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"c2992f5c466c17d4","code_sha256_prefix":"c2992f5c466c17d4","mcp_get_code":{"code_sha256":"c2992f5c466c17d4"}},{"arxiv_id":"2505.19525","arxiv_id_is_arxiv":true,"paper":"/paper/rethinking-gating-mechanism-in-sparse-moe","title":"Rethinking Gating Mechanism in Sparse MoE: Handling Arbitrary Modality Inputs with Confidence-Guided Gate","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zehuiwu/MMML","path":"utils/cross_attn_encoder.py","file_url":"https://github.com/zehuiwu/MMML/blob/HEAD/utils/cross_attn_encoder.py","status":"ran","verification_level":1,"contract_check":null,"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, zehuiwu/MMML when it was checked","code_sha256":"10838ca8dd1e6973","code_sha256_prefix":"10838ca8dd1e6973","mcp_get_code":{"code_sha256":"10838ca8dd1e6973"}},{"arxiv_id":"2308.12587","arxiv_id_is_arxiv":true,"paper":"/paper/grounded-entity-landmark-adaptive-pre","title":"Grounded Entity-Landmark Adaptive Pre-training for Vision-and-Language Navigation","date":"2023-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csir1996/vln-gela","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.py","status":"ran","verification_level":1,"contract_check":null,"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, csir1996/vln-gela when it was checked","code_sha256":"80fb8132656f0023","code_sha256_prefix":"80fb8132656f0023","mcp_get_code":{"code_sha256":"80fb8132656f0023"}},{"arxiv_id":"2305.12074","arxiv_id_is_arxiv":true,"paper":"/paper/disco-distilled-student-models-co-training","title":"DisCo: Distilled Student Models Co-training for Semi-supervised Text Mining","date":"2023-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"litesslhub/disco","path":"src/model.py","file_url":"https://github.com/litesslhub/disco/blob/HEAD/src/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, litesslhub/disco when it was checked","code_sha256":"954a1d17fbc63ebc","code_sha256_prefix":"954a1d17fbc63ebc","mcp_get_code":{"code_sha256":"954a1d17fbc63ebc"}},{"arxiv_id":"2305.03602","arxiv_id_is_arxiv":true,"paper":"/paper/a-dual-semantic-aware-recurrent-global","title":"A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language Navigation","date":"2023-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CrystalSixone/DSRG","path":"finetune_src/models/vilmodel.py","file_url":"https://github.com/CrystalSixone/DSRG/blob/HEAD/finetune_src/models/vilmodel.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":"cd1fc93df76d6f16","code_sha256_prefix":"cd1fc93df76d6f16","mcp_get_code":{"code_sha256":"cd1fc93df76d6f16"}},{"arxiv_id":"2304.08682","arxiv_id_is_arxiv":true,"paper":"/paper/learning-situation-hyper-graphs-for-video","title":"Learning Situation Hyper-Graphs for Video Question Answering","date":"2023-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aurooj/SHG-VQA","path":"AGQA/src/lxrt/modeling_capsbert.py","file_url":"https://github.com/aurooj/SHG-VQA/blob/HEAD/AGQA/src/lxrt/modeling_capsbert.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, aurooj/SHG-VQA when it was checked","code_sha256":"07fe34e1f674c0cc","code_sha256_prefix":"07fe34e1f674c0cc","mcp_get_code":{"code_sha256":"07fe34e1f674c0cc"}},{"arxiv_id":"2210.08714","arxiv_id_is_arxiv":true,"paper":"/paper/selective-query-guided-debiasing-network-for","title":"Selective Query-guided Debiasing for Video Corpus Moment Retrieval","date":"2022-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dbstjswo505/SQuiDNet","path":"model/squidnet.py","file_url":"https://github.com/dbstjswo505/SQuiDNet/blob/HEAD/model/squidnet.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b25762789d877739","code_sha256_prefix":"b25762789d877739","mcp_get_code":{"code_sha256":"b25762789d877739"}},{"arxiv_id":"2210.08465","arxiv_id_is_arxiv":true,"paper":"/paper/character-centric-story-visualization-via","title":"Character-Centric Story Visualization via Visual Planning and Token Alignment","date":"2022-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adymaharana/VLCStoryGan","path":"vlcgan/model.py","file_url":"https://github.com/adymaharana/VLCStoryGan/blob/HEAD/vlcgan/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"455739c5ad6b2387","code_sha256_prefix":"455739c5ad6b2387","mcp_get_code":{"code_sha256":"455739c5ad6b2387"}},{"arxiv_id":"2205.00274","arxiv_id_is_arxiv":true,"paper":"/paper/clues-before-answers-generation-enhanced","title":"Clues Before Answers: Generation-Enhanced Multiple-Choice QA","date":"2022-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nju-websoft/GenMC","path":"model/modeling_genmc.py","file_url":"https://github.com/nju-websoft/GenMC/blob/HEAD/model/modeling_genmc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"9d9d13aefaa0121e","code_sha256_prefix":"9d9d13aefaa0121e","mcp_get_code":{"code_sha256":"9d9d13aefaa0121e"}},{"arxiv_id":"2110.13309","arxiv_id_is_arxiv":true,"paper":"/paper/history-aware-multimodal-transformer-for","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","date":"2021-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cshizhe/vln-hamt","path":"finetune_src/models/vilmodel_cmt.py","file_url":"https://github.com/cshizhe/vln-hamt/blob/HEAD/finetune_src/models/vilmodel_cmt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"97d0724e78e93d36","code_sha256_prefix":"97d0724e78e93d36","mcp_get_code":{"code_sha256":"97d0724e78e93d36"}},{"arxiv_id":"2106.14019","arxiv_id_is_arxiv":true,"paper":"/paper/umic-an-unreferenced-metric-for-image","title":"UMIC: An Unreferenced Metric for Image Captioning via Contrastive Learning","date":"2021-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hwanheelee1993/UMIC","path":"model/ce.py","file_url":"https://github.com/hwanheelee1993/UMIC/blob/HEAD/model/ce.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"f7d5bced2dfc431a","code_sha256_prefix":"f7d5bced2dfc431a","mcp_get_code":{"code_sha256":"f7d5bced2dfc431a"}},{"arxiv_id":"2105.03761","arxiv_id_is_arxiv":true,"paper":"/paper/e-vil-a-dataset-and-benchmark-for-natural","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","date":"2021-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maximek3/e-ViL","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, maximek3/e-ViL when it was checked","code_sha256":"8c436a09d6111527","code_sha256_prefix":"8c436a09d6111527","mcp_get_code":{"code_sha256":"8c436a09d6111527"}},{"arxiv_id":"2010.08210","arxiv_id_is_arxiv":true,"paper":"/paper/coarse-to-fine-pre-training-for-named-entity","title":"Coarse-to-Fine Pre-training for Named Entity Recognition","date":"2020-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"strawberryx/CoFEE","path":"model/bert_mrc_ner_cluster.py","file_url":"https://github.com/strawberryx/CoFEE/blob/HEAD/model/bert_mrc_ner_cluster.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, strawberryx/CoFEE when it was checked","code_sha256":"d6fda06a2ac2d1bd","code_sha256_prefix":"d6fda06a2ac2d1bd","mcp_get_code":{"code_sha256":"d6fda06a2ac2d1bd"}},{"arxiv_id":"1907.11692","arxiv_id_is_arxiv":true,"paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data","path":"run_hbm.py","file_url":"https://github.com/GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data/blob/HEAD/run_hbm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data when it was checked","code_sha256":"6e60ffe93c5ec5fa","code_sha256_prefix":"6e60ffe93c5ec5fa","mcp_get_code":{"code_sha256":"6e60ffe93c5ec5fa"}},{"arxiv_id":"1810.04805","arxiv_id_is_arxiv":true,"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":"cedrickchee/pytorch-pretrained-BERT","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/cedrickchee/pytorch-pretrained-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"c7123d4962da3767","code_sha256_prefix":"c7123d4962da3767","mcp_get_code":{"code_sha256":"c7123d4962da3767"}},{"arxiv_id":"1810.04805","arxiv_id_is_arxiv":true,"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":"derronxu/sparsebert","path":"SparseBERT/main_functions/transformer/modeling.py","file_url":"https://github.com/derronxu/sparsebert/blob/HEAD/SparseBERT/main_functions/transformer/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, derronxu/sparsebert when it was checked","code_sha256":"f27f0935fbe1b62b","code_sha256_prefix":"f27f0935fbe1b62b","mcp_get_code":{"code_sha256":"f27f0935fbe1b62b"}},{"arxiv_id":"1810.04805","arxiv_id_is_arxiv":true,"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":"lonePatient/ERNIE-text-classification-pytorch","path":"pyernie/model/ernie/modeling.py","file_url":"https://github.com/lonePatient/ERNIE-text-classification-pytorch/blob/HEAD/pyernie/model/ernie/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, lonePatient/ERNIE-text-classification-pytorch when it was checked","code_sha256":"9597f5146c4fa55c","code_sha256_prefix":"9597f5146c4fa55c","mcp_get_code":{"code_sha256":"9597f5146c4fa55c"}},{"arxiv_id":"1810.04805","arxiv_id_is_arxiv":true,"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":"EuphoriaYan/bert_component","path":"layers/bert_basic_model.py","file_url":"https://github.com/EuphoriaYan/bert_component/blob/HEAD/layers/bert_basic_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"fe52ecd17f753018","code_sha256_prefix":"fe52ecd17f753018","mcp_get_code":{"code_sha256":"fe52ecd17f753018"}},{"arxiv_id":"1810.04805","arxiv_id_is_arxiv":true,"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":"Impavidity/relogic","path":"relogic/logickit/inference/modeling.py","file_url":"https://github.com/Impavidity/relogic/blob/HEAD/relogic/logickit/inference/modeling.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"622c5fc2c7a23655","code_sha256_prefix":"622c5fc2c7a23655","mcp_get_code":{"code_sha256":"622c5fc2c7a23655"}},{"arxiv_id":"1810.04805","arxiv_id_is_arxiv":true,"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":"yifding/hetseq","path":"hetseq/bert_modeling.py","file_url":"https://github.com/yifding/hetseq/blob/HEAD/hetseq/bert_modeling.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":"4073de88226e1038","code_sha256_prefix":"4073de88226e1038","mcp_get_code":{"code_sha256":"4073de88226e1038"}}],"record_sha256":"d59453149d34d0a0f839383b000744ca39f7c95baa934beca08643521c9d9ff3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}