{"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/pooling","entry":"pooling","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":13,"n_papers_ran":6,"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":10,"n_samples_ran":4,"n_samples_fingerprinted":1,"n_places":13,"n_places_pointer_only":4,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":2,"ran":1,"unverified":6},"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":"2607.21752","paper":"/paper/arxiv-2607-21752","title":"Parameter-free Adaptive Sparse Attention via Compression-Based Content Selection","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"sc782/SBM-Transformer","path":"code/model_wrapper.py","file_url":"https://github.com/sc782/SBM-Transformer/blob/HEAD/code/model_wrapper.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9dbe45c9859b04e5","mcp_get_code":{"code_sha256":"9dbe45c9859b04e5"}},{"arxiv_id":"2603.11327","paper":"/paper/arxiv-2603-11327","title":"Meta-Reinforcement Learning with Self-Reflection for Agentic Search","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"tengxiao1/MR-Search","path":"meta-search/search/index_builder.py","file_url":"https://github.com/tengxiao1/MR-Search/blob/HEAD/meta-search/search/index_builder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8f15fb50de86d072","mcp_get_code":{"code_sha256":"8f15fb50de86d072"}},{"arxiv_id":"2601.14896","paper":"/paper/arxiv-2601-14896","title":"Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"Cherry-qwq/LcRL-Open","path":"search_r1/search/index_builder.py","file_url":"https://github.com/Cherry-qwq/LcRL-Open/blob/HEAD/search_r1/search/index_builder.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":"8f15fb50de86d072","mcp_get_code":{"code_sha256":"8f15fb50de86d072"}},{"arxiv_id":"2505.12260","paper":"/paper/lightretriever-a-llm-based-hybrid-retrieval","title":"LightRetriever: A LLM-based Hybrid Retrieval Architecture with 1000x Faster Query Inference","date":"2025-05-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"caskcsg/lightretriever","path":"src/lightretriever/finetune/dense_pooling.py","file_url":"https://github.com/caskcsg/lightretriever/blob/HEAD/src/lightretriever/finetune/dense_pooling.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":"028d8766e22f9773","mcp_get_code":{"code_sha256":"028d8766e22f9773"}},{"arxiv_id":"2505.04119","paper":"/paper/gaprompt-geometry-aware-point-cloud-prompt","title":"GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model","date":"2025-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhoujiahuan1991/icml2025-gaprompt","path":"models/GAPrompt.py","file_url":"https://github.com/zhoujiahuan1991/icml2025-gaprompt/blob/HEAD/models/GAPrompt.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":"c8323a81e01ee29f","mcp_get_code":{"code_sha256":"c8323a81e01ee29f"}},{"arxiv_id":"2401.11248","paper":"/paper/drop-your-decoder-pre-training-with-bag-of","title":"Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval","date":"2024-01-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ma787639046/bowdpr","path":"src/bowdpr/pretrain/modeling.py","file_url":"https://github.com/ma787639046/bowdpr/blob/HEAD/src/bowdpr/pretrain/modeling.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"28cec7e054181c12","mcp_get_code":{"code_sha256":"28cec7e054181c12"}},{"arxiv_id":"2312.02829","paper":"/paper/mimonets-multiple-input-multiple-output-1","title":"MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition","date":"2023-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IBM/multiple-input-multiple-output-nets","path":"MIMOFormer/code/model_wrapper.py","file_url":"https://github.com/IBM/multiple-input-multiple-output-nets/blob/HEAD/MIMOFormer/code/model_wrapper.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":"9dbe45c9859b04e5","mcp_get_code":{"code_sha256":"9dbe45c9859b04e5"}},{"arxiv_id":"2206.11010","paper":"/paper/agent-based-graph-neural-networks","title":"Agent-based Graph Neural Networks","date":"2022-06-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"karolismart/agentnet","path":"smp_models/utils/layers.py","file_url":"https://github.com/karolismart/agentnet/blob/HEAD/smp_models/utils/layers.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7a693a902861da98","mcp_get_code":{"code_sha256":"7a693a902861da98"}},{"arxiv_id":"2110.08678","paper":"/paper/transformer-with-a-mixture-of-gaussian-keys-1","title":"Improving Transformers with Probabilistic Attention Keys","date":"2021-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"minhtannguyen/transformer-mgk","path":"lra/model_wrapper.py","file_url":"https://github.com/minhtannguyen/transformer-mgk/blob/HEAD/lra/model_wrapper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"e8f5f9eaaaacad5e","mcp_get_code":{"code_sha256":"e8f5f9eaaaacad5e"}},{"arxiv_id":"2010.07717","paper":"/paper/wasserstein-distance-regularized-sequence","title":"Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains","date":"2020-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RUC-WSM/WD-Match","path":"src/model.py","file_url":"https://github.com/RUC-WSM/WD-Match/blob/HEAD/src/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dc02d636fe86e94c","mcp_get_code":{"code_sha256":"dc02d636fe86e94c"}},{"arxiv_id":"1908.00300","paper":"/paper/simple-and-effective-text-matching-with-1","title":"Simple and Effective Text Matching with Richer Alignment Features","date":"2019-08-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alibaba-edu/simple-effective-text-matching","path":"src/modules/pooling.py","file_url":"https://github.com/alibaba-edu/simple-effective-text-matching/blob/HEAD/src/modules/pooling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dc02d636fe86e94c","mcp_get_code":{"code_sha256":"dc02d636fe86e94c"}},{"arxiv_id":"1902.01069","paper":"/paper/a-comprehensive-exploration-on-wikisql-with","title":"A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization","date":"2019-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qjay612/meta_learning_NL2SQL","path":"src/models/model_wikisql.py","file_url":"https://github.com/qjay612/meta_learning_NL2SQL/blob/HEAD/src/models/model_wikisql.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eb5186ba7911c429","mcp_get_code":{"code_sha256":"eb5186ba7911c429"}},{"arxiv_id":"1811.09245","paper":"/paper/tganv2-efficient-training-of-large-models-for","title":"Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN","date":"2018-11-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pfnet-research/tgan2","path":"tgan2/datasets/multi_level.py","file_url":"https://github.com/pfnet-research/tgan2/blob/HEAD/tgan2/datasets/multi_level.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a91291b41bbb98e","mcp_get_code":{"code_sha256":"8a91291b41bbb98e"}}]}